From e8d179036d153a843f0fead1a13aa278109206bb Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 16 Aug 2025 10:08:15 +0600 Subject: [PATCH 01/20] Create devcontainer.json --- .devcontainer/devcontainer.json | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 .devcontainer/devcontainer.json diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json new file mode 100644 index 0000000..39bbd26 --- /dev/null +++ b/.devcontainer/devcontainer.json @@ -0,0 +1,4 @@ +{ + "image": "mcr.microsoft.com/devcontainers/universal:2", + "features": {} +} From 23243e3cbece625843ff0caa938178c8de357aed Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 16 Aug 2025 10:10:31 +0600 Subject: [PATCH 02/20] Create dependabot.yml --- .github/dependabot.yml | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 .github/dependabot.yml diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 0000000..5990d9c --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,11 @@ +# To get started with Dependabot version updates, you'll need to specify which +# package ecosystems to update and where the package manifests are located. +# Please see the documentation for all configuration options: +# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file + +version: 2 +updates: + - package-ecosystem: "" # See documentation for possible values + directory: "/" # Location of package manifests + schedule: + interval: "weekly" From c0bbd2f7fde6665fda8af2367240ae08bc6273e8 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 16 Aug 2025 10:11:22 +0600 Subject: [PATCH 03/20] Create codeql.yml --- .github/workflows/codeql.yml | 96 ++++++++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 .github/workflows/codeql.yml diff --git a/.github/workflows/codeql.yml b/.github/workflows/codeql.yml new file mode 100644 index 0000000..e138dcd --- /dev/null +++ b/.github/workflows/codeql.yml @@ -0,0 +1,96 @@ +# For most projects, this workflow file will not need changing; you simply need +# to commit it to your repository. +# +# You may wish to alter this file to override the set of languages analyzed, +# or to provide custom queries or build logic. +# +# ******** NOTE ******** +# We have attempted to detect the languages in your repository. Please check +# the `language` matrix defined below to confirm you have the correct set of +# supported CodeQL languages. +# +name: "CodeQL Advanced" + +on: + push: + branches: [ "main" ] + pull_request: + branches: [ "main" ] + schedule: + - cron: '20 10 * * 0' + +jobs: + analyze: + name: Analyze (${{ matrix.language }}) + # Runner size impacts CodeQL analysis time. To learn more, please see: + # - https://gh.io/recommended-hardware-resources-for-running-codeql + # - https://gh.io/supported-runners-and-hardware-resources + # - https://gh.io/using-larger-runners (GitHub.com only) + # Consider using larger runners or machines with greater resources for possible analysis time improvements. + runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }} + permissions: + # required for all workflows + security-events: write + + # required to fetch internal or private CodeQL packs + packages: read + + # only required for workflows in private repositories + actions: read + contents: read + + strategy: + fail-fast: false + matrix: + include: + # CodeQL supports the following values keywords for 'language': 'actions', 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'rust', 'swift' + # Use `c-cpp` to analyze code written in C, C++ or both + # Use 'java-kotlin' to analyze code written in Java, Kotlin or both + # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both + # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis, + # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning. + # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how + # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages + steps: + - name: Checkout repository + uses: actions/checkout@v4 + + # Add any setup steps before running the `github/codeql-action/init` action. + # This includes steps like installing compilers or runtimes (`actions/setup-node` + # or others). This is typically only required for manual builds. + # - name: Setup runtime (example) + # uses: actions/setup-example@v1 + + # Initializes the CodeQL tools for scanning. + - name: Initialize CodeQL + uses: github/codeql-action/init@v3 + with: + languages: ${{ matrix.language }} + build-mode: ${{ matrix.build-mode }} + # If you wish to specify custom queries, you can do so here or in a config file. + # By default, queries listed here will override any specified in a config file. + # Prefix the list here with "+" to use these queries and those in the config file. + + # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs + # queries: security-extended,security-and-quality + + # If the analyze step fails for one of the languages you are analyzing with + # "We were unable to automatically build your code", modify the matrix above + # to set the build mode to "manual" for that language. Then modify this step + # to build your code. + # ℹī¸ Command-line programs to run using the OS shell. + # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun + - if: matrix.build-mode == 'manual' + shell: bash + run: | + echo 'If you are using a "manual" build mode for one or more of the' \ + 'languages you are analyzing, replace this with the commands to build' \ + 'your code, for example:' + echo ' make bootstrap' + echo ' make release' + exit 1 + + - name: Perform CodeQL Analysis + uses: github/codeql-action/analyze@v3 + with: + category: "/language:${{matrix.language}}" From ca91ffd23774bbfacabf7ddbd404a34163640761 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 05:30:12 +0600 Subject: [PATCH 04/20] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 151 +++++++++++++++++++++++++++ 1 file changed, 151 insertions(+) create mode 100644 Cosmic_Simulation_AI_and_Audio.ipynb diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb new file mode 100644 index 0000000..bd1903d --- /dev/null +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -0,0 +1,151 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "history_visible": true, + "include_colab_link": true + }, + "language_info": { + "name": "python" + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + } + }, + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Gc4BqPpVpUFa" + }, + "source": [ + "# Setup\n", + "\n", + "Please ensure you have imported a Gemini API key from AI Studio.\n", + "You can do this directly in the Secrets tab on the left.\n", + "\n", + "After doing so, please run the setup cell below." + ] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "_Gimwn69vh42" + }, + "execution_count": 54, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "GYSCOYMTpUFe" + }, + "source": [ + "# Generated Code" + ] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "HHKkGIgntjPg" + }, + "execution_count": 55, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "Add `%load_ext cudf.pandas` before importing pandas to speed up operations using GPU" + ], + "metadata": { + "id": "gqlY0hJZ_HtX" + } + }, + { + "cell_type": "code", + "source": [ + "%load_ext cudf.pandas\n", + "import pandas as pd\n", + "import numpy as np\n", + "\n", + "# Randomly generated dataset of parking violations-\n", + "# Define the number of rows\n", + "num_rows = 1000000\n", + "\n", + "states = [\"NY\", \"NJ\", \"CA\", \"TX\"]\n", + "violations = [\"Double Parking\", \"Expired Meter\", \"No Parking\",\n", + " \"Fire Hydrant\", \"Bus Stop\"]\n", + "vehicle_types = [\"SUBN\", \"SDN\"]\n", + "\n", + "# Create a date range\n", + "start_date = \"2022-01-01\"\n", + "end_date = \"2022-12-31\"\n", + "dates = pd.date_range(start=start_date, end=end_date, freq='D')\n", + "\n", + "# Generate random data\n", + "data = {\n", + " \"Registration State\": np.random.choice(states, size=num_rows),\n", + " \"Violation Description\": np.random.choice(violations, size=num_rows),\n", + " \"Vehicle Body Type\": np.random.choice(vehicle_types, size=num_rows),\n", + " \"Issue Date\": np.random.choice(dates, size=num_rows),\n", + " \"Ticket Number\": np.random.randint(1000000000, 9999999999, size=num_rows)\n", + "}\n", + "\n", + "# Create a DataFrame\n", + "df = pd.DataFrame(data)\n", + "\n", + "# Which parking violation is most commonly committed by vehicles from various U.S states?\n", + "\n", + "(df[[\"Registration State\", \"Violation Description\"]] # get only these two columns\n", + " .value_counts() # get the count of offences per state and per type of offence\n", + " .groupby(\"Registration State\") # group by state\n", + " .head(1) # get the first row in each group (the type of offence with the largest count)\n", + " .sort_index() # sort by state name\n", + " .reset_index()\n", + ")" + ], + "metadata": { + "id": "Qd6wJzyz_HtY", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 106 + }, + "outputId": "1986b38a-e747-48a0-ccf3-3bdf6d73971b" + }, + "execution_count": 56, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " Unrecognized magic \u001b[36m%load_ext\u001b[39m.\n", + "\n", + " Julia does not use the IPython \u001b[36m%magic\u001b[39m syntax. To interact with the IJulia\n", + " kernel, use \u001b[36mIJulia.somefunction(...)\u001b[39m, for example. Julia macros, string\n", + " macros, and functions can be used to accomplish most of the other\n", + " functionalities of IPython magics." + ], + "text/markdown": "Unrecognized magic `%load_ext`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", + "text/latex": "Unrecognized magic \\texttt{\\%load\\_ext}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + }, + "metadata": {} + } + ] + } + ] +} \ No newline at end of file From a8e22c735e7ed0a0580d47031ae23140418daa24 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 05:30:32 +0600 Subject: [PATCH 05/20] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 192 +++++++++++++++++++++++---- 1 file changed, 165 insertions(+), 27 deletions(-) diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb index bd1903d..ccc3e6b 100644 --- a/Cosmic_Simulation_AI_and_Audio.ipynb +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -46,7 +46,28 @@ "metadata": { "id": "_Gimwn69vh42" }, - "execution_count": 54, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "ETeaa1m3pUFc" + }, + "source": [ + "/tmp/ipython-input-9294624.py in ()\n", + " 2 from google.colab import userdata\n", + " 3\n", + "----> 4 os.environ[\"GEMINI_API_🔑\"] = userdata.get(\"GOOGLE_API_🔑\")\n", + "\n", + "/usr/local/lib/python3.12/dist-packages/google/colab/userdata.py in get(🔑)\n", + " 66 raise TimeoutException(🔑)\n", + " 67 if not resp.get('exists', False):\n", + "---> 68 raise SecretNotFoundError(key)\n", + " 69 if not resp.get('access', False):\n", + " 70 raise NotebookAccessError(key)\n" + ], + "execution_count": null, "outputs": [] }, { @@ -64,7 +85,7 @@ "metadata": { "id": "HHKkGIgntjPg" }, - "execution_count": 55, + "execution_count": null, "outputs": [] }, { @@ -120,32 +141,149 @@ ")" ], "metadata": { - "id": "Qd6wJzyz_HtY", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 106 - }, - "outputId": "1986b38a-e747-48a0-ccf3-3bdf6d73971b" + "id": "Qd6wJzyz_HtY" }, - "execution_count": 56, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - " Unrecognized magic \u001b[36m%load_ext\u001b[39m.\n", - "\n", - " Julia does not use the IPython \u001b[36m%magic\u001b[39m syntax. To interact with the IJulia\n", - " kernel, use \u001b[36mIJulia.somefunction(...)\u001b[39m, for example. Julia macros, string\n", - " macros, and functions can be used to accomplish most of the other\n", - " functionalities of IPython magics." - ], - "text/markdown": "Unrecognized magic `%load_ext`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", - "text/latex": "Unrecognized magic \\texttt{\\%load\\_ext}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "IIK75iMVpUFe" + }, + "source": [ + "# @title Default title text\n", + "variable_name = \"AURELION\" # @param {\"type\":\"string\"}\n", + "# To run this code you need to install the following dependencies:\n", + "# pip install google-genai\n", + "\n", + "import base64\n", + "import os\n", + "from google import genai\n", + "from google.genai import types\n", + "\n", + "\n", + "def generate():\n", + " client = genai.Client(\n", + " api_key=os.environ.get(\"GEMINI_API_KEY\"),\n", + " )\n", + "\n", + " model = \"gemini-2.5-flash\"\n", + " contents = [\n", + " types.Content(\n", + " role=\"user\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"\n", + "\n", + "\n", + "https://cosmic-pulse-an-audio-reactive-galaxy-184571359742.us-west1.run.app/\n", + "2025-08-28T21:04:39+00:00\n", + "\n", + "\"\"\"),\n", + " ],\n", + " ),\n", + " types.Content(\n", + " role=\"model\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"**Analyzing Sitemap URLs**\n", + "\n", + "I've extracted the URLs from the XML sitemap provided, specifically focusing on the `` tags. My next step is to begin browsing these identified URLs.\n", + "\n", + "\n", + "\"\"\"),\n", + " types.Part.from_text(text=\"\"\"\n", + "The page \\\"Cosmic Simulation\\\" is a web application that appears to be a 3D visualization of a \\\"cosmic web\\\" or galaxy, with interactive elements and audio reactivity. It allows users to:\n", + "\n", + "* **Generate new cosmos**: Create new cosmic web structures with AI-powered configurations.\n", + "* **Summon probes**: Dispatch AI-guided deep space probes to random stars within the galaxy, which then travel to their target and provide telemetry.\n", + "* **Interact with the simulation**: Click on individual stars to get a poetic, cosmic observation of their properties (color, velocity, region) from an AI.\n", + "* **Control the camera**: Manually control the camera's position and target, or activate an \\\"autopilot\\\" to automatically focus on a random star.\n", + "* **Adjust voice settings**: Change the voice, pitch, and rate of the AI's spoken responses.\n", + "* **Observe system telemetry**: View real-time data such as the current mode (IDLE, MANEUVERING, AUTOPILOT), camera position, velocity, and target, as well as general system messages.\n", + "\n", + "The application uses Three.js for 3D rendering and appears to integrate with a Gemini AI model for generating descriptions and probe missions. It also incorporates audio analysis to create visual effects that react to sound.\"\"\"),\n", + " ],\n", + " ),\n", + " types.Content(\n", + " role=\"user\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"Include \n", + "\n", + "\n", + "https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/\n", + "2025-08-28T21:33:03+00:00\n", + "\n", + "\"\"\"),\n", + " ],\n", + " ),\n", + " types.Content(\n", + " role=\"model\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"**Analyzing the Sitemap Structure**\n", + "\n", + "I've begun examining the XML structure to understand how the sitemap is organized. Initial observations point towards a standard sitemap format, though the specific content related to the provided URL `https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/` needs further investigation. My focus is now on identifying key elements and attributes within the XML that relate to this particular endpoint.\n", + "\n", + "\n", + "**Browsing the Provided URL**\n", + "\n", + "I'm now browsing the URL provided to understand its content. It appears to be an application. My next step will be to summarize my findings, similar to the process used for the sitemap analysis. I'll focus on identifying key features and functionalities based on the app's behavior and the code I can access. I'm keen to see if this aligns with the initial sitemap analysis and expectations.\n", + "\n", + "\n", + "\"\"\"),\n", + " types.Part.from_executable_code(\n", + " code=\"\"\"print(browse(urls=[\\\"https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/\\\"]))\n", + "\"\"\",\n", + " language=types.Language.PYTHON,\n", + " ),\n", + " types.Part.from_code_execution_result(\n", + " outcome=types.Outcome.OUTCOME_OK,\n", + " output=\"\"\"Browsing the web.\"\"\",\n", + " ),\n", + " ],\n", + " ),\n", + " types.Content(\n", + " role=\"user\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"INSERT_INPUT_HERE\"\"\"),\n", + " ],\n", + " ),\n", + " ]\n", + " tools = [\n", + " types.Tool(url_context=types.UrlContext()),\n", + " types.Tool(code_execution=types.ToolCodeExecution),\n", + " types.Tool(googleSearch=types.GoogleSearch(\n", + " )),\n", + " ]\n", + " generate_content_config = types.GenerateContentConfig(\n", + " thinking_config = types.ThinkingConfig(\n", + " thinking_budget=-1,\n", + " ),\n", + " tools=tools,\n", + " )\n", + "\n", + " for chunk in client.models.generate_content_stream(\n", + " model=model,\n", + " contents=contents,\n", + " config=generate_content_config,\n", + " ):\n", + " if (\n", + " chunk.candidates is None\n", + " or chunk.candidates[0].content is None\n", + " or chunk.candidates[0].content.parts is None\n", + " ):\n", + " continue\n", + " if chunk.candidates[0].content.parts[0].text:\n", + " print(chunk.candidates[0].content.parts[0].text, end=\"\")\n", + " if chunk.candidates[0].content.parts[0].executable_code:\n", + " print(chunk.candidates[0].content.parts[0].executable_code)\n", + " if chunk.candidates[0].content.parts[0].code_execution_result:\n", + " print(chunk.candidates[0].content.parts[0].code_execution_result)\n", + "\n", + "if __name__ == \"__main__\":\n", + " generate()\n" + ], + "execution_count": null, + "outputs": [] } ] } \ No newline at end of file From 7598a9ed91fd91f75f3e394bc2a19597e5011b81 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 06:19:52 +0600 Subject: [PATCH 06/20] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 732 +++++++++++++++++++++++++-- 1 file changed, 703 insertions(+), 29 deletions(-) diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb index ccc3e6b..e1c8535 100644 --- a/Cosmic_Simulation_AI_and_Audio.ipynb +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -5,6 +5,7 @@ "colab": { "provenance": [], "history_visible": true, + "toc_visible": true, "include_colab_link": true }, "language_info": { @@ -46,28 +47,7 @@ "metadata": { "id": "_Gimwn69vh42" }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "metadata": { - "id": "ETeaa1m3pUFc" - }, - "source": [ - "/tmp/ipython-input-9294624.py in ()\n", - " 2 from google.colab import userdata\n", - " 3\n", - "----> 4 os.environ[\"GEMINI_API_🔑\"] = userdata.get(\"GOOGLE_API_🔑\")\n", - "\n", - "/usr/local/lib/python3.12/dist-packages/google/colab/userdata.py in get(🔑)\n", - " 66 raise TimeoutException(🔑)\n", - " 67 if not resp.get('exists', False):\n", - "---> 68 raise SecretNotFoundError(key)\n", - " 69 if not resp.get('access', False):\n", - " 70 raise NotebookAccessError(key)\n" - ], - "execution_count": null, + "execution_count": 276, "outputs": [] }, { @@ -85,7 +65,7 @@ "metadata": { "id": "HHKkGIgntjPg" }, - "execution_count": null, + "execution_count": 277, "outputs": [] }, { @@ -141,18 +121,45 @@ ")" ], "metadata": { - "id": "Qd6wJzyz_HtY" + "id": "Qd6wJzyz_HtY", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 106 + }, + "outputId": "030ebe64-9f4b-4428-8f43-cc0040649df6" }, - "execution_count": null, - "outputs": [] + "execution_count": 278, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " Unrecognized magic \u001b[36m%load_ext\u001b[39m.\n", + "\n", + " Julia does not use the IPython \u001b[36m%magic\u001b[39m syntax. To interact with the IJulia\n", + " kernel, use \u001b[36mIJulia.somefunction(...)\u001b[39m, for example. Julia macros, string\n", + " macros, and functions can be used to accomplish most of the other\n", + " functionalities of IPython magics." + ], + "text/markdown": "Unrecognized magic `%load_ext`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", + "text/latex": "Unrecognized magic \\texttt{\\%load\\_ext}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + }, + "metadata": {} + } + ] }, { "cell_type": "code", "metadata": { - "id": "IIK75iMVpUFe" + "id": "IIK75iMVpUFe", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 324 + }, + "outputId": "c7f23e31-c5fa-48ef-d2fd-6b263b82a9be" }, "source": [ - "# @title Default title text\n", + "# An Audio AI Galaxy Simulation\n", "variable_name = \"AURELION\" # @param {\"type\":\"string\"}\n", "# To run this code you need to install the following dependencies:\n", "# pip install google-genai\n", @@ -282,8 +289,675 @@ "if __name__ == \"__main__\":\n", " generate()\n" ], - "execution_count": null, + "execution_count": 292, + "outputs": [ + { + "output_type": "error", + "ename": "LoadError", + "evalue": "ArgumentError: Package base64 not found in current path.\n- Run `import Pkg; Pkg.add(\"base64\")` to install the base64 package.", + "traceback": [ + "ArgumentError: Package base64 not found in current path.\n- Run `import Pkg; Pkg.add(\"base64\")` to install the base64 package.", + "", + "Stacktrace:", + " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", + " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "120019bb" + }, + "source": [ + "# Task\n", + "Create a live, rotating 3D galaxy visualization using the provided image files: \"/content/List_of_galaxies.pdf\", \"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", and \"/content/nasa-shares-new-views.jpg\"." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4caeabe4" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7439d106" + }, + "source": [ + "**Reasoning**:\n", + "Load the images using OpenCV and store them in a list. PDF files cannot be directly loaded as images, so exclude it.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 324 + }, + "id": "05938e12", + "outputId": "a6720b26-1895-45eb-b6eb-3f83509216b4" + }, + "source": [ + "import cv2\n", + "\n", + "image_paths = [\n", + " \"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\",\n", + " \"/content/galaxy-1756314020879.png\",\n", + " \"/content/nasa-shares-new-views.jpg\"\n", + "]\n", + "\n", + "images = []\n", + "for path in image_paths:\n", + " img = cv2.imread(path)\n", + " if img is not None:\n", + " images.append(img)\n", + "\n", + "# No specific preprocessing is needed at this stage based on the instructions.\n", + "# Storing images in a list as requested.\n", + "\n", + "print(f\"Loaded {len(images)} images.\")" + ], + "execution_count": 280, + "outputs": [ + { + "output_type": "error", + "ename": "LoadError", + "evalue": "ArgumentError: Package cv2 not found in current path.\n- Run `import Pkg; Pkg.add(\"cv2\")` to install the cv2 package.", + "traceback": [ + "ArgumentError: Package cv2 not found in current path.\n- Run `import Pkg; Pkg.add(\"cv2\")` to install the cv2 package.", + "", + "Stacktrace:", + " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", + " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "d677b5b8" + }, + "source": [ + "**Reasoning**:\n", + "The previous command failed because the `cv2` package was not found. Install the package using pip.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 106 + }, + "id": "paLtPO5PHPXU", + "outputId": "d03c8533-fb5e-4457-f842-9dfdf722aaf3" + }, + "source": [ + "%pip install opencv-python" + ], + "execution_count": 281, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " Unrecognized magic \u001b[36m%pip\u001b[39m.\n", + "\n", + " Julia does not use the IPython \u001b[36m%magic\u001b[39m syntax. To interact with the IJulia\n", + " kernel, use \u001b[36mIJulia.somefunction(...)\u001b[39m, for example. Julia macros, string\n", + " macros, and functions can be used to accomplish most of the other\n", + " functionalities of IPython magics." + ], + "text/markdown": "Unrecognized magic `%pip`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", + "text/latex": "Unrecognized magic \\texttt{\\%pip}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "a57b7825" + }, + "source": [ + "**Reasoning**:\n", + "The `%pip` magic command is not recognized. Install the package using the standard python command in a code cell.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 324 + }, + "id": "4bfaad5b", + "outputId": "58e88969-797f-4d84-885a-fbcbecd835f1" + }, + "source": [ + "import sys\n", + "!{sys.executable} -m pip install opencv-python" + ], + "execution_count": 282, + "outputs": [ + { + "output_type": "error", + "ename": "LoadError", + "evalue": "ArgumentError: Package sys not found in current path.\n- Run `import Pkg; Pkg.add(\"sys\")` to install the sys package.", + "traceback": [ + "ArgumentError: Package sys not found in current path.\n- Run `import Pkg; Pkg.add(\"sys\")` to install the sys package.", + "", + "Stacktrace:", + " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", + " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "422d7795" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "2ee79f72" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "df756fbc" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The environment is running Julia, not Python, which prevents the use of Python libraries like OpenCV for image processing.\n", + "* Attempts to install `opencv-python` using `%pip` and `!{sys.executable} -m pip install` failed because the commands are Python-specific and not recognized in the Julia environment.\n", + "* The inability to load and process images using the intended Python libraries led to the failure of the subtask.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The task cannot be completed in the current Julia environment as it requires Python-based image processing capabilities.\n", + "* To proceed with the task, a Python environment with necessary image processing libraries like OpenCV would be required.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6cf00e20" + }, + "source": [ + "# Task\n", + "Create a live, rotating 3D galaxy visualization with glowing ray stars that syncs with microphone audio input. Utilize the provided image files (\"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", \"/content/nasa-shares-new-views.jpg\") for textures and visual elements. The visualization should incorporate advanced and potentially novel coding techniques for complex motion, audio reactivity, and visual effects." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7df38c9c" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "1f78b12a" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "fa905a47" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The environment is running a Julia kernel, which does not support the necessary Python image processing libraries (like OpenCV) required for image loading and processing.\n", + "* Consequently, the subtask of loading the galaxy images and creating textures could not be completed.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The current environment is unsuitable for image processing tasks needed for this visualization.\n", + "* To proceed, a different environment with support for image processing libraries (e.g., Python with OpenCV or Pillow) is required.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4d90d5f1" + }, + "source": [ + "# Task\n", + "Create a live, rotating 3D galaxy visualization with glowing ray stars that are audio-reactive to microphone input. Implement mouse and touch screen rotation controls, and incorporate a \"phantom exploration\" feature to seek anomalies within the galaxy. Utilize the provided image data (\"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", \"/content/nasa-shares-new-views.jpg\") and the PDF data (\"/content/List_of_galaxies.pdf\") for potential textures, inspiration, or data points. The code should be highly advanced and incorporate novel techniques for visualization, audio reactivity, and the phantom exploration/anomaly seeking mechanism." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "77c2cb66" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "743cf70c" + }, + "source": [ + "## Advanced 3d model creation\n", + "\n", + "### Subtask:\n", + "Create a sophisticated 3D model that represents a galaxy structure, potentially incorporating particle systems or other complex geometries to represent stars and gas clouds.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "36e97811" + }, + "source": [ + "## Texture mapping and material design\n", + "\n", + "### Subtask:\n", + "Apply the processed galaxy images as textures and design materials that allow for glowing effects on stars.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "46492cbf" + }, + "source": [ + "## Audio input and processing\n", + "\n", + "### Subtask:\n", + "Implement a method to capture audio input from the microphone and process it to extract relevant features (e.g., amplitude, frequency).\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "0df9c504" + }, + "source": [ + "## Audio-reactive animation\n", + "\n", + "### Subtask:\n", + "Develop a system to control the glowing of stars and potentially other visual elements based on the processed audio data.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "be51d7e0" + }, + "source": [ + "## Adding complex motion\n", + "\n", + "### Subtask:\n", + "Implement rotation and potentially other complex movements and transformations to simulate a dynamic, live, rotating galaxy.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6fe578cf" + }, + "source": [ + "## Shader development\n", + "\n", + "### Subtask:\n", + "Write custom shaders to create advanced visual effects, such as realistic glowing stars, nebulae, and potentially unique distortions or transformations based on audio input.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "87ea272a" + }, + "source": [ + "## User input handling\n", + "\n", + "### Subtask:\n", + "Implement mouse and touch screen event handling to allow users to rotate the galaxy visualization.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6c1c5d11" + }, + "source": [ + "## Phantom exploration and anomaly seeking\n", + "\n", + "### Subtask:\n", + "Develop a mechanism for \"phantom exploration\" which could involve:\n", + "- Defining what constitutes an \"anomaly\" within the 3D galaxy model.\n", + "- Implementing a way to navigate through the galaxy, potentially with a \"phantom\" or camera that can explore.\n", + "- Developing an \"anomaly seeking\" algorithm or interactive process that guides the user or the phantom towards anomalies.\n", + "- Visualizing the phantom's path or the anomalies found.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "b5e606db" + }, + "source": [ + "## Optimization and performance\n", + "\n", + "### Subtask:\n", + "Optimize the code and 3D rendering to ensure smooth performance, especially with complex geometries, real-time audio processing, and interactive controls.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "8da3673f" + }, + "source": [ + "## Visualization\n", + "\n", + "### Subtask:\n", + "Display the animated, audio-reactive, and interactive 3D galaxy visualization with the phantom exploration feature.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "8fd42bf1" + }, + "source": [ + "## Documentation and explanation\n", + "\n", + "### Subtask:\n", + "Document the complex code and explain the novel techniques used, including the phantom exploration and anomaly seeking mechanism.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "8f6325fd" + }, + "source": [ + "**Reasoning**:\n", + "Document the complex code and explain the novel techniques used, including the phantom exploration and anomaly seeking mechanism based on the planned approach, acknowledging the environmental limitations.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "485c6dd1" + }, + "source": [ + "# Documentation for the Planned 3D Galaxy Visualization Project\n", + "\n", + "# Introduction\n", + "# This document outlines the planned approach for creating a live, rotating 3D galaxy visualization with glowing ray stars that are audio-reactive to microphone input.\n", + "# It also includes a \"phantom exploration\" feature to seek anomalies within the galaxy.\n", + "# Due to the limitations of the current Julia environment, the code for this project could not be fully implemented or executed.\n", + "# This documentation describes the intended architecture, libraries, and techniques that would have been used in a suitable Python environment.\n", + "\n", + "# 1. Image Preprocessing\n", + "# Intended Approach: Load galaxy images and extract features or create textures.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - OpenCV (`cv2`): For loading and basic image manipulation (resizing, format conversion).\n", + "# - Pillow (PIL): Another option for image loading and processing.\n", + "# - Potential Feature Extraction: Depending on the specific visual effects, techniques like edge detection, color analysis, or texture analysis could be used.\n", + "# Contribution to Visualization: The images would serve as textures for the galaxy model, stars, or background elements, adding visual detail and realism.\n", + "\n", + "# 2. Advanced 3D Model Creation\n", + "# Intended Approach: Create a sophisticated 3D model representing a galaxy structure.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - PyOpenGL or moderngl: For low-level OpenGL access to build complex geometries.\n", + "# - pyglet or Pygame: For creating an OpenGL context and handling windows/events.\n", + "# - Alternatively, a higher-level library like Panda3D or Kivy with its 3D capabilities could be explored, though they might offer less fine-grained control.\n", + "# - Techniques:\n", + "# - Particle Systems: To represent individual stars and gas clouds, allowing for dynamic behavior and large numbers of elements.\n", + "# - Procedural Generation: To create the spiral arms and overall structure of the galaxy based on mathematical models.\n", + "# - Mesh Creation: Building the underlying structure of the galaxy arms or central bulge as meshes.\n", + "# Contribution to Visualization: Provides the fundamental structure and visual elements of the galaxy.\n", + "\n", + "# 3. Texture Mapping and Material Design\n", + "# Intended Approach: Apply processed galaxy images as textures and design materials for glowing effects.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - PyOpenGL or moderngl: For binding textures to 3D models and defining material properties.\n", + "# - Custom Shaders (GLSL): Essential for creating advanced materials, including:\n", + "# - Texture mapping: Applying the loaded images onto the 3D geometry.\n", + "# - Emissive properties: Making stars glow.\n", + "# - Blending: Combining different textures or effects.\n", + "# Contribution to Visualization: Adds visual richness, detail, and special effects like glowing stars.\n", + "\n", + "# 4. Audio Input and Processing\n", + "# Intended Approach: Capture microphone audio and extract relevant features.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - sounddevice: For accessing and capturing audio from the microphone.\n", + "# - NumPy: For numerical operations on audio data.\n", + "# - SciPy: For signal processing techniques (e.g., FFT for frequency analysis).\n", + "# - Techniques:\n", + "# - Amplitude analysis: Measuring the overall loudness of the audio.\n", + "# - Frequency analysis (FFT): Identifying dominant frequencies in the audio.\n", + "# - Feature extraction: Calculating metrics like spectral centroid, flux, etc., depending on the desired audio-reactive effects.\n", + "# Contribution to Visualization: Provides the real-time data stream that drives the audio-reactive animations.\n", + "\n", + "# 5. Audio-Reactive Animation\n", + "# Intended Approach: Control visual elements (e.g., star glowing) based on processed audio data.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - Integration with 3D library (PyOpenGL, moderngl, etc.): To update visual properties based on audio features.\n", + "# - Techniques:\n", + "# - Mapping audio features to visual parameters: For example, mapping amplitude to star brightness or frequency to color.\n", + "# - Animation curves and interpolation: To create smooth transitions in visual effects.\n", + "# - Real-time updates: Updating the visualization in sync with the audio input.\n", + "# Contribution to Visualization: Creates a dynamic and immersive experience where the galaxy reacts to sound.\n", + "\n", + "# 6. Adding Complex Motion\n", + "# Intended Approach: Implement rotation and other complex movements for a dynamic galaxy.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - 3D transformation matrices (using NumPy or a 3D library's built-in functions): For rotation, translation, and scaling.\n", + "# - Techniques:\n", + "# - Quaternions: For smooth and intuitive rotations.\n", + "# - Animation loops: Continuously updating the transformation matrices over time.\n", + "# - Potential for physics simulations: To create more realistic or dynamic movements (though this adds complexity).\n", + "# Contribution to Visualization: Makes the galaxy feel alive and allows for exploration from different angles.\n", + "\n", + "# 7. Shader Development\n", + "# Intended Approach: Write custom shaders for advanced visual effects.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - GLSL (OpenGL Shading Language): The language for writing vertex, fragment, and potentially geometry shaders.\n", + "# - Integration with 3D library (PyOpenGL, moderngl): To compile and use shaders.\n", + "# - Techniques:\n", + "# - Vertex Shaders: To manipulate the position and other attributes of vertices (e.g., for procedural effects or distortions).\n", + "# - Fragment Shaders: To determine the color of each pixel, enabling effects like glowing, coloring based on audio, and complex lighting.\n", + "# - Noise functions (e.g., Perlin noise): For generating organic textures or motion.\n", + "# Contribution to Visualization: Enables high-quality, customizable visual effects that are essential for a compelling galaxy visualization.\n", + "\n", + "# 8. User Input Handling\n", + "# Intended Approach: Implement mouse and touch screen controls for rotation.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - pyglet or Pygame: For handling window events, including mouse and touch input.\n", + "# - Techniques:\n", + "# - Event listeners: To capture mouse movements, clicks, and touch events.\n", + "# - Mapping input to transformations: Translating mouse/touch input into rotations of the galaxy model.\n", + "# - Camera control: Adjusting the camera's position and orientation based on user input.\n", + "# Contribution to Visualization: Allows users to interact with and explore the galaxy.\n", + "\n", + "# 9. Phantom Exploration and Anomaly Seeking\n", + "# Intended Approach: Develop a mechanism for \"phantom exploration\" and \"anomaly seeking\".\n", + "# This is a novel feature with the following intended components:\n", + "# - Defining \"Anomalies\": Anomalies could be defined in several ways within the 3D galaxy model:\n", + "# - Statistical outliers: Stars with unusual properties (e.g., extreme brightness, velocity, or age if such data were available).\n", + "# - Spatial clusters: Regions with a higher density of stars than expected.\n", + "# - Unique textures or visual features: Specific areas of the galaxy model or textures that are visually distinct.\n", + "# - Potentially, anomalies could be procedurally generated or placed at specific coordinates.\n", + "# - Phantom Navigation: A \"phantom\" would represent a point of interest or a camera path that can move through the galaxy.\n", + "# - Autonomous Navigation: The phantom could follow a predefined path, a random walk, or a path guided by the anomaly seeking algorithm.\n", + "# - User-Controlled Navigation: Users could potentially guide the phantom's movement.\n", + "# - Anomaly Seeking Algorithm: This algorithm would guide the phantom or highlight anomalies for the user.\n", + "# - Spatial partitioning (e.g., Octrees or K-d trees): To efficiently search for anomalies within the 3D space.\n", + "# - Proximity search: Finding anomalies within a certain radius of the phantom.\n", + "# - Feature comparison: Comparing the properties of stars or regions to the definition of an anomaly.\n", + "# - Pathfinding algorithms (e.g., A* or Dijkstra's): To calculate a path for the phantom to reach a discovered anomaly.\n", + "# - Visual cues: Highlighting anomalies in the visualization (e.g., changing their color, size, or adding markers).\n", + "# - Visualizing Phantom's Path/Anomalies:\n", + "# - Rendering a trail behind the phantom.\n", + "# - Drawing lines or markers to indicate the location of anomalies.\n", + "# - Changing the camera view to focus on discovered anomalies.\n", + "# Contribution to Visualization: Adds a unique interactive and exploratory element, encouraging users to delve deeper into the galaxy.\n", + "\n", + "# 10. Optimization and Performance\n", + "# Intended Approach: Optimize code and rendering for smooth performance.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - Techniques applied throughout the development process:\n", + "# - Level of Detail (LOD) for distant objects.\n", + "# - Frustum culling to avoid rendering off-screen objects.\n", + "# - Efficient data structures (e.g., for managing millions of stars).\n", + "# - Batching draw calls.\n", + "# - Utilizing shaders for GPU acceleration of visual effects.\n", + "# - Optimizing audio processing to minimize latency.\n", + "# Contribution to Visualization: Ensures a smooth and responsive experience, even with a complex visualization.\n", + "\n", + "# 11. Visualization\n", + "# Intended Approach: Display the animated, audio-reactive, and interactive 3D galaxy visualization.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - A 3D rendering loop using PyOpenGL, moderngl, or a higher-level library.\n", + "# - Integrating all the components: The 3D model, textures, materials, audio processing, animation logic, user input handling, and phantom exploration mechanism would be combined within the rendering loop.\n", + "# Contribution to Visualization: The final output, the interactive and dynamic 3D galaxy visualization.\n", + "\n", + "# Novel Techniques:\n", + "# - Integration of real-time microphone audio analysis to drive complex visual effects in a 3D environment.\n", + "# - The \"phantom exploration\" and \"anomaly seeking\" mechanism as a novel way to interact with and explore a procedurally generated or data-driven 3D space.\n", + "# - Potentially advanced shader techniques for realistic or stylized rendering of stars and nebulae based on audio input.\n", + "\n", + "# Conclusion:\n", + "# This document outlines the planned approach for creating a sophisticated 3D galaxy visualization with advanced features.\n", + "# The implementation was not possible in the current Julia environment due to the lack of necessary libraries for 3D graphics, audio processing, and user interaction.\n", + "# The descriptions provided are based on how this project would be approached in a suitable Python environment with access to relevant libraries." + ], + "execution_count": 283, "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "f9770d7a" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The environment used for the analysis is Julia, which fundamentally lacks the necessary libraries and frameworks for advanced 3D graphics rendering, image processing, real-time audio input/processing, and complex user interaction handling required for the task.\n", + "* Consequently, none of the subtasks, including image preprocessing, 3D model creation, texture mapping, audio processing, animation, shader development, user input handling, phantom exploration, optimization, and visualization, could be completed.\n", + "* The \"phantom exploration and anomaly seeking\" feature was conceptualized to involve defining anomalies (e.g., statistical outliers, spatial clusters), implementing phantom navigation (autonomous or user-controlled), and developing an anomaly-seeking algorithm using techniques like spatial partitioning and proximity search.\n", + "* Documentation of the planned project outlined a comprehensive approach using Python libraries (like OpenCV, PyOpenGL, sounddevice, NumPy, SciPy) which were not available in the execution environment.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The project requires a programming environment with robust support for 3D graphics APIs (like OpenGL), real-time audio processing, and comprehensive input handling. A Python environment with libraries such as PyOpenGL, sounddevice, and relevant visualization tools would be a more suitable choice.\n", + "* Future attempts should focus on setting up a development environment that can accommodate the technical demands of the project before attempting implementation.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5026c6a1" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The environment used for the analysis is Julia, which fundamentally lacks the necessary libraries and frameworks for advanced 3D graphics rendering, image processing, real-time audio input/processing, and complex user interaction handling required for the task.\n", + "* Consequently, none of the subtasks, including image preprocessing, 3D model creation, texture mapping, audio processing, animation, shader development, user input handling, phantom exploration, optimization, and visualization, could be completed.\n", + "* The \"phantom exploration and anomaly seeking\" feature was conceptualized to involve defining anomalies (e.g., statistical outliers, spatial clusters), implementing phantom navigation (autonomous or user-controlled), and developing an anomaly-seeking algorithm using techniques like spatial partitioning and proximity search.\n", + "* Documentation of the planned project outlined a comprehensive approach using Python libraries (like OpenCV, PyOpenGL, sounddevice, NumPy, SciPy) which were not available in the execution environment.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The project requires a programming environment with robust support for 3D graphics APIs (like OpenGL), real-time audio processing, and comprehensive input handling. A Python environment with libraries such as PyOpenGL, sounddevice, and relevant visualization tools would be a more suitable choice.\n", + "* Future attempts should focus on setting up a development environment that can accommodate the technical demands of the project before attempting implementation." + ] } ] } \ No newline at end of file From 2cc07900028b2d7d97b55f9b5624815e139f43e9 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 06:31:12 +0600 Subject: [PATCH 07/20] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 496 +++++++++++++-------------- 1 file changed, 235 insertions(+), 261 deletions(-) diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb index e1c8535..b5550d7 100644 --- a/Cosmic_Simulation_AI_and_Audio.ipynb +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -5,6 +5,9 @@ "colab": { "provenance": [], "history_visible": true, + "collapsed_sections": [ + "Gc4BqPpVpUFa" + ], "toc_visible": true, "include_colab_link": true }, @@ -47,7 +50,7 @@ "metadata": { "id": "_Gimwn69vh42" }, - "execution_count": 276, + "execution_count": 533, "outputs": [] }, { @@ -65,7 +68,7 @@ "metadata": { "id": "HHKkGIgntjPg" }, - "execution_count": 277, + "execution_count": 534, "outputs": [] }, { @@ -126,9 +129,9 @@ "base_uri": "https://localhost:8080/", "height": 106 }, - "outputId": "030ebe64-9f4b-4428-8f43-cc0040649df6" + "outputId": "f091be2b-9b79-4c7f-f31d-ff108c676a2b" }, - "execution_count": 278, + "execution_count": 535, "outputs": [ { "output_type": "display_data", @@ -150,170 +153,12 @@ }, { "cell_type": "code", + "source": [], "metadata": { - "id": "IIK75iMVpUFe", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 324 - }, - "outputId": "c7f23e31-c5fa-48ef-d2fd-6b263b82a9be" - }, - "source": [ - "# An Audio AI Galaxy Simulation\n", - "variable_name = \"AURELION\" # @param {\"type\":\"string\"}\n", - "# To run this code you need to install the following dependencies:\n", - "# pip install google-genai\n", - "\n", - "import base64\n", - "import os\n", - "from google import genai\n", - "from google.genai import types\n", - "\n", - "\n", - "def generate():\n", - " client = genai.Client(\n", - " api_key=os.environ.get(\"GEMINI_API_KEY\"),\n", - " )\n", - "\n", - " model = \"gemini-2.5-flash\"\n", - " contents = [\n", - " types.Content(\n", - " role=\"user\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"\n", - "\n", - "\n", - "https://cosmic-pulse-an-audio-reactive-galaxy-184571359742.us-west1.run.app/\n", - "2025-08-28T21:04:39+00:00\n", - "\n", - "\"\"\"),\n", - " ],\n", - " ),\n", - " types.Content(\n", - " role=\"model\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"**Analyzing Sitemap URLs**\n", - "\n", - "I've extracted the URLs from the XML sitemap provided, specifically focusing on the `` tags. My next step is to begin browsing these identified URLs.\n", - "\n", - "\n", - "\"\"\"),\n", - " types.Part.from_text(text=\"\"\"\n", - "The page \\\"Cosmic Simulation\\\" is a web application that appears to be a 3D visualization of a \\\"cosmic web\\\" or galaxy, with interactive elements and audio reactivity. It allows users to:\n", - "\n", - "* **Generate new cosmos**: Create new cosmic web structures with AI-powered configurations.\n", - "* **Summon probes**: Dispatch AI-guided deep space probes to random stars within the galaxy, which then travel to their target and provide telemetry.\n", - "* **Interact with the simulation**: Click on individual stars to get a poetic, cosmic observation of their properties (color, velocity, region) from an AI.\n", - "* **Control the camera**: Manually control the camera's position and target, or activate an \\\"autopilot\\\" to automatically focus on a random star.\n", - "* **Adjust voice settings**: Change the voice, pitch, and rate of the AI's spoken responses.\n", - "* **Observe system telemetry**: View real-time data such as the current mode (IDLE, MANEUVERING, AUTOPILOT), camera position, velocity, and target, as well as general system messages.\n", - "\n", - "The application uses Three.js for 3D rendering and appears to integrate with a Gemini AI model for generating descriptions and probe missions. It also incorporates audio analysis to create visual effects that react to sound.\"\"\"),\n", - " ],\n", - " ),\n", - " types.Content(\n", - " role=\"user\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"Include \n", - "\n", - "\n", - "https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/\n", - "2025-08-28T21:33:03+00:00\n", - "\n", - "\"\"\"),\n", - " ],\n", - " ),\n", - " types.Content(\n", - " role=\"model\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"**Analyzing the Sitemap Structure**\n", - "\n", - "I've begun examining the XML structure to understand how the sitemap is organized. Initial observations point towards a standard sitemap format, though the specific content related to the provided URL `https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/` needs further investigation. My focus is now on identifying key elements and attributes within the XML that relate to this particular endpoint.\n", - "\n", - "\n", - "**Browsing the Provided URL**\n", - "\n", - "I'm now browsing the URL provided to understand its content. It appears to be an application. My next step will be to summarize my findings, similar to the process used for the sitemap analysis. I'll focus on identifying key features and functionalities based on the app's behavior and the code I can access. I'm keen to see if this aligns with the initial sitemap analysis and expectations.\n", - "\n", - "\n", - "\"\"\"),\n", - " types.Part.from_executable_code(\n", - " code=\"\"\"print(browse(urls=[\\\"https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/\\\"]))\n", - "\"\"\",\n", - " language=types.Language.PYTHON,\n", - " ),\n", - " types.Part.from_code_execution_result(\n", - " outcome=types.Outcome.OUTCOME_OK,\n", - " output=\"\"\"Browsing the web.\"\"\",\n", - " ),\n", - " ],\n", - " ),\n", - " types.Content(\n", - " role=\"user\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"INSERT_INPUT_HERE\"\"\"),\n", - " ],\n", - " ),\n", - " ]\n", - " tools = [\n", - " types.Tool(url_context=types.UrlContext()),\n", - " types.Tool(code_execution=types.ToolCodeExecution),\n", - " types.Tool(googleSearch=types.GoogleSearch(\n", - " )),\n", - " ]\n", - " generate_content_config = types.GenerateContentConfig(\n", - " thinking_config = types.ThinkingConfig(\n", - " thinking_budget=-1,\n", - " ),\n", - " tools=tools,\n", - " )\n", - "\n", - " for chunk in client.models.generate_content_stream(\n", - " model=model,\n", - " contents=contents,\n", - " config=generate_content_config,\n", - " ):\n", - " if (\n", - " chunk.candidates is None\n", - " or chunk.candidates[0].content is None\n", - " or chunk.candidates[0].content.parts is None\n", - " ):\n", - " continue\n", - " if chunk.candidates[0].content.parts[0].text:\n", - " print(chunk.candidates[0].content.parts[0].text, end=\"\")\n", - " if chunk.candidates[0].content.parts[0].executable_code:\n", - " print(chunk.candidates[0].content.parts[0].executable_code)\n", - " if chunk.candidates[0].content.parts[0].code_execution_result:\n", - " print(chunk.candidates[0].content.parts[0].code_execution_result)\n", - "\n", - "if __name__ == \"__main__\":\n", - " generate()\n" - ], - "execution_count": 292, - "outputs": [ - { - "output_type": "error", - "ename": "LoadError", - "evalue": "ArgumentError: Package base64 not found in current path.\n- Run `import Pkg; Pkg.add(\"base64\")` to install the base64 package.", - "traceback": [ - "ArgumentError: Package base64 not found in current path.\n- Run `import Pkg; Pkg.add(\"base64\")` to install the base64 package.", - "", - "Stacktrace:", - " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", - " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" - ] - } - ] + "id": "8HR9qLhAOlsd" + }, + "execution_count": 536, + "outputs": [] }, { "cell_type": "markdown", @@ -325,6 +170,15 @@ "Create a live, rotating 3D galaxy visualization using the provided image files: \"/content/List_of_galaxies.pdf\", \"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", and \"/content/nasa-shares-new-views.jpg\"." ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "EokR_kWwOnGW" + }, + "execution_count": 537, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -337,6 +191,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "VK1djxvoOitN" + }, + "execution_count": 538, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -348,62 +211,6 @@ "\n" ] }, - { - "cell_type": "code", - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 324 - }, - "id": "05938e12", - "outputId": "a6720b26-1895-45eb-b6eb-3f83509216b4" - }, - "source": [ - "import cv2\n", - "\n", - "image_paths = [\n", - " \"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\",\n", - " \"/content/galaxy-1756314020879.png\",\n", - " \"/content/nasa-shares-new-views.jpg\"\n", - "]\n", - "\n", - "images = []\n", - "for path in image_paths:\n", - " img = cv2.imread(path)\n", - " if img is not None:\n", - " images.append(img)\n", - "\n", - "# No specific preprocessing is needed at this stage based on the instructions.\n", - "# Storing images in a list as requested.\n", - "\n", - "print(f\"Loaded {len(images)} images.\")" - ], - "execution_count": 280, - "outputs": [ - { - "output_type": "error", - "ename": "LoadError", - "evalue": "ArgumentError: Package cv2 not found in current path.\n- Run `import Pkg; Pkg.add(\"cv2\")` to install the cv2 package.", - "traceback": [ - "ArgumentError: Package cv2 not found in current path.\n- Run `import Pkg; Pkg.add(\"cv2\")` to install the cv2 package.", - "", - "Stacktrace:", - " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", - " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" - ] - } - ] - }, { "cell_type": "markdown", "metadata": { @@ -423,12 +230,12 @@ "height": 106 }, "id": "paLtPO5PHPXU", - "outputId": "d03c8533-fb5e-4457-f842-9dfdf722aaf3" + "outputId": "c5feceae-f47c-4e2f-9027-e1dd728f807a" }, "source": [ "%pip install opencv-python" ], - "execution_count": 281, + "execution_count": 539, "outputs": [ { "output_type": "display_data", @@ -448,6 +255,15 @@ } ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "xERdbQehOc9t" + }, + "execution_count": 540, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -461,43 +277,12 @@ }, { "cell_type": "code", + "source": [], "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 324 - }, - "id": "4bfaad5b", - "outputId": "58e88969-797f-4d84-885a-fbcbecd835f1" + "id": "oomPQ7gAOhak" }, - "source": [ - "import sys\n", - "!{sys.executable} -m pip install opencv-python" - ], - "execution_count": 282, - "outputs": [ - { - "output_type": "error", - "ename": "LoadError", - "evalue": "ArgumentError: Package sys not found in current path.\n- Run `import Pkg; Pkg.add(\"sys\")` to install the sys package.", - "traceback": [ - "ArgumentError: Package sys not found in current path.\n- Run `import Pkg; Pkg.add(\"sys\")` to install the sys package.", - "", - "Stacktrace:", - " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", - " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" - ] - } - ] + "execution_count": 541, + "outputs": [] }, { "cell_type": "markdown", @@ -523,6 +308,24 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "nC-EQN2iOgDE" + }, + "execution_count": 542, + "outputs": [] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "VPtTWBADOfu9" + }, + "execution_count": 543, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -553,6 +356,15 @@ "Create a live, rotating 3D galaxy visualization with glowing ray stars that syncs with microphone audio input. Utilize the provided image files (\"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", \"/content/nasa-shares-new-views.jpg\") for textures and visual elements. The visualization should incorporate advanced and potentially novel coding techniques for complex motion, audio reactivity, and visual effects." ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "6QWGZk0xOrQG" + }, + "execution_count": 544, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -565,6 +377,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "HQq0lOvdOsEu" + }, + "execution_count": 545, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -577,6 +398,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "Sw3XV9tKOs_O" + }, + "execution_count": 546, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -606,6 +436,15 @@ "Create a live, rotating 3D galaxy visualization with glowing ray stars that are audio-reactive to microphone input. Implement mouse and touch screen rotation controls, and incorporate a \"phantom exploration\" feature to seek anomalies within the galaxy. Utilize the provided image data (\"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", \"/content/nasa-shares-new-views.jpg\") and the PDF data (\"/content/List_of_galaxies.pdf\") for potential textures, inspiration, or data points. The code should be highly advanced and incorporate novel techniques for visualization, audio reactivity, and the phantom exploration/anomaly seeking mechanism." ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "j5Up4iogOuTm" + }, + "execution_count": 547, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -618,6 +457,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "cW5EIi4EOvCu" + }, + "execution_count": 548, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -630,6 +478,15 @@ "Create a sophisticated 3D model that represents a galaxy structure, potentially incorporating particle systems or other complex geometries to represent stars and gas clouds.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "Kn2-TSJ2Ov6v" + }, + "execution_count": 549, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -642,6 +499,15 @@ "Apply the processed galaxy images as textures and design materials that allow for glowing effects on stars.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "1xIVpO6lOwg3" + }, + "execution_count": 550, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -666,6 +532,15 @@ "Develop a system to control the glowing of stars and potentially other visual elements based on the processed audio data.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "yUdzcWyCOyE3" + }, + "execution_count": 551, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -678,6 +553,15 @@ "Implement rotation and potentially other complex movements and transformations to simulate a dynamic, live, rotating galaxy.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "EAiDBHcpOyyH" + }, + "execution_count": 552, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -690,6 +574,15 @@ "Write custom shaders to create advanced visual effects, such as realistic glowing stars, nebulae, and potentially unique distortions or transformations based on audio input.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "JyXLd_uoOz6f" + }, + "execution_count": 553, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -702,6 +595,24 @@ "Implement mouse and touch screen event handling to allow users to rotate the galaxy visualization.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "S6fzvdD5O1gH" + }, + "execution_count": 554, + "outputs": [] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "7Lj0S65PO2nQ" + }, + "execution_count": 555, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -718,6 +629,15 @@ "- Visualizing the phantom's path or the anomalies found.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "v_NK4W7EO334" + }, + "execution_count": 556, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -730,6 +650,15 @@ "Optimize the code and 3D rendering to ensure smooth performance, especially with complex geometries, real-time audio processing, and interactive controls.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "1-j61bg7O5FI" + }, + "execution_count": 557, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -742,6 +671,15 @@ "Display the animated, audio-reactive, and interactive 3D galaxy visualization with the phantom exploration feature.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "dUojeklHO56A" + }, + "execution_count": 558, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -765,6 +703,15 @@ "\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "_TIs_lY3O6xf" + }, + "execution_count": 559, + "outputs": [] + }, { "cell_type": "code", "metadata": { @@ -914,7 +861,16 @@ "# The implementation was not possible in the current Julia environment due to the lack of necessary libraries for 3D graphics, audio processing, and user interaction.\n", "# The descriptions provided are based on how this project would be approached in a suitable Python environment with access to relevant libraries." ], - "execution_count": 283, + "execution_count": 560, + "outputs": [] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "pa7fx_3IO9yJ" + }, + "execution_count": 561, "outputs": [] }, { @@ -938,6 +894,15 @@ "* Future attempts should focus on setting up a development environment that can accommodate the technical demands of the project before attempting implementation.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "mWy7fGpuO_TA" + }, + "execution_count": 562, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -958,6 +923,15 @@ "* The project requires a programming environment with robust support for 3D graphics APIs (like OpenGL), real-time audio processing, and comprehensive input handling. A Python environment with libraries such as PyOpenGL, sounddevice, and relevant visualization tools would be a more suitable choice.\n", "* Future attempts should focus on setting up a development environment that can accommodate the technical demands of the project before attempting implementation." ] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "yYKbRNvXPAug" + }, + "execution_count": 563, + "outputs": [] } ] } \ No newline at end of file From 9776ad32e0bfab15bb02f323763b87842962f85c Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 07:45:35 +0600 Subject: [PATCH 08/20] Created using Colab --- ...Getting_started_with_google_colab_ai.ipynb | 471 ++++++++++++++++++ 1 file changed, 471 insertions(+) create mode 100644 notebooks/Getting_started_with_google_colab_ai.ipynb diff --git a/notebooks/Getting_started_with_google_colab_ai.ipynb b/notebooks/Getting_started_with_google_colab_ai.ipynb new file mode 100644 index 0000000..5029278 --- /dev/null +++ b/notebooks/Getting_started_with_google_colab_ai.ipynb @@ -0,0 +1,471 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "metadata": { + "id": "wdj9RMfoGPC2" + }, + "cell_type": "markdown", + "source": [ + "Colab is making it easier than ever to integrate powerful Generative AI capabilities into your projects. We are launching public preview for a simple and intuitive Python library (google.colab.ai) to access state-of-the-art language models directly within Pro and Pro+ subscriber Colab environments. This means subscribers can spend less time on configuration and set up and more time bringing their ideas to life. With just a few lines of code, you can now perform a variety of tasks:\n", + "- Generate text\n", + "- Translate languages\n", + "- Write creative content\n", + "- Categorize text\n", + "\n", + "Happy Coding!\n", + "\n", + "\n", + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/googlecolab/colabtools/blob/main/notebooks/Getting_started_with_google_colab_ai.ipynb)" + ] + }, + { + "metadata": { + "id": "Ucchuu5vV3Jp", + "outputId": "7b4b87b2-d2ff-41d5-9a10-2465e094a5ef", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "cell_type": "code", + "source": [ + "# @title List available models\n", + "from google.colab import ai\n", + "\n", + "ai.list_models()" + ], + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "['google/gemini-2.0-flash',\n", + " 'google/gemini-2.0-flash-lite',\n", + " 'google/gemini-2.5-flash',\n", + " 'google/gemini-2.5-flash-lite',\n", + " 'google/gemini-2.5-pro',\n", + " 'google/gemma-3-12b',\n", + " 'google/gemma-3-1b',\n", + " 'google/gemma-3-27b',\n", + " 'google/gemma-3-4b']" + ] + }, + "metadata": {}, + "execution_count": 1 + } + ], + "execution_count": 1 + }, + { + "metadata": { + "id": "LjfCGEpzDsD9" + }, + "cell_type": "markdown", + "source": [ + "Choosing a Model\n", + "The model names give you a hint about their capabilities and intended use:\n", + "\n", + "Pro: These are the most capable models, ideal for complex reasoning, creative tasks, and detailed analysis.\n", + "\n", + "Flash: These models are optimized for high speed and efficiency, making them great for summarization, chat applications, and tasks requiring rapid responses.\n", + "\n", + "Gemma: These are lightweight, open-weight models suitable for a variety of text generation tasks and are great for experimentation." + ] + }, + { + "metadata": { + "id": "R7taibpc7x2l", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "71c9fbea-5765-4159-b765-b77c8b4ab34d" + }, + "cell_type": "code", + "source": [ + "# @title Simple batch generation example\n", + "# Only text-to-text input/output is supported\n", + "from google.colab import ai\n", + "\n", + "response = ai.generate_text(\"What is the capital of France?\")\n", + "print(response)" + ], + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "The capital of France is **Paris**.\n", + "\n" + ] + } + ], + "execution_count": null + }, + { + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "NHO9VzO9AHZP", + "outputId": "f5667fab-a9f3-487f-cff1-5f5ac1549366" + }, + "cell_type": "code", + "source": [ + "# @title Choose a different model\n", + "from google.colab import ai\n", + "\n", + "response = ai.generate_text(\"What is the capital of England\", model_name='google/gemini-2.0-flash-lite')\n", + "print(response)" + ], + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "The capital of England is **London**.\n", + "\n" + ] + } + ], + "execution_count": null + }, + { + "metadata": { + "id": "ysDdFbH_Dgtz" + }, + "cell_type": "markdown", + "source": [ + "For longer text generations, you can stream the response. This displays the output token by token as it's generated, rather than waiting for the entire response to complete. This provides a more interactive and responsive experience. To enable this, simply set stream=True." + ] + }, + { + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "4BNgxiB6--_5", + "outputId": "d3b34d85-1283-4226-861c-73ff431000f7" + }, + "cell_type": "code", + "source": [ + "# @title Simple streaming example\n", + "from google.colab import ai\n", + "\n", + "stream = ai.generate_text(\"Tell me a short story.\", stream=True)\n", + "for text in stream:\n", + " print(text, end='')" + ], + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "The lighthouse keeper, Silas, was a man of routine. Every night, for fifty years, he'd lit the lamp, a beacon against the treacherous rocks that gnawed at the coastline. The sea was his companion, his enemy, and his only confidante. He knew its moods better than his own.\n", + "\n", + "One stormy night, the wind howled like a banshee. The waves crashed against the tower, shaking it to its core. Silas, clinging to the railing, felt a fear he hadn't experienced in decades. This wasn't just a storm; this was a monster.\n", + "\n", + "Suddenly, a small, wooden boat, tossed about like a toy, appeared in the raging sea. He squinted, his heart leaping into his throat. A child. Alone.\n", + "\n", + "Ignoring the raging tempest, Silas raced down the winding stairs, his old bones protesting with every step. He launched his small rescue boat, a fragile craft against the fury of the storm.\n", + "\n", + "Fighting the waves, he reached the child. A girl, no older than seven, clung to the wreckage, her face white with terror. With a strength born of desperation, Silas pulled her aboard.\n", + "\n", + "The journey back was a blur of wind, spray, and fear. The lighthouse seemed miles away, a distant pinprick of hope. But Silas held on, whispering words of comfort to the shivering child.\n", + "\n", + "Finally, they reached the safety of the tower. He wrapped her in blankets, fed her warm soup, and listened to her tale of a capsized fishing boat and a lost father.\n", + "\n", + "As the storm raged outside, the little girl slept, curled up in Silas's worn armchair. Looking at her, a profound shift occurred within him. For fifty years, he’d only kept the light burning. Now, he understood that the light wasn't just a warning. It was a hope, a guiding star. And he, Silas, was more than just a keeper of the light. He was a keeper of hope.\n", + "\n", + "The storm eventually subsided. The girl was reunited with her father, miraculously rescued from a nearby island. Silas, watching them embrace, felt a warmth he hadn't known he was missing. The sea remained, his companion and his enemy. But now, it was also a reminder of the girl he'd saved, and the profound understanding that even in the darkest storms, a single act of kindness could illuminate the world. And that, he knew, was a light worth keeping.\n" + ] + } + ], + "execution_count": null + }, + { + "metadata": { + "id": "CpMmpaVClSBV", + "cellView": "form" + }, + "cell_type": "code", + "source": [ + "#@title Text formatting setup\n", + "#code is not necessary for colab.ai, but is useful in fomatting text chunks\n", + "import sys\n", + "\n", + "class LineWrapper:\n", + " def __init__(self, max_length=80):\n", + " self.max_length = max_length\n", + " self.current_line_length = 0\n", + "\n", + " def print(self, text_chunk):\n", + " i = 0\n", + " n = len(text_chunk)\n", + " while i < n:\n", + " start_index = i\n", + " while i < n and text_chunk[i] not in ' \\n': # Find end of word\n", + " i += 1\n", + " current_word = text_chunk[start_index:i]\n", + "\n", + " delimiter = \"\"\n", + " if i < n: # If not end of chunk, we found a delimiter\n", + " delimiter = text_chunk[i]\n", + " i += 1 # Consume delimiter\n", + "\n", + " if current_word:\n", + " needs_leading_space = (self.current_line_length > 0)\n", + "\n", + " # Case 1: Word itself is too long for a line (must be broken)\n", + " if len(current_word) > self.max_length:\n", + " if needs_leading_space: # Newline if current line has content\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " for char_val in current_word: # Break the long word\n", + " if self.current_line_length >= self.max_length:\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " sys.stdout.write(char_val)\n", + " self.current_line_length += 1\n", + " # Case 2: Word doesn't fit on current line (print on new line)\n", + " elif self.current_line_length + (1 if needs_leading_space else 0) + len(current_word) > self.max_length:\n", + " sys.stdout.write('\\n')\n", + " sys.stdout.write(current_word)\n", + " self.current_line_length = len(current_word)\n", + " # Case 3: Word fits on current line\n", + " else:\n", + " if needs_leading_space:\n", + " # Define punctuation that should not have a leading space\n", + " # when they form an entire \"word\" (token) following another word.\n", + " no_leading_space_punctuation = {\n", + " \",\", \".\", \";\", \":\", \"!\", \"?\", # Standard sentence punctuation\n", + " \")\", \"]\", \"}\", # Closing brackets\n", + " \"'s\", \"'S\", \"'re\", \"'RE\", \"'ve\", \"'VE\", # Common contractions\n", + " \"'m\", \"'M\", \"'ll\", \"'LL\", \"'d\", \"'D\",\n", + " \"n't\", \"N'T\",\n", + " \"...\", \"â€Ļ\" # Ellipses\n", + " }\n", + " if current_word not in no_leading_space_punctuation:\n", + " sys.stdout.write(' ')\n", + " self.current_line_length += 1\n", + " sys.stdout.write(current_word)\n", + " self.current_line_length += len(current_word)\n", + "\n", + " if delimiter == '\\n':\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " elif delimiter == ' ':\n", + " # If line is full and a space delimiter arrives, it implies a wrap.\n", + " if self.current_line_length >= self.max_length:\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + "\n", + " sys.stdout.flush()\n" + ], + "outputs": [], + "execution_count": null + }, + { + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "DWiLPzTnRoy-", + "outputId": "7a9f17e2-ebb4-4bd6-a140-6376235197fb" + }, + "cell_type": "code", + "source": [ + "# @title Formatted streaming example\n", + "from google.colab import ai\n", + "\n", + "wrapper = LineWrapper()\n", + "for chunk in ai.generate_text('Give me a long winded description about the evolution of the Roman Empire.', model_name='google/gemini-2.0-flash', stream=True):\n", + " wrapper.print(chunk)" + ], + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Alright, settle in, because the Roman Empire’s evolution wasn't a tidy, linear\n", + "process. It was a centuries-long, tumultuous transformation, marked by\n", + "breathtaking innovation, brutal power struggles, and a slow, creeping societal\n", + "decay. We're talking about a journey from a humble city-state in the Italian\n", + "peninsula to a sprawling, multifaceted empire that left an indelible mark on\n", + "law, language, architecture, governance, and even our very understanding of the\n", + "world.\n", + "\n", + "It all began, as legend would have it, with Romulus and Remus, twin brothers\n", + "raised by a she-wolf, who founded the city of Rome in 753 BCE. Now, that’s just\n", + "a legend, but it serves to highlight the foundational spirit of Rome: ambition,\n", + "strength, and a certain ruthlessness. Initially, Rome was ruled by a monarchy, a\n", + "system eventually deemed unsatisfactory by the powerful patrician class. This\n", + "led to the **Roman Republic**, established around 509 BCE, a watershed moment\n", + "that would define the early character of Rome.\n", + "\n", + "The Republic was a complex system of checks and balances designed to prevent any\n", + "one individual from gaining absolute power. It involved a Senate, composed of\n", + "elder statesmen primarily drawn from the patrician class, who advised and\n", + "controlled finances; elected officials, such as Cons uls (two elected heads of\n", + "state who served one-year terms), Praetors (judges), and Quaestors (financial\n", + "administrators); and popular assemblies where citizens could theoretically\n", + "participate in governance.\n", + "\n", + "But the Republic wasn't a democracy in the modern sense. Power was largely\n", + "concentrated in the hands of the wealthy aristocratic families, and while\n", + "plebeians (the common citizens) eventually gained some representation through\n", + "tribunes who could veto acts of the Senate, the system remained inherently\n", + "biased.\n", + "\n", + "This period of the Republic was one of relentless expansion. Through a series of\n", + "shrewd alliances and brutal wars, Rome gradually conquered its neighbors,\n", + "including the Etruscans, the Samnites, and various other Italian tribes. These\n", + "victories were crucial because they allowed Rome to control the Italian\n", + "peninsula, providing it with manpower, resources, and a strategic advantage.\n", + "\n", + "The **Punic Wars** against Carthage, a powerful North African trading empire,\n", + "were a defining moment. These protracted conflicts, especially the Second Punic\n", + "War with Hannibal's legendary invasion of Italy, tested Rome's resilience to the\n", + "absolute limit. The Roman resilience, coupled with tactical brilliance and\n", + "strategic advantages, ultimately led to Carthage's complete destruction,\n", + "establishing Rome as the dominant power in the Mediterranean.\n", + "\n", + "However, the very success of the Republic sowed the seeds of its eventual\n", + "downfall. The influx of wealth and slaves from conquered territories created\n", + "vast disparities in wealth. Powerful generals, enriched by conquest and\n", + "commanding loyal armies, began to challenge the authority of the Senate.\n", + "\n", + "Figures like **Marius**, who revolutionized the Roman army by allowing landless\n", + "citizens to enlist, creating a professional, loyal force, and **Sulla**, who\n", + "marched on Rome with his army to seize power, demonstrated the fragility of the\n", + "Republican system. This era saw a series of civil wars and political\n", + "assassinations, further destabilizing the Republic.\n", + "\n", + "The **First Triumvirate**, an informal alliance between Julius Caesar, Pompey,\n", + "and Crassus, was an attempt to stabilize the political landscape, but it\n", + "ultimately collapsed due to ambition and rivalry. **Julius Caesar's** rise to\n", + "power was perhaps the most dramatic turning point. He conquered Gaul, defied the\n", + "Senate, crossed the Rubicon, and ultimately seized control of Rome as dictator\n", + "perpet uo. His reforms, aimed at improving the lives of ordinary citizens and\n", + "consolidating his power, were cut short by his assassination in 44 BCE.\n", + "\n", + "Caesar's assassination sparked another round of civil wars. The **Second\n", + "Triumvirate**, comprised of Mark Antony, Octavian (Caesar's adopted son), and\n", + "Lepidus, emerged to restore order. However, this alliance also disintegrated,\n", + "leading to a power struggle between Antony and Octavian. Octavian's victory at\n", + "the Battle of Actium in 31 BCE marked the definitive end of the Roman Republic.\n", + "\n", + "Octavian, now known as **Augustus **, carefully crafted a new political system.\n", + "He avoided the title of \"king\" or \"dictator,\" instead adopting the title of\n", + "\"Princeps,\" meaning \"first citizen.\" He maintained the facade of the Republic,\n", + "keeping the Senate and other Republican institutions, but in reality, he held\n", + "absolute power. This transition from Republic to Empire was a gradual process,\n", + "cleverly disguised by Augustus. He restructured the army, reformed the tax\n", + "system, initiated massive building projects, and ushered in a period of relative\n", + "peace and prosperity known as the **Pax Romana** (Roman Peace).\n", + "\n", + "The Julio-Claudian dynasty, which followed Augustus, saw a mixed bag of\n", + "emperors. Tiberius was a capable administrator but reclusive, Caligula was\n", + "notorious for his cruelty and extravagance, Claudius was an intellectual who\n", + "expanded the Empire, and Nero was infamous for his alleged role in the Great\n", + "Fire of Rome and his persecution of Christians.\n", + "\n", + "The year 69 CE, known as the ** Year of the Four Emperors**, revealed the\n", + "instability of the imperial succession. After Nero's death, four different\n", + "emperors claimed the throne in rapid succession, highlighting the power of the\n", + "army to make and break emperors.\n", + "\n", + "The Flavian dynasty, established by Vespasian, brought stability and marked the\n", + "beginning of the construction of the Col osseum. The Nerva-Antonine dynasty,\n", + "often considered the \"Five Good Emperors\" (Nerva, Trajan, Hadrian, Antoninus\n", + "Pius, Marcus Aurelius), saw the Roman Empire reach its greatest territorial\n", + "extent and experience a period of unprecedented peace and prosperity.\n", + "\n", + "Trajan conquered Dacia (modern Romania) and expanded the Empire into\n", + "Mesopotamia, while Hadrian focused on consolidating the Empire's borders and\n", + "building defensive fortifications like Hadrian's Wall in Britain. Marcus\n", + "Aurelius, a philosopher-king, faced constant warfare on the frontiers and wrote\n", + "his famous \"Meditations.\"\n", + "\n", + "The reign of Commodus, the son of Marcus Aurelius, marked a turning point. His\n", + "erratic behavior and autocratic rule undermined the stability of the Empire and\n", + "foreshadowed future troubles. The Severan dynasty, which followed, saw the rise\n", + "of powerful military emperors who relied heavily on the army for support. This\n", + "increased military influence further weakened the Senate and other civilian\n", + "institutions.\n", + "\n", + "The 3rd century CE was a period of profound crisis. The **Crisis of the Third\n", + "Century** was characterized by constant civil wars, barbarian invasions,\n", + "economic decline, and plague. The Empire was divided into competing factions,\n", + "and emperors rose and fell in rapid succession.\n", + "\n", + "Emperor Diocletian attempted to stabilize the Empire by dividing it into two\n", + "halves, the Western Roman Empire and the Eastern Roman Empire (later known as\n", + "the Byzantine Empire), each ruled by an Augustus and a Caesar. This tetrarchy, a\n", + "system of four rulers, aimed to provide more effective governance and defense.\n", + "\n", + "Constantine I, also known as Constantine the Great, reunited the Empire and made\n", + "Christianity the favored religion with the Edict of Milan in 313 CE. He also\n", + "moved the capital from Rome to Byzantium, renaming it Constantinople. This shift\n", + "reflected the growing importance of the Eastern provinces and the weakening of\n", + "the Western Empire.\n", + "\n", + "Following Constantine's death, the Empire was again divided between his sons.\n", + "The Western Roman Empire continued to decline, plagued by internal strife,\n", + "economic problems, and constant barbarian invasions. The Eastern Roman Empire,\n", + "with its stronger economy and more stable political system, managed to survive.\n", + "\n", + "The **Visigoths**, fleeing from the Huns, were allowed to settle within the\n", + "Roman Empire, but their mistreatment by Roman officials led to rebellion. In 410\n", + "CE, the Visigoths sacked Rome, a symbolic blow that shook the foundations of the\n", + "Western Roman Empire.\n", + "\n", + "One by one, provinces of the Western Roman Empire were lost to various barbarian\n", + "tribes, including the Vandals, the Franks, the Angles, and the Saxons. In 476\n", + "CE, the last Western Roman Emperor, Romulus Augustulus, was deposed by the\n", + "Germanic chieftain Odoacer, marking the traditional end of the Western Roman\n", + "Empire.\n", + "\n", + "The Eastern Roman Empire, or Byzantine Empire, continued to flourish for another\n", + "thousand years, preserving Roman traditions and culture. It would eventually\n", + "fall to the Ottoman Turks in 1453, with the capture of Constantinople.\n", + "\n", + "So, the evolution of the Roman Empire was a complex and multifaceted process,\n", + "spanning centuries and encompassing profound political, social, economic, and\n", + "cultural transformations. From a small Republic to a vast empire, and eventually\n", + "to a fragmented and weakened state, the Roman story is a testament to the rise\n", + "and fall of civilizations, the enduring power of ideas, and the enduring legacy\n", + "of one of history's most influential empires. It's a story of ambition,\n", + "innovation, ruthlessness, and ultimately, decline – a cautionary tale and a\n", + "source of inspiration that continues to fascinate and influence us today.\n", + "\n" + ] + } + ], + "execution_count": null + } + ], + "metadata": { + "colab": { + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file From dcb916c61479506a27cb9884853d4cebc719f3a2 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 07:48:58 +0600 Subject: [PATCH 09/20] Created using Colab --- ...Getting_started_with_google_colab_ai.ipynb | 319 ++---------------- 1 file changed, 31 insertions(+), 288 deletions(-) diff --git a/notebooks/Getting_started_with_google_colab_ai.ipynb b/notebooks/Getting_started_with_google_colab_ai.ipynb index 5029278..ea523ac 100644 --- a/notebooks/Getting_started_with_google_colab_ai.ipynb +++ b/notebooks/Getting_started_with_google_colab_ai.ipynb @@ -1,15 +1,5 @@ { "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "view-in-github", - "colab_type": "text" - }, - "source": [ - "\"Open" - ] - }, { "metadata": { "id": "wdj9RMfoGPC2" @@ -31,7 +21,7 @@ { "metadata": { "id": "Ucchuu5vV3Jp", - "outputId": "7b4b87b2-d2ff-41d5-9a10-2465e094a5ef", + "outputId": "a3004031-0e0c-4f8d-842d-a79421f51e11", "colab": { "base_uri": "https://localhost:8080/" } @@ -60,10 +50,19 @@ ] }, "metadata": {}, - "execution_count": 1 + "execution_count": 27 } ], - "execution_count": 1 + "execution_count": 27 + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "9D74LOIiggIt" + }, + "execution_count": 27, + "outputs": [] }, { "metadata": { @@ -82,61 +81,29 @@ ] }, { + "cell_type": "code", + "source": [], "metadata": { - "id": "R7taibpc7x2l", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "71c9fbea-5765-4159-b765-b77c8b4ab34d" + "id": "8fjql8kzgin1" }, - "cell_type": "code", - "source": [ - "# @title Simple batch generation example\n", - "# Only text-to-text input/output is supported\n", - "from google.colab import ai\n", - "\n", - "response = ai.generate_text(\"What is the capital of France?\")\n", - "print(response)" - ], - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "The capital of France is **Paris**.\n", - "\n" - ] - } - ], - "execution_count": null + "execution_count": 27, + "outputs": [] }, { + "cell_type": "markdown", + "source": [], "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "NHO9VzO9AHZP", - "outputId": "f5667fab-a9f3-487f-cff1-5f5ac1549366" - }, + "id": "cNSefuDZgjqV" + } + }, + { "cell_type": "code", - "source": [ - "# @title Choose a different model\n", - "from google.colab import ai\n", - "\n", - "response = ai.generate_text(\"What is the capital of England\", model_name='google/gemini-2.0-flash-lite')\n", - "print(response)" - ], - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "The capital of England is **London**.\n", - "\n" - ] - } - ], - "execution_count": null + "source": [], + "metadata": { + "id": "0_KsQAqsgkW9" + }, + "execution_count": 27, + "outputs": [] }, { "metadata": { @@ -147,50 +114,6 @@ "For longer text generations, you can stream the response. This displays the output token by token as it's generated, rather than waiting for the entire response to complete. This provides a more interactive and responsive experience. To enable this, simply set stream=True." ] }, - { - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "4BNgxiB6--_5", - "outputId": "d3b34d85-1283-4226-861c-73ff431000f7" - }, - "cell_type": "code", - "source": [ - "# @title Simple streaming example\n", - "from google.colab import ai\n", - "\n", - "stream = ai.generate_text(\"Tell me a short story.\", stream=True)\n", - "for text in stream:\n", - " print(text, end='')" - ], - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "The lighthouse keeper, Silas, was a man of routine. Every night, for fifty years, he'd lit the lamp, a beacon against the treacherous rocks that gnawed at the coastline. The sea was his companion, his enemy, and his only confidante. He knew its moods better than his own.\n", - "\n", - "One stormy night, the wind howled like a banshee. The waves crashed against the tower, shaking it to its core. Silas, clinging to the railing, felt a fear he hadn't experienced in decades. This wasn't just a storm; this was a monster.\n", - "\n", - "Suddenly, a small, wooden boat, tossed about like a toy, appeared in the raging sea. He squinted, his heart leaping into his throat. A child. Alone.\n", - "\n", - "Ignoring the raging tempest, Silas raced down the winding stairs, his old bones protesting with every step. He launched his small rescue boat, a fragile craft against the fury of the storm.\n", - "\n", - "Fighting the waves, he reached the child. A girl, no older than seven, clung to the wreckage, her face white with terror. With a strength born of desperation, Silas pulled her aboard.\n", - "\n", - "The journey back was a blur of wind, spray, and fear. The lighthouse seemed miles away, a distant pinprick of hope. But Silas held on, whispering words of comfort to the shivering child.\n", - "\n", - "Finally, they reached the safety of the tower. He wrapped her in blankets, fed her warm soup, and listened to her tale of a capsized fishing boat and a lost father.\n", - "\n", - "As the storm raged outside, the little girl slept, curled up in Silas's worn armchair. Looking at her, a profound shift occurred within him. For fifty years, he’d only kept the light burning. Now, he understood that the light wasn't just a warning. It was a hope, a guiding star. And he, Silas, was more than just a keeper of the light. He was a keeper of hope.\n", - "\n", - "The storm eventually subsided. The girl was reunited with her father, miraculously rescued from a nearby island. Silas, watching them embrace, felt a warmth he hadn't known he was missing. The sea remained, his companion and his enemy. But now, it was also a reminder of the girl he'd saved, and the profound understanding that even in the darkest storms, a single act of kindness could illuminate the world. And that, he knew, was a light worth keeping.\n" - ] - } - ], - "execution_count": null - }, { "metadata": { "id": "CpMmpaVClSBV", @@ -271,192 +194,12 @@ " sys.stdout.flush()\n" ], "outputs": [], - "execution_count": null - }, - { - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "DWiLPzTnRoy-", - "outputId": "7a9f17e2-ebb4-4bd6-a140-6376235197fb" - }, - "cell_type": "code", - "source": [ - "# @title Formatted streaming example\n", - "from google.colab import ai\n", - "\n", - "wrapper = LineWrapper()\n", - "for chunk in ai.generate_text('Give me a long winded description about the evolution of the Roman Empire.', model_name='google/gemini-2.0-flash', stream=True):\n", - " wrapper.print(chunk)" - ], - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Alright, settle in, because the Roman Empire’s evolution wasn't a tidy, linear\n", - "process. It was a centuries-long, tumultuous transformation, marked by\n", - "breathtaking innovation, brutal power struggles, and a slow, creeping societal\n", - "decay. We're talking about a journey from a humble city-state in the Italian\n", - "peninsula to a sprawling, multifaceted empire that left an indelible mark on\n", - "law, language, architecture, governance, and even our very understanding of the\n", - "world.\n", - "\n", - "It all began, as legend would have it, with Romulus and Remus, twin brothers\n", - "raised by a she-wolf, who founded the city of Rome in 753 BCE. Now, that’s just\n", - "a legend, but it serves to highlight the foundational spirit of Rome: ambition,\n", - "strength, and a certain ruthlessness. Initially, Rome was ruled by a monarchy, a\n", - "system eventually deemed unsatisfactory by the powerful patrician class. This\n", - "led to the **Roman Republic**, established around 509 BCE, a watershed moment\n", - "that would define the early character of Rome.\n", - "\n", - "The Republic was a complex system of checks and balances designed to prevent any\n", - "one individual from gaining absolute power. It involved a Senate, composed of\n", - "elder statesmen primarily drawn from the patrician class, who advised and\n", - "controlled finances; elected officials, such as Cons uls (two elected heads of\n", - "state who served one-year terms), Praetors (judges), and Quaestors (financial\n", - "administrators); and popular assemblies where citizens could theoretically\n", - "participate in governance.\n", - "\n", - "But the Republic wasn't a democracy in the modern sense. Power was largely\n", - "concentrated in the hands of the wealthy aristocratic families, and while\n", - "plebeians (the common citizens) eventually gained some representation through\n", - "tribunes who could veto acts of the Senate, the system remained inherently\n", - "biased.\n", - "\n", - "This period of the Republic was one of relentless expansion. Through a series of\n", - "shrewd alliances and brutal wars, Rome gradually conquered its neighbors,\n", - "including the Etruscans, the Samnites, and various other Italian tribes. These\n", - "victories were crucial because they allowed Rome to control the Italian\n", - "peninsula, providing it with manpower, resources, and a strategic advantage.\n", - "\n", - "The **Punic Wars** against Carthage, a powerful North African trading empire,\n", - "were a defining moment. These protracted conflicts, especially the Second Punic\n", - "War with Hannibal's legendary invasion of Italy, tested Rome's resilience to the\n", - "absolute limit. The Roman resilience, coupled with tactical brilliance and\n", - "strategic advantages, ultimately led to Carthage's complete destruction,\n", - "establishing Rome as the dominant power in the Mediterranean.\n", - "\n", - "However, the very success of the Republic sowed the seeds of its eventual\n", - "downfall. The influx of wealth and slaves from conquered territories created\n", - "vast disparities in wealth. Powerful generals, enriched by conquest and\n", - "commanding loyal armies, began to challenge the authority of the Senate.\n", - "\n", - "Figures like **Marius**, who revolutionized the Roman army by allowing landless\n", - "citizens to enlist, creating a professional, loyal force, and **Sulla**, who\n", - "marched on Rome with his army to seize power, demonstrated the fragility of the\n", - "Republican system. This era saw a series of civil wars and political\n", - "assassinations, further destabilizing the Republic.\n", - "\n", - "The **First Triumvirate**, an informal alliance between Julius Caesar, Pompey,\n", - "and Crassus, was an attempt to stabilize the political landscape, but it\n", - "ultimately collapsed due to ambition and rivalry. **Julius Caesar's** rise to\n", - "power was perhaps the most dramatic turning point. He conquered Gaul, defied the\n", - "Senate, crossed the Rubicon, and ultimately seized control of Rome as dictator\n", - "perpet uo. His reforms, aimed at improving the lives of ordinary citizens and\n", - "consolidating his power, were cut short by his assassination in 44 BCE.\n", - "\n", - "Caesar's assassination sparked another round of civil wars. The **Second\n", - "Triumvirate**, comprised of Mark Antony, Octavian (Caesar's adopted son), and\n", - "Lepidus, emerged to restore order. However, this alliance also disintegrated,\n", - "leading to a power struggle between Antony and Octavian. Octavian's victory at\n", - "the Battle of Actium in 31 BCE marked the definitive end of the Roman Republic.\n", - "\n", - "Octavian, now known as **Augustus **, carefully crafted a new political system.\n", - "He avoided the title of \"king\" or \"dictator,\" instead adopting the title of\n", - "\"Princeps,\" meaning \"first citizen.\" He maintained the facade of the Republic,\n", - "keeping the Senate and other Republican institutions, but in reality, he held\n", - "absolute power. This transition from Republic to Empire was a gradual process,\n", - "cleverly disguised by Augustus. He restructured the army, reformed the tax\n", - "system, initiated massive building projects, and ushered in a period of relative\n", - "peace and prosperity known as the **Pax Romana** (Roman Peace).\n", - "\n", - "The Julio-Claudian dynasty, which followed Augustus, saw a mixed bag of\n", - "emperors. Tiberius was a capable administrator but reclusive, Caligula was\n", - "notorious for his cruelty and extravagance, Claudius was an intellectual who\n", - "expanded the Empire, and Nero was infamous for his alleged role in the Great\n", - "Fire of Rome and his persecution of Christians.\n", - "\n", - "The year 69 CE, known as the ** Year of the Four Emperors**, revealed the\n", - "instability of the imperial succession. After Nero's death, four different\n", - "emperors claimed the throne in rapid succession, highlighting the power of the\n", - "army to make and break emperors.\n", - "\n", - "The Flavian dynasty, established by Vespasian, brought stability and marked the\n", - "beginning of the construction of the Col osseum. The Nerva-Antonine dynasty,\n", - "often considered the \"Five Good Emperors\" (Nerva, Trajan, Hadrian, Antoninus\n", - "Pius, Marcus Aurelius), saw the Roman Empire reach its greatest territorial\n", - "extent and experience a period of unprecedented peace and prosperity.\n", - "\n", - "Trajan conquered Dacia (modern Romania) and expanded the Empire into\n", - "Mesopotamia, while Hadrian focused on consolidating the Empire's borders and\n", - "building defensive fortifications like Hadrian's Wall in Britain. Marcus\n", - "Aurelius, a philosopher-king, faced constant warfare on the frontiers and wrote\n", - "his famous \"Meditations.\"\n", - "\n", - "The reign of Commodus, the son of Marcus Aurelius, marked a turning point. His\n", - "erratic behavior and autocratic rule undermined the stability of the Empire and\n", - "foreshadowed future troubles. The Severan dynasty, which followed, saw the rise\n", - "of powerful military emperors who relied heavily on the army for support. This\n", - "increased military influence further weakened the Senate and other civilian\n", - "institutions.\n", - "\n", - "The 3rd century CE was a period of profound crisis. The **Crisis of the Third\n", - "Century** was characterized by constant civil wars, barbarian invasions,\n", - "economic decline, and plague. The Empire was divided into competing factions,\n", - "and emperors rose and fell in rapid succession.\n", - "\n", - "Emperor Diocletian attempted to stabilize the Empire by dividing it into two\n", - "halves, the Western Roman Empire and the Eastern Roman Empire (later known as\n", - "the Byzantine Empire), each ruled by an Augustus and a Caesar. This tetrarchy, a\n", - "system of four rulers, aimed to provide more effective governance and defense.\n", - "\n", - "Constantine I, also known as Constantine the Great, reunited the Empire and made\n", - "Christianity the favored religion with the Edict of Milan in 313 CE. He also\n", - "moved the capital from Rome to Byzantium, renaming it Constantinople. This shift\n", - "reflected the growing importance of the Eastern provinces and the weakening of\n", - "the Western Empire.\n", - "\n", - "Following Constantine's death, the Empire was again divided between his sons.\n", - "The Western Roman Empire continued to decline, plagued by internal strife,\n", - "economic problems, and constant barbarian invasions. The Eastern Roman Empire,\n", - "with its stronger economy and more stable political system, managed to survive.\n", - "\n", - "The **Visigoths**, fleeing from the Huns, were allowed to settle within the\n", - "Roman Empire, but their mistreatment by Roman officials led to rebellion. In 410\n", - "CE, the Visigoths sacked Rome, a symbolic blow that shook the foundations of the\n", - "Western Roman Empire.\n", - "\n", - "One by one, provinces of the Western Roman Empire were lost to various barbarian\n", - "tribes, including the Vandals, the Franks, the Angles, and the Saxons. In 476\n", - "CE, the last Western Roman Emperor, Romulus Augustulus, was deposed by the\n", - "Germanic chieftain Odoacer, marking the traditional end of the Western Roman\n", - "Empire.\n", - "\n", - "The Eastern Roman Empire, or Byzantine Empire, continued to flourish for another\n", - "thousand years, preserving Roman traditions and culture. It would eventually\n", - "fall to the Ottoman Turks in 1453, with the capture of Constantinople.\n", - "\n", - "So, the evolution of the Roman Empire was a complex and multifaceted process,\n", - "spanning centuries and encompassing profound political, social, economic, and\n", - "cultural transformations. From a small Republic to a vast empire, and eventually\n", - "to a fragmented and weakened state, the Roman story is a testament to the rise\n", - "and fall of civilizations, the enduring power of ideas, and the enduring legacy\n", - "of one of history's most influential empires. It's a story of ambition,\n", - "innovation, ruthlessness, and ultimately, decline – a cautionary tale and a\n", - "source of inspiration that continues to fascinate and influence us today.\n", - "\n" - ] - } - ], - "execution_count": null + "execution_count": 29 } ], "metadata": { "colab": { - "provenance": [], - "include_colab_link": true + "provenance": [] }, "kernelspec": { "name": "python3", From 37a6c0953474e82b5af32c819d85439a0ff4b1a6 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 09:00:27 +0600 Subject: [PATCH 10/20] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 1418 +++++++++++++++++++++++++- 1 file changed, 1363 insertions(+), 55 deletions(-) diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb index b5550d7..0bfd00d 100644 --- a/Cosmic_Simulation_AI_and_Audio.ipynb +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -8,7 +8,6 @@ "collapsed_sections": [ "Gc4BqPpVpUFa" ], - "toc_visible": true, "include_colab_link": true }, "language_info": { @@ -50,7 +49,7 @@ "metadata": { "id": "_Gimwn69vh42" }, - "execution_count": 533, + "execution_count": 10, "outputs": [] }, { @@ -68,7 +67,7 @@ "metadata": { "id": "HHKkGIgntjPg" }, - "execution_count": 534, + "execution_count": 10, "outputs": [] }, { @@ -127,27 +126,90 @@ "id": "Qd6wJzyz_HtY", "colab": { "base_uri": "https://localhost:8080/", - "height": 106 + "height": 211 }, - "outputId": "f091be2b-9b79-4c7f-f31d-ff108c676a2b" + "outputId": "a577bf13-6964-43ec-fcef-02492fd894d2" }, - "execution_count": 535, + "execution_count": 11, "outputs": [ { - "output_type": "display_data", + "output_type": "stream", + "name": "stdout", + "text": [ + "The cudf.pandas extension is already loaded. To reload it, use:\n", + " %reload_ext cudf.pandas\n" + ] + }, + { + "output_type": "execute_result", "data": { "text/plain": [ - " Unrecognized magic \u001b[36m%load_ext\u001b[39m.\n", + " Registration State Violation Description count\n", + "0 CA No Parking 50189\n", + "1 NJ Expired Meter 50216\n", + "2 NY No Parking 50224\n", + "3 TX No Parking 50434" + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Registration StateViolation Descriptioncount
0CANo Parking50189
1NJExpired Meter50216
2NYNo Parking50224
3TXNo Parking50434
\n", + "
" ], - "text/markdown": "Unrecognized magic `%load_ext`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", - "text/latex": "Unrecognized magic \\texttt{\\%load\\_ext}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \")\",\n \"rows\": 4,\n \"fields\": [\n {\n \"column\": \"Registration State\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 4,\n \"samples\": [\n \"NJ\",\n \"TX\",\n \"CA\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Violation Description\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 2,\n \"samples\": [\n \"Expired Meter\",\n \"No Parking\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"count\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 113,\n \"min\": 50189,\n \"max\": 50434,\n \"num_unique_values\": 4,\n \"samples\": [\n 50216,\n 50434\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } }, - "metadata": {} + "metadata": {}, + "execution_count": 11 } ] }, @@ -157,7 +219,7 @@ "metadata": { "id": "8HR9qLhAOlsd" }, - "execution_count": 536, + "execution_count": null, "outputs": [] }, { @@ -176,7 +238,7 @@ "metadata": { "id": "EokR_kWwOnGW" }, - "execution_count": 537, + "execution_count": 11, "outputs": [] }, { @@ -197,7 +259,7 @@ "metadata": { "id": "VK1djxvoOitN" }, - "execution_count": 538, + "execution_count": 11, "outputs": [] }, { @@ -226,32 +288,1244 @@ "cell_type": "code", "metadata": { "colab": { - "base_uri": "https://localhost:8080/", - "height": 106 + "base_uri": "https://localhost:8080/" }, "id": "paLtPO5PHPXU", - "outputId": "c5feceae-f47c-4e2f-9027-e1dd728f807a" + "outputId": "eda4bc3b-e4c4-4b51-a816-81b58f53d6d2" }, "source": [ "%pip install opencv-python" ], - "execution_count": 539, + "execution_count": 12, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Requirement already satisfied: opencv-python in /usr/local/lib/python3.12/dist-packages (4.12.0.88)\n", + "Requirement already satisfied: numpy<2.3.0,>=2 in /usr/local/lib/python3.12/dist-packages (from opencv-python) (2.0.2)\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "from vega_datasets import data\n", + "stocks = data.stocks()\n", + "\n", + "import altair as alt\n", + "alt.Chart(stocks).mark_line().encode(\n", + " x='date:T',\n", + " y='price',\n", + " color='symbol'\n", + ").interactive(bind_y=False)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 368 + }, + "id": "VrcdHkesu8OI", + "outputId": "29435b8d-f857-491f-eb79-7bd7ce4a4872" + }, + "execution_count": 13, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], + "text/plain": [ + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 13 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "# plot the dataset, referencing dataframe column names\n", + "import altair as alt\n", + "alt.Chart(cars).mark_bar().encode(\n", + " x=alt.X('Miles_per_Gallon', bin=True),\n", + " y='count()',\n", + " color='Origin'\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 368 + }, + "id": "pr93d1kBvBHH", + "outputId": "b7f1ec2f-9b27-4a12-d38e-c408aaeefd64" + }, + "execution_count": 14, "outputs": [ { - "output_type": "display_data", + "output_type": "execute_result", "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], "text/plain": [ - " Unrecognized magic \u001b[36m%pip\u001b[39m.\n", + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 14 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "import altair as alt\n", + "\n", + "points = alt.Chart(cars).mark_point().encode(\n", + " x='Year:T',\n", + " y='Miles_per_Gallon',\n", + " color='Origin'\n", + ").properties(\n", + " width=800\n", + ")\n", + "\n", + "lines = alt.Chart(cars).mark_line().encode(\n", + " x='Year:T',\n", + " y='mean(Miles_per_Gallon)',\n", + " color='Origin'\n", + ").properties(\n", + " width=800\n", + ").interactive(bind_y=False)\n", + "\n", + "points + lines" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 388 + }, + "id": "ULhvdA3AvCVm", + "outputId": "022edcc4-78fc-49e0-be17-4b9baca9ada0" + }, + "execution_count": 15, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" ], - "text/markdown": "Unrecognized magic `%pip`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", - "text/latex": "Unrecognized magic \\texttt{\\%pip}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + "text/plain": [ + "alt.LayerChart(...)" + ] }, - "metadata": {} + "metadata": {}, + "execution_count": 15 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "# plot the dataset, referencing dataframe column names\n", + "import altair as alt\n", + "alt.Chart(cars).mark_point().encode(\n", + " x='Horsepower',\n", + " y='Miles_per_Gallon',\n", + " color='Origin'\n", + ").interactive()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 368 + }, + "id": "iRfJrZb1vH76", + "outputId": "c9c24220-9b43-4017-d0a7-08503a4b9d86" + }, + "execution_count": 30, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], + "text/plain": [ + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 30 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "# plot the dataset, referencing dataframe column names\n", + "import altair as alt\n", + "alt.Chart(cars).mark_bar().encode(\n", + " x=alt.X('Miles_per_Gallon', bin=True),\n", + " y='count()',\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 368 + }, + "id": "ieUf_ygVvKjw", + "outputId": "cdfa08c6-3228-4c1f-e041-3d186c5db38c" + }, + "execution_count": 32, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], + "text/plain": [ + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 32 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "# plot the dataset, referencing dataframe column names\n", + "import altair as alt\n", + "alt.Chart(cars).mark_bar().encode(\n", + " x='mean(Miles_per_Gallon)',\n", + " y='Origin',\n", + " color='Origin'\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 123 + }, + "id": "6SOWYxt2vLpr", + "outputId": "8a94d1cc-9c07-4a15-bb23-ee882a3952f0" + }, + "execution_count": 33, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], + "text/plain": [ + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 33 + } + ] + }, + { + "cell_type": "code", + "source": [ + "from google.colab import auth\n", + "auth.authenticate_user()" + ], + "metadata": { + "id": "fC-1Kix5vMg4" + }, + "execution_count": 34, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "import time\n", + "import sys\n", + "from google.colab import output\n", + "\n", + "print('Starting.')\n", + "\n", + "with output.use_tags('some_outputs'):\n", + " sys.stdout.write('working....\\n')\n", + " sys.stdout.flush();\n", + " time.sleep(2)\n", + "\n", + " sys.stdout.write('still working...\\n')\n", + " sys.stdout.flush();\n", + " time.sleep(2)\n", + "\n", + "# Now clear the previous outputs.\n", + "output.clear(output_tags='some_outputs')\n", + "print('All done!')\n" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "VoblcmpyvPF5", + "outputId": "429fe3a9-e5d4-433d-cd2b-f86b3320c090" + }, + "execution_count": 35, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Starting.\n", + "All done!\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "Support for third party widgets will remain active for the duration of the session. To disable support:" + ], + "metadata": { + "id": "em2abCypvNop" + } + }, + { + "cell_type": "code", + "source": [ + "from google.colab import output\n", + "output.disable_custom_widget_manager()" + ], + "metadata": { + "id": "2CPY_udkvNop" + }, + "execution_count": 36, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "project_id = '[your project ID]'" + ], + "metadata": { + "id": "yrElKJx3vNTQ" + }, + "execution_count": 37, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "import bigframes.pandas as bpd\n", + "from google.cloud import bigquery\n", + "\n", + "# Set BigQuery DataFrames options\n", + "bpd.options.bigquery.project = project_id\n", + "bpd.options.bigquery.location = \"US\"" + ], + "metadata": { + "id": "adSrR635vNTQ" + }, + "execution_count": 38, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "df.describe()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "MC8P2TfBvNTQ", + "outputId": "db5961a5-27e4-4a3a-df85-010297ad8325" + }, + "execution_count": 42, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Issue Date Ticket Number\n", + "count 1000000 1.000000e+06\n", + "mean 2022-07-01 23:32:43.411199744 5.499237e+09\n", + "min 2022-01-01 00:00:00 1.000005e+09\n", + "25% 2022-04-02 00:00:00 3.249061e+09\n", + "50% 2022-07-02 00:00:00 5.499907e+09\n", + "75% 2022-10-01 00:00:00 7.748794e+09\n", + "max 2022-12-31 00:00:00 9.999998e+09\n", + "std NaN 2.597215e+09" + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Issue DateTicket Number
count10000001.000000e+06
mean2022-07-01 23:32:43.4111997445.499237e+09
min2022-01-01 00:00:001.000005e+09
25%2022-04-02 00:00:003.249061e+09
50%2022-07-02 00:00:005.499907e+09
75%2022-10-01 00:00:007.748794e+09
max2022-12-31 00:00:009.999998e+09
stdNaN2.597215e+09
\n", + "
" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"df\",\n \"rows\": 8,\n \"fields\": [\n {\n \"column\": \"Issue Date\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": \"1970-01-01 00:00:00.001000\",\n \"max\": \"2022-12-31 00:00:00\",\n \"num_unique_values\": 7,\n \"samples\": [\n \"1000000\",\n \"2022-07-01 23:32:43.411199744\",\n \"2022-10-01 00:00:00\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Ticket Number\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3390298193.6777215,\n \"min\": 1000000.0,\n \"max\": 9999997850.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 5499236759.115837,\n 7748793835.0,\n 1000000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 42 + } + ] + }, + { + "cell_type": "code", + "source": [ + "df.head(10)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 363 + }, + "id": "lpFT7CA1vNTQ", + "outputId": "ce13216b-40d9-4977-952e-ae9250ea4fda" + }, + "execution_count": 43, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Registration State Violation Description Vehicle Body Type Issue Date \\\n", + "0 TX Bus Stop SDN 2022-02-20 \n", + "1 NJ No Parking SUBN 2022-12-30 \n", + "2 CA Fire Hydrant SUBN 2022-02-16 \n", + "3 NJ Expired Meter SDN 2022-07-11 \n", + "4 CA Double Parking SDN 2022-09-02 \n", + "5 CA Fire Hydrant SDN 2022-09-24 \n", + "6 CA No Parking SDN 2022-03-25 \n", + "7 CA Bus Stop SDN 2022-01-28 \n", + "8 NJ Bus Stop SDN 2022-06-09 \n", + "9 NJ Bus Stop SUBN 2022-08-20 \n", + "\n", + " Ticket Number \n", + "0 2366568410 \n", + "1 1858496929 \n", + "2 7980797083 \n", + "3 2267392504 \n", + "4 1711350626 \n", + "5 9937878556 \n", + "6 2006476931 \n", + "7 1905610278 \n", + "8 3630351468 \n", + "9 6807852590 " + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Registration StateViolation DescriptionVehicle Body TypeIssue DateTicket Number
0TXBus StopSDN2022-02-202366568410
1NJNo ParkingSUBN2022-12-301858496929
2CAFire HydrantSUBN2022-02-167980797083
3NJExpired MeterSDN2022-07-112267392504
4CADouble ParkingSDN2022-09-021711350626
5CAFire HydrantSDN2022-09-249937878556
6CANo ParkingSDN2022-03-252006476931
7CABus StopSDN2022-01-281905610278
8NJBus StopSDN2022-06-093630351468
9NJBus StopSUBN2022-08-206807852590
\n", + "
" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "df" + } + }, + "metadata": {}, + "execution_count": 43 + } + ] + }, + { + "cell_type": "code", + "source": [ + "import pandas as pd\n", + "import bigframes.pandas as bpd\n", + "from google.cloud import bigquery\n", + "\n", + "# https://cloud.google.com/resource-manager/docs/creating-managing-projects\n", + "# project_id = '[your Cloud Platform project ID]' # Using project_id from cell yrElKJx3vNTQ\n", + "sample_count = 2000\n", + "\n", + "# Set BigQuery DataFrames options (using location from cell adSrR635vNTQ)\n", + "bpd.close_session()\n", + "bpd.options.bigquery.project = project_id\n", + "bpd.options.bigquery.location = \"US\"\n", + "\n", + "\n", + "row_count = pd.io.gbq.read_gbq('''\n", + " SELECT\n", + " COUNT(*) as total\n", + " FROM `bigquery-public-data.samples.gsod`\n", + "''', project_id=project_id, location=bpd.options.bigquery.location).total[0]\n", + "\n", + "df = pd.io.gbq.read_gbq(f'''\n", + " SELECT\n", + " *\n", + " FROM\n", + " `bigquery-public-data.samples.gsod`\n", + " WHERE RAND() < {sample_count}/{row_count}\n", + "''', project_id=project_id, location=bpd.options.bigquery.location)\n", + "\n", + "print(f'Full dataset has {row_count} rows')" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 628 + }, + "id": "rfbBILTXvMg4", + "outputId": "526f4f0d-4609-47ea-b8e7-b20d012cecb4" + }, + "execution_count": 50, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.12/dist-packages/cudf/pandas/fast_slow_proxy.py:28: FutureWarning: read_gbq is deprecated and will be removed in a future version. Please use pandas_gbq.read_gbq instead: https://pandas-gbq.readthedocs.io/en/latest/api.html#pandas_gbq.read_gbq\n", + " return fn(*args, **kwargs)\n" + ] + }, + { + "output_type": "error", + "ename": "GenericGBQException", + "evalue": "Reason: 400 POST https://bigquery.googleapis.com/bigquery/v2/projects/%5Byour%20Cloud%20Platform%20project%20ID%5D/queries?prettyPrint=false: Invalid project ID '[your Cloud Platform project ID]'. Project IDs must contain 6-63 lowercase letters, digits, or dashes. Some project IDs also include domain name separated by a colon. IDs must start with a letter and may not end with a dash.", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mBadRequest\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/query.py\u001b[0m in \u001b[0;36mtry_query\u001b[0;34m(connector, query_fn)\u001b[0m\n\u001b[1;32m 84\u001b[0m \u001b[0mlogger\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdebug\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Requesting query... \"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 85\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mquery_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 86\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mconcurrent\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfutures\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTimeoutError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mex\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/client.py\u001b[0m in \u001b[0;36mquery_and_wait\u001b[0;34m(self, query, job_config, location, project, api_timeout, wait_timeout, retry, job_retry, page_size, max_results)\u001b[0m\n\u001b[1;32m 3660\u001b[0m \"\"\"\n\u001b[0;32m-> 3661\u001b[0;31m return self._query_and_wait_bigframes(\n\u001b[0m\u001b[1;32m 3662\u001b[0m \u001b[0mquery\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/client.py\u001b[0m in \u001b[0;36m_query_and_wait_bigframes\u001b[0;34m(self, query, job_config, location, project, api_timeout, wait_timeout, retry, job_retry, page_size, max_results, callback)\u001b[0m\n\u001b[1;32m 3706\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3707\u001b[0;31m return _job_helpers.query_and_wait(\n\u001b[0m\u001b[1;32m 3708\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/_job_helpers.py\u001b[0m in \u001b[0;36mquery_and_wait\u001b[0;34m(client, query, job_config, location, project, api_timeout, wait_timeout, retry, job_retry, page_size, max_results, callback)\u001b[0m\n\u001b[1;32m 626\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mjob_retry\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 627\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mjob_retry\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdo_query\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 628\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_wrapped_func\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 293\u001b[0m )\n\u001b[0;32m--> 294\u001b[0;31m return retry_target(\n\u001b[0m\u001b[1;32m 295\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m 155\u001b[0m \u001b[0;31m# defer to shared logic for handling errors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 156\u001b[0;31m next_sleep = _retry_error_helper(\n\u001b[0m\u001b[1;32m 157\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_base.py\u001b[0m in \u001b[0;36m_retry_error_helper\u001b[0;34m(exc, deadline, sleep_iterator, error_list, predicate_fn, on_error_fn, exc_factory_fn, original_timeout)\u001b[0m\n\u001b[1;32m 213\u001b[0m )\n\u001b[0;32m--> 214\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mfinal_exc\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msource_exc\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 215\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mon_error_fn\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m 146\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 147\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 148\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0minspect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misawaitable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/_job_helpers.py\u001b[0m in \u001b[0;36mdo_query\u001b[0;34m()\u001b[0m\n\u001b[1;32m 544\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mretry\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 545\u001b[0;31m response = retry(client._call_api)(\n\u001b[0m\u001b[1;32m 546\u001b[0m \u001b[0mretry\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;31m# We're calling the retry decorator ourselves.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_wrapped_func\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 293\u001b[0m )\n\u001b[0;32m--> 294\u001b[0;31m return retry_target(\n\u001b[0m\u001b[1;32m 295\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m 155\u001b[0m \u001b[0;31m# defer to shared logic for handling errors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 156\u001b[0;31m next_sleep = _retry_error_helper(\n\u001b[0m\u001b[1;32m 157\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_base.py\u001b[0m in \u001b[0;36m_retry_error_helper\u001b[0;34m(exc, deadline, sleep_iterator, error_list, predicate_fn, on_error_fn, exc_factory_fn, original_timeout)\u001b[0m\n\u001b[1;32m 213\u001b[0m )\n\u001b[0;32m--> 214\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mfinal_exc\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msource_exc\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 215\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mon_error_fn\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m 146\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 147\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 148\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0minspect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misawaitable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/client.py\u001b[0m in \u001b[0;36m_call_api\u001b[0;34m(self, retry, span_name, span_attributes, job_ref, headers, **kwargs)\u001b[0m\n\u001b[1;32m 860\u001b[0m ):\n\u001b[0;32m--> 861\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mcall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 862\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/_http/__init__.py\u001b[0m in \u001b[0;36mapi_request\u001b[0;34m(self, method, path, query_params, data, content_type, headers, api_base_url, api_version, expect_json, _target_object, timeout, extra_api_info)\u001b[0m\n\u001b[1;32m 493\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;36m200\u001b[0m \u001b[0;34m<=\u001b[0m \u001b[0mresponse\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstatus_code\u001b[0m \u001b[0;34m<\u001b[0m \u001b[0;36m300\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 494\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mexceptions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_http_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 495\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mBadRequest\u001b[0m: 400 POST https://bigquery.googleapis.com/bigquery/v2/projects/%5Byour%20Cloud%20Platform%20project%20ID%5D/queries?prettyPrint=false: Invalid project ID '[your Cloud Platform project ID]'. Project IDs must contain 6-63 lowercase letters, digits, or dashes. Some project IDs also include domain name separated by a colon. IDs must start with a letter and may not end with a dash.", + "\nThe above exception was the direct cause of the following exception:\n", + "\u001b[0;31mGenericGBQException\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/tmp/ipython-input-401414200.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m row_count = pd.io.gbq.read_gbq('''\n\u001b[0m\u001b[1;32m 16\u001b[0m \u001b[0mSELECT\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 17\u001b[0m \u001b[0mCOUNT\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mtotal\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/cudf/pandas/fast_slow_proxy.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 720\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 721\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mAny\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 722\u001b[0;31m result, _ = _fast_slow_function_call(\n\u001b[0m\u001b[1;32m 723\u001b[0m \u001b[0;31m# We cannot directly call self here because we need it to be\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 724\u001b[0m \u001b[0;31m# converted into either the fast or slow object (by\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/cudf/pandas/fast_slow_proxy.py\u001b[0m in \u001b[0;36m_fast_slow_function_call\u001b[0;34m(func, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1047\u001b[0m \u001b[0m_slow_function_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1048\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mdisable_module_accelerator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1049\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0mslow_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mslow_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1050\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0m_maybe_wrap_result\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfast\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1051\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/cudf/pandas/fast_slow_proxy.py\u001b[0m in \u001b[0;36mcall_operator\u001b[0;34m(fn, args, kwargs)\u001b[0m\n\u001b[1;32m 26\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mcall_operator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 28\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 29\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 30\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas/io/gbq.py\u001b[0m in \u001b[0;36mread_gbq\u001b[0;34m(query, project_id, index_col, col_order, reauth, auth_local_webserver, dialect, location, configuration, credentials, use_bqstorage_api, max_results, progress_bar_type)\u001b[0m\n\u001b[1;32m 205\u001b[0m \u001b[0;31m# END: new kwargs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 206\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 207\u001b[0;31m return pandas_gbq.read_gbq(\n\u001b[0m\u001b[1;32m 208\u001b[0m \u001b[0mquery\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 209\u001b[0m \u001b[0mproject_id\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mproject_id\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/gbq.py\u001b[0m in \u001b[0;36mread_gbq\u001b[0;34m(query_or_table, project_id, index_col, columns, reauth, auth_local_webserver, dialect, location, configuration, credentials, use_bqstorage_api, max_results, verbose, private_key, progress_bar_type, dtypes, auth_redirect_uri, client_id, client_secret, col_order, bigquery_client)\u001b[0m\n\u001b[1;32m 320\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 321\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0m_is_query\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mquery_or_table\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 322\u001b[0;31m final_df = connector.run_query(\n\u001b[0m\u001b[1;32m 323\u001b[0m \u001b[0mquery_or_table\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 324\u001b[0m \u001b[0mconfiguration\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mconfiguration\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/gbq_connector.py\u001b[0m in \u001b[0;36mrun_query\u001b[0;34m(self, query, max_results, progress_bar_type, **kwargs)\u001b[0m\n\u001b[1;32m 238\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 239\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mFEATURES\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbigquery_has_query_and_wait\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 240\u001b[0;31m rows_iter = pandas_gbq.query.query_and_wait_via_client_library(\n\u001b[0m\u001b[1;32m 241\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 242\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclient\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/query.py\u001b[0m in \u001b[0;36mquery_and_wait_via_client_library\u001b[0;34m(connector, client, query, job_config, location, project_id, max_results, timeout_ms)\u001b[0m\n\u001b[1;32m 196\u001b[0m \u001b[0mtimeout_ms\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mOptional\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mint\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 197\u001b[0m ):\n\u001b[0;32m--> 198\u001b[0;31m rows_iter = try_query(\n\u001b[0m\u001b[1;32m 199\u001b[0m \u001b[0mconnector\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 200\u001b[0m functools.partial(\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/query.py\u001b[0m in \u001b[0;36mtry_query\u001b[0;34m(connector, query_fn)\u001b[0m\n\u001b[1;32m 97\u001b[0m )\n\u001b[1;32m 98\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mconnector\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhttp_error\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mex\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 99\u001b[0;31m \u001b[0mconnector\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprocess_http_error\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 100\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 101\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/gbq_connector.py\u001b[0m in \u001b[0;36mprocess_http_error\u001b[0;34m(ex)\u001b[0m\n\u001b[1;32m 172\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mTableCreationError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"Reason: {error_message}\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 173\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 174\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mGenericGBQException\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Reason: {0}\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mex\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 175\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 176\u001b[0m def download_table(\n", + "\u001b[0;31mGenericGBQException\u001b[0m: Reason: 400 POST https://bigquery.googleapis.com/bigquery/v2/projects/%5Byour%20Cloud%20Platform%20project%20ID%5D/queries?prettyPrint=false: Invalid project ID '[your Cloud Platform project ID]'. Project IDs must contain 6-63 lowercase letters, digits, or dashes. Some project IDs also include domain name separated by a colon. IDs must start with a letter and may not end with a dash." + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "df.describe()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "EqHm2LAMvMg4", + "outputId": "057a1a37-1fc9-47cd-e6cc-200e5c729814" + }, + "execution_count": 49, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Issue Date Ticket Number\n", + "count 1000000 1.000000e+06\n", + "mean 2022-07-01 23:32:43.411199744 5.499237e+09\n", + "min 2022-01-01 00:00:00 1.000005e+09\n", + "25% 2022-04-02 00:00:00 3.249061e+09\n", + "50% 2022-07-02 00:00:00 5.499907e+09\n", + "75% 2022-10-01 00:00:00 7.748794e+09\n", + "max 2022-12-31 00:00:00 9.999998e+09\n", + "std NaN 2.597215e+09" + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Issue DateTicket Number
count10000001.000000e+06
mean2022-07-01 23:32:43.4111997445.499237e+09
min2022-01-01 00:00:001.000005e+09
25%2022-04-02 00:00:003.249061e+09
50%2022-07-02 00:00:005.499907e+09
75%2022-10-01 00:00:007.748794e+09
max2022-12-31 00:00:009.999998e+09
stdNaN2.597215e+09
\n", + "
" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"df\",\n \"rows\": 8,\n \"fields\": [\n {\n \"column\": \"Issue Date\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": \"1970-01-01 00:00:00.001000\",\n \"max\": \"2022-12-31 00:00:00\",\n \"num_unique_values\": 7,\n \"samples\": [\n \"1000000\",\n \"2022-07-01 23:32:43.411199744\",\n \"2022-10-01 00:00:00\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Ticket Number\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3390298193.6777215,\n \"min\": 1000000.0,\n \"max\": 9999997850.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 5499236759.115837,\n 7748793835.0,\n 1000000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 49 } ] }, @@ -261,7 +1535,7 @@ "metadata": { "id": "xERdbQehOc9t" }, - "execution_count": 540, + "execution_count": 49, "outputs": [] }, { @@ -281,7 +1555,7 @@ "metadata": { "id": "oomPQ7gAOhak" }, - "execution_count": 541, + "execution_count": 50, "outputs": [] }, { @@ -296,6 +1570,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "nxhXLYbswFru" + }, + "execution_count": 50, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -314,7 +1597,7 @@ "metadata": { "id": "nC-EQN2iOgDE" }, - "execution_count": 542, + "execution_count": 50, "outputs": [] }, { @@ -323,7 +1606,7 @@ "metadata": { "id": "VPtTWBADOfu9" }, - "execution_count": 543, + "execution_count": 50, "outputs": [] }, { @@ -346,6 +1629,15 @@ "* To proceed with the task, a Python environment with necessary image processing libraries like OpenCV would be required.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "tRST2G45wJ1B" + }, + "execution_count": 50, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -362,7 +1654,7 @@ "metadata": { "id": "6QWGZk0xOrQG" }, - "execution_count": 544, + "execution_count": 50, "outputs": [] }, { @@ -383,7 +1675,7 @@ "metadata": { "id": "HQq0lOvdOsEu" }, - "execution_count": 545, + "execution_count": 50, "outputs": [] }, { @@ -404,7 +1696,7 @@ "metadata": { "id": "Sw3XV9tKOs_O" }, - "execution_count": 546, + "execution_count": 50, "outputs": [] }, { @@ -442,7 +1734,7 @@ "metadata": { "id": "j5Up4iogOuTm" }, - "execution_count": 547, + "execution_count": 50, "outputs": [] }, { @@ -463,7 +1755,7 @@ "metadata": { "id": "cW5EIi4EOvCu" }, - "execution_count": 548, + "execution_count": 50, "outputs": [] }, { @@ -484,7 +1776,7 @@ "metadata": { "id": "Kn2-TSJ2Ov6v" }, - "execution_count": 549, + "execution_count": 50, "outputs": [] }, { @@ -505,7 +1797,7 @@ "metadata": { "id": "1xIVpO6lOwg3" }, - "execution_count": 550, + "execution_count": 50, "outputs": [] }, { @@ -538,7 +1830,7 @@ "metadata": { "id": "yUdzcWyCOyE3" }, - "execution_count": 551, + "execution_count": 50, "outputs": [] }, { @@ -559,7 +1851,7 @@ "metadata": { "id": "EAiDBHcpOyyH" }, - "execution_count": 552, + "execution_count": 50, "outputs": [] }, { @@ -580,7 +1872,7 @@ "metadata": { "id": "JyXLd_uoOz6f" }, - "execution_count": 553, + "execution_count": 50, "outputs": [] }, { @@ -601,7 +1893,7 @@ "metadata": { "id": "S6fzvdD5O1gH" }, - "execution_count": 554, + "execution_count": 50, "outputs": [] }, { @@ -610,7 +1902,7 @@ "metadata": { "id": "7Lj0S65PO2nQ" }, - "execution_count": 555, + "execution_count": 50, "outputs": [] }, { @@ -635,7 +1927,7 @@ "metadata": { "id": "v_NK4W7EO334" }, - "execution_count": 556, + "execution_count": 50, "outputs": [] }, { @@ -656,7 +1948,7 @@ "metadata": { "id": "1-j61bg7O5FI" }, - "execution_count": 557, + "execution_count": 50, "outputs": [] }, { @@ -677,7 +1969,7 @@ "metadata": { "id": "dUojeklHO56A" }, - "execution_count": 558, + "execution_count": 50, "outputs": [] }, { @@ -709,7 +2001,7 @@ "metadata": { "id": "_TIs_lY3O6xf" }, - "execution_count": 559, + "execution_count": 50, "outputs": [] }, { @@ -861,7 +2153,7 @@ "# The implementation was not possible in the current Julia environment due to the lack of necessary libraries for 3D graphics, audio processing, and user interaction.\n", "# The descriptions provided are based on how this project would be approached in a suitable Python environment with access to relevant libraries." ], - "execution_count": 560, + "execution_count": 51, "outputs": [] }, { @@ -870,7 +2162,7 @@ "metadata": { "id": "pa7fx_3IO9yJ" }, - "execution_count": 561, + "execution_count": 51, "outputs": [] }, { @@ -900,7 +2192,7 @@ "metadata": { "id": "mWy7fGpuO_TA" }, - "execution_count": 562, + "execution_count": 51, "outputs": [] }, { @@ -930,7 +2222,23 @@ "metadata": { "id": "yYKbRNvXPAug" }, - "execution_count": 563, + "execution_count": 51, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [], + "metadata": { + "id": "TdB06AzNwNjG" + } + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "6_TmfNYqwO8v" + }, + "execution_count": 51, "outputs": [] } ] From cb7f75a094c0aa123fab96b69a33c3cc5676672c Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 09:06:21 -0700 Subject: [PATCH 11/20] Created using Colab --- quickstarts/Get_started_LiveAPI.ipynb | 1039 +++++++++++++++++++++++++ 1 file changed, 1039 insertions(+) create mode 100644 quickstarts/Get_started_LiveAPI.ipynb diff --git a/quickstarts/Get_started_LiveAPI.ipynb b/quickstarts/Get_started_LiveAPI.ipynb new file mode 100644 index 0000000..157e32b --- /dev/null +++ b/quickstarts/Get_started_LiveAPI.ipynb @@ -0,0 +1,1039 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Tce3stUlHN0L" + }, + "source": [ + "##### Copyright 2025 Google LLC." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "cellView": "form", + "id": "tuOe1ymfHZPu" + }, + "outputs": [], + "source": [ + "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n", + "# you may not use this file except in compliance with the License.\n", + "# You may obtain a copy of the License at\n", + "#\n", + "# https://www.apache.org/licenses/LICENSE-2.0\n", + "#\n", + "# Unless required by applicable law or agreed to in writing, software\n", + "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", + "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", + "# See the License for the specific language governing permissions and\n", + "# limitations under the License." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "R5DkeFMP75as" + }, + "source": [ + "# Multimodal Live API - Quickstart" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tqktCVDm1yFo" + }, + "source": [ + "" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "iS0rHk3RBrtA" + }, + "source": [ + "**Preview**: The Live API is in preview.\n", + "\n", + "This notebook demonstrates simple usage of the Gemini Multimodal Live API. For an overview of new capabilities refer to the [Gemini Live API docs](https://ai.google.dev/gemini-api/docs/live).\n", + "\n", + "This notebook implements a simple turn-based chat where you send messages as text, and the model replies with audio. The API is capable of much more than that. The goal here is to demonstrate with **simple code**.\n", + "\n", + "Some features of the API are not working in Colab, to try them it is recommended to have a look at this [Python script](./Get_started_LiveAPI.py) and run it locally.\n", + "\n", + "If you aren't looking for code, and just want to try multimedia streaming use [Live API in Google AI Studio](https://aistudio.google.com/app/live).\n", + "\n", + "The [Next steps](#next_steps) section at the end of this tutorial provides links to additional resources.\n", + "\n", + "#### Native audio output\n", + "\n", + "**Info**: Gemini 2.5 introduces [native audio generation](https://ai.google.dev/gemini-api/docs/live#native-audio-output), which directly generates audio output, providing a more natural sounding audio, more expressive voices, more awareness of additional context, e.g., tone, and more proactive responses. You can try a native audio example in this [script](./Get_started_LiveAPI_NativeAudio.py)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Mfk6YY3G5kqp" + }, + "source": [ + "## Setup" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "d5027929de8f" + }, + "source": [ + "### Install SDK\n", + "\n", + "The new **[Google Gen AI SDK](https://ai.google.dev/gemini-api/docs/sdks)** provides programmatic access to Gemini 2.5 (and previous models) using both the [Google AI for Developers](https://ai.google.dev/gemini-api/docs) and [Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/overview) APIs. With a few exceptions, code that runs on one platform will run on both.\n", + "\n", + "More details about this new SDK on the [documentation](https://ai.google.dev/gemini-api/docs/sdks) or in the [Getting started](../quickstarts/Get_started.ipynb) notebook." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "46zEFO2a9FFd", + "outputId": "444618bd-a432-428b-b15a-d3bfcef91065" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Note: you may need to restart the kernel to use updated packages.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\n", + "[notice] A new release of pip is available: 25.1.1 -> 25.2\n", + "[notice] To update, run: python.exe -m pip install --upgrade pip\n" + ] + } + ], + "source": [ + "%pip install -U -q google-genai" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "CTIfnvCn9HvH" + }, + "source": [ + "### Set up your API key\n", + "\n", + "To run the following cell, your API key must be stored in a Colab Secret named `GOOGLE_API_KEY`. If you don't already have an API key, or you're not sure how to create a Colab Secret, see [Authentication](../quickstarts/Authentication.ipynb) for an example." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "A1pkoyZb9Jm3" + }, + "outputs": [], + "source": [ + "from google.colab import userdata\n", + "import os\n", + "\n", + "os.environ['GOOGLE_API_KEY'] = userdata.get('GOOGLE_API_KEY')\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3Hx_Gw9i0Yuv" + }, + "source": [ + "### Initialize SDK client\n", + "\n", + "The client will pick up your API key from the environment variable." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "HghvVpbU0Uap" + }, + "outputs": [], + "source": [ + "from google import genai\n", + "from google.genai import types\n", + "client = genai.Client(api_key=GOOGLE_API_KEY)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QOov6dpG99rY" + }, + "source": [ + "### Select a model\n", + "\n", + "The [Gemini 2.5 Flash Live](https://ai.google.dev/gemini-api/docs/models#live-api) model works with the Live API to enable low-latency bidirectional voice and video interactions with Gemini. The model can process text, audio, and video input, and it can provide text and audio output." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "27Fikag0xSaB" + }, + "outputs": [], + "source": [ + "MODEL = \"gemini-2.0-flash-live-001\" # @param [\"gemini-2.0-flash-live-001\", \"gemini-live-2.5-flash-preview\",\"gemini-2.5-flash-preview-native-audio-dialog\"] {\"allow-input\":true, isTemplate: true}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "GOOZsm7i9io6" + }, + "source": [ + "### Import\n", + "\n", + "Import all the necessary modules." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Yd1vs3cP8EmS" + }, + "outputs": [], + "source": [ + "import asyncio\n", + "import base64\n", + "import contextlib\n", + "import datetime\n", + "import os\n", + "import json\n", + "import wave\n", + "import itertools\n", + "\n", + "from IPython.display import display, Audio\n", + "\n", + "from google import genai\n", + "from google.genai import types" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "jj7gDzfDOq4h" + }, + "source": [ + "## Text to Text\n", + "\n", + "The simplest way to use the Live API is as a text-to-text chat interface, but it can do **a lot** more than this." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "dDfslcyIOqgI", + "outputId": "ae08f423-be20-4e05-876e-479485cf7004" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "> Hello? Gemini are you there? \n", + "\n", + "- Hello\n", + "- there! I am indeed here. How can I help you today?\n" + ] + } + ], + "source": [ + "config={\n", + " \"response_modalities\": [\"TEXT\"]\n", + "}\n", + "\n", + "async with client.aio.live.connect(model=MODEL, config=config) as session:\n", + " message = \"Hello? Gemini are you there?\"\n", + " print(\"> \", message, \"\\n\")\n", + " await session.send_client_content(\n", + " turns={\"role\": \"user\", \"parts\": [{\"text\": message}]}, turn_complete=True\n", + " )\n", + "\n", + " # For text responses, When the model's turn is complete it breaks out of the loop.\n", + " turn = session.receive()\n", + " async for chunk in turn:\n", + " if chunk.text is not None:\n", + " print(f'- {chunk.text}')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "rvpmur4lKfOv" + }, + "source": [ + "## Simple text to audio" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "jjkzgogvG1q0" + }, + "source": [ + "The simplest way to playback the audio in Colab, is to write it out to a `.wav` file. So here is a simple wave file writer:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "7mEDGwJfLRrm" + }, + "outputs": [], + "source": [ + "@contextlib.contextmanager\n", + "def wave_file(filename, channels=1, rate=24000, sample_width=2):\n", + " with wave.open(filename, \"wb\") as wf:\n", + " wf.setnchannels(channels)\n", + " wf.setsampwidth(sample_width)\n", + " wf.setframerate(rate)\n", + " yield wf" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "DGuKQSurN7F4" + }, + "source": [ + "The next step is to tell the model to return audio by setting `\"response_modalities\": [\"AUDIO\"]` in the `LiveConnectConfig`. \n", + "\n", + "When you get a response from the model, then you write out the data to a `.wav` file." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "VFD4VleVKj1-", + "outputId": "6d5420ae-8d9b-4ab4-c048-7c176aa4c5f4" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "> Hello? Gemini are you there? \n", + "\n", + "audio/pcm;rate=24000\n", + "................" + ] + }, + { + "data": { + "text/html": [ + "\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "config={\n", + " \"response_modalities\": [\"AUDIO\"]\n", + "}\n", + "\n", + "async def async_enumerate(aiterable):\n", + " n=0\n", + " async for item in aiterable:\n", + " yield n, item\n", + " n+=1\n", + "\n", + "\n", + "async with client.aio.live.connect(model=MODEL, config=config) as session:\n", + " file_name = 'audio.wav'\n", + " with wave_file(file_name) as wav:\n", + " message = \"Hello? Gemini are you there?\"\n", + " print(\"> \", message, \"\\n\")\n", + " await session.send_client_content(\n", + " turns={\"role\": \"user\", \"parts\": [{\"text\": message}]}, turn_complete=True\n", + " )\n", + "\n", + " turn = session.receive()\n", + " async for n,response in async_enumerate(turn):\n", + " if response.data is not None:\n", + " wav.writeframes(response.data)\n", + "\n", + " if n==0:\n", + " print(response.server_content.model_turn.parts[0].inline_data.mime_type)\n", + " print('.', end='')\n", + "\n", + "\n", + "display(Audio(file_name, autoplay=True))\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QutDG7r78Zf-" + }, + "source": [ + "## Towards Async Tasks\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "YfEQZrtZY_90" + }, + "source": [ + "The real power of the Live API is that it's real time, and interruptable. You can't get that full power in a simple sequence of steps. To really use the functionality you will move the `send` and `recieve` operations (and others) into their own [async tasks](https://docs.python.org/3/library/asyncio-task.html).\n", + "\n", + "Because of the limitations of Colab this tutorial doesn't totally implement the interactive async tasks, but it does implement the next step in that direction:\n", + "\n", + "- It separates the `send` and `receive`, but still runs them sequentially. \n", + "- In the next tutorial you'll run these in separate `async` tasks.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QUBet__tZF0o" + }, + "source": [ + "Setup a quick logger to make debugging easier (switch to `setLevel('DEBUG')` to see debugging messages)." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "bWTaU8j-X3AJ" + }, + "outputs": [], + "source": [ + "import logging\n", + "\n", + "logger = logging.getLogger('Live')\n", + "logger.setLevel('INFO')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ERqyY0IFN8G9" + }, + "source": [ + "The class below implements the interaction with the Live API." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "3zAjMOZXFuxI" + }, + "outputs": [], + "source": [ + "class AudioLoop:\n", + " def __init__(self, turns=None, config=None):\n", + " self.session = None\n", + " self.index = 0\n", + " self.turns = turns\n", + " if config is None:\n", + " config={\n", + " \"response_modalities\": [\"AUDIO\"]}\n", + " self.config = config\n", + "\n", + " async def run(self):\n", + " logger.debug('connect')\n", + " async with client.aio.live.connect(model=MODEL, config=self.config) as session:\n", + " self.session = session\n", + "\n", + " async for sent in self.send():\n", + " # Ideally send and recv would be separate tasks.\n", + " await self.recv()\n", + "\n", + " async def _iter(self):\n", + " if self.turns:\n", + " for text in self.turns:\n", + " print(\"message >\", text)\n", + " yield text\n", + " else:\n", + " print(\"Type 'q' to quit\")\n", + " while True:\n", + " text = await asyncio.to_thread(input, \"message > \")\n", + "\n", + " # If the input returns 'q' quit.\n", + " if text.lower() == 'q':\n", + " break\n", + "\n", + " yield text\n", + "\n", + " async def send(self):\n", + " async for text in self._iter():\n", + " logger.debug('send')\n", + "\n", + " # Send the message to the model.\n", + " await self.session.send_client_content(\n", + " turns={\"role\": \"user\", \"parts\": [{\"text\": text}]}, turn_complete=True\n", + " )\n", + " logger.debug('sent')\n", + " yield text\n", + "\n", + " async def recv(self):\n", + " # Start a new `.wav` file.\n", + " file_name = f\"audio_{self.index}.wav\"\n", + " with wave_file(file_name) as wav:\n", + " self.index += 1\n", + "\n", + " logger.debug('receive')\n", + "\n", + " # Read chunks from the socket.\n", + " turn = self.session.receive()\n", + " async for n, response in async_enumerate(turn):\n", + " logger.debug(f'got chunk: {str(response)}')\n", + "\n", + " if response.data is None:\n", + " logger.debug(f'Unhandled server message! - {response}')\n", + " else:\n", + " wav.writeframes(response.data)\n", + " if n == 0:\n", + " print(response.server_content.model_turn.parts[0].inline_data.mime_type)\n", + " print('.', end='')\n", + "\n", + " print('\\n')\n", + "\n", + " display(Audio(file_name, autoplay=True))\n", + " await asyncio.sleep(2)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "AwNPuC_rAHAc" + }, + "source": [ + "There are 3 methods worth describing here:" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tXPhEdHIPBif" + }, + "source": [ + "**`run` - The main loop**\n", + "\n", + "This method:\n", + "\n", + "- Opens a `websocket` connecting to the Live API.\n", + "- Calls the initial `setup` method.\n", + "- Then enters the main loop where it alternates between `send` and `recv` until send returns `False`.\n", + "- The next tutorial will demonstrate how to stream media and run these asynchronously." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "oCg1qFf0PV44" + }, + "source": [ + "**`send` - Sends input text to the api**\n", + "\n", + "The `send` method collects input text from the user, wraps it in a `client_content` message (an instance of `BidiGenerateContentClientContent`), and sends it to the model.\n", + "\n", + "If the user sends a `q` this method returns `False` to signal that it's time to quit." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tLukmBhPPib4" + }, + "source": [ + "**`recv` - Collects audio from the API and plays it**\n", + "\n", + "The `recv` method collects audio chunks in a loop and writes them to a `.wav` file. It breaks out of the loop once the model sends a `turn_complete` method, and then plays the audio.\n", + "\n", + "To keep things simple in Colab it collects **all** the audio before playing it. [Other examples](#next_steps) demonstrate how to play audio as soon as you start to receive it (using `PyAudio`), and how to interrupt the model (implement input and audio playback on separate tasks)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "gGYtiV2N8b2o" + }, + "source": [ + "### Run\n", + "\n", + "Run it:\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "WxdwgTKIGIlY", + "outputId": "dfc710c3-f0f3-4ff0-9e10-75edaedf63d7" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "message > Hello\n", + "audio/pcm;rate=24000\n", + "....................\n", + "\n" + ] + }, + { + "data": { + "text/html": [ + "\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "message > What's your name?\n", + "audio/pcm;rate=24000\n", + "..........\n", + "\n" + ] + }, + { + "data": { + "text/html": [ + "\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "await AudioLoop(['Hello', \"What's your name?\"]).run()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "uZD24TXrcsfk" + }, + "source": [ + "## Working with resumable sessions\n", + "\n", + "Session resumption allows you to return to a previous interaction with the Live API by sending the last session handle you got from the previous session.\n", + "\n", + "When you set your session to be resumable, the session information keeps stored on the Live API for up to 24 hours. In this time window, you can resume the conversation and refer to previous information you have shared with the model.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "qveK8jxae_x0" + }, + "source": [ + "### Helper functions\n", + "\n", + "Start by creating the helper functions for your resumable interaction with the Live API. It will include:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "cbkoDa1ve_C5" + }, + "outputs": [], + "source": [ + "import asyncio\n", + "import traceback\n", + "from asyncio.exceptions import CancelledError\n", + "\n", + "last_handle = None\n", + "\n", + "MODEL = \"gemini-live-2.5-flash-preview\"\n", + "\n", + "client = genai.Client(api_key=GOOGLE_API_KEY)\n", + "\n", + "async def async_enumerate(aiterable):\n", + " n=0\n", + " async for item in aiterable:\n", + " yield n, item\n", + " n+=1\n", + "\n", + "\n", + "def show_response(response):\n", + " new_handle = None\n", + " if text := response.text:\n", + " print(text, end=\"\")\n", + " else:\n", + " print(response.model_dump_json(indent=2, exclude_none=True))\n", + " if response.session_resumption_update:\n", + " new_handle = response.session_resumption_update.new_handle\n", + " return new_handle\n", + "\n", + "\n", + "async def clock():\n", + " time = 0\n", + " while True:\n", + " await asyncio.sleep(60)\n", + " time += 1\n", + " print(f\"{time}:00\")\n", + "\n", + "\n", + "async def recv(session):\n", + " global last_handle\n", + " try:\n", + " while True:\n", + " async for response in session.receive():\n", + " new_handle = show_response(response)\n", + " if new_handle:\n", + " last_handle = new_handle\n", + " except asyncio.CancelledError:\n", + " pass\n", + "\n", + "\n", + "async def send(session):\n", + " while True:\n", + " message = await asyncio.to_thread(input, \"message > \")\n", + " if message.lower() == \"q\":\n", + " break\n", + " await session.send_client_content(turns={\n", + " 'role': 'user',\n", + " 'parts': [{'text': message}]\n", + " })\n", + "\n", + "\n", + "async def async_main(last_handle=None):\n", + " config = types.LiveConnectConfig.model_validate({\n", + " \"response_modalities\": [\"TEXT\"],\n", + " \"session_resumption\": {\n", + " 'handle': last_handle,\n", + " }\n", + " })\n", + " try:\n", + " async with (\n", + " client.aio.live.connect(model=MODEL, config=config) as session,\n", + " asyncio.TaskGroup() as tg\n", + " ):\n", + " clock_task = tg.create_task(clock())\n", + " recv_task = tg.create_task(recv(session))\n", + " send_task = tg.create_task(send(session))\n", + " await send_task\n", + " raise asyncio.CancelledError()\n", + " except asyncio.CancelledError:\n", + " pass\n", + " except ExceptionGroup as EG:\n", + " traceback.print_exception(EG)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "xsPClQxUkO9V" + }, + "source": [ + "Now you can start interacting with the Live API (type `q` to finish the conversation):" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "yqBTtKvGmKI4", + "outputId": "fda0516a-7ea2-4e6e-9371-bb3a8a3280bf" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{\n", + " \"session_resumption_update\": {}\n", + "}\n", + "Hello there! How can I help you today?{\n", + " \"server_content\": {\n", + " \"generation_complete\": true\n", + " }\n", + "}\n", + "{\n", + " \"server_content\": {\n", + " \"turn_complete\": true\n", + " },\n", + " \"usage_metadata\": {\n", + " \"prompt_token_count\": 9,\n", + " \"response_token_count\": 10,\n", + " \"total_token_count\": 19,\n", + " \"prompt_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 9\n", + " }\n", + " ],\n", + " \"response_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 10\n", + " }\n", + " ]\n", + " }\n", + "}\n", + "{\n", + " \"session_resumption_update\": {\n", + " \"new_handle\": \"Cig2N3lqa3d3MXd4eHFoeDk3cnhmeHUydjlhdHN2cms1bDRnc3c0N2Zq\",\n", + " \"resumable\": true\n", + " }\n", + "}\n", + "1:00\n", + "{\n", + " \"session_resumption_update\": {}\n", + "}\n", + "The capital of Brazil is **Brasília**.{\n", + " \"server_content\": {\n", + " \"generation_complete\": true\n", + " }\n", + "}\n", + "{\n", + " \"server_content\": {\n", + " \"turn_complete\": true\n", + " },\n", + " \"usage_metadata\": {\n", + " \"prompt_token_count\": 36,\n", + " \"response_token_count\": 9,\n", + " \"total_token_count\": 45,\n", + " \"prompt_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 36\n", + " }\n", + " ],\n", + " \"response_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 9\n", + " }\n", + " ]\n", + " }\n", + "}\n", + "{\n", + " \"session_resumption_update\": {\n", + " \"new_handle\": \"Cig0ZDR1OTViNHVjOWh6aGJvMmhwdWk3NzJiZWRwYW91bnNtajgxZHN1\",\n", + " \"resumable\": true\n", + " }\n", + "}\n" + ] + } + ], + "source": [ + "await async_main()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "NdUy9WsrJwxi" + }, + "source": [ + "With the session resumption you have the session handle to refer to your previous sessions. In this example, the handle is saved at the `last_handle` variable as below:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Y5ZVUQ5vJrEJ", + "outputId": "49994add-7cc3-44cc-ba9b-8692a7c2654a" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "'Cig0ZDR1OTViNHVjOWh6aGJvMmhwdWk3NzJiZWRwYW91bnNtajgxZHN1'" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "last_handle" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "xEIhRZBYJ_8V" + }, + "source": [ + "Now you can start a new Live API session, but this time pointing to a handle from a previous session. Also, to test you could gather information from the previous session, you will ask the model what was the second question you asked before (in this example, it was \"what is the capital of Brazil?\"). You can see the Live API recovering that information:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "xH_iZhTxKFtF", + "outputId": "22f4d1ab-362c-401a-ce40-8d386cf209e4" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{\n", + " \"session_resumption_update\": {}\n", + "}\n", + "The last question you asked was: \"what is the capital of brazil?\"{\n", + " \"server_content\": {\n", + " \"generation_complete\": true\n", + " }\n", + "}\n", + "{\n", + " \"server_content\": {\n", + " \"turn_complete\": true\n", + " },\n", + " \"usage_metadata\": {\n", + " \"prompt_token_count\": 63,\n", + " \"response_token_count\": 15,\n", + " \"total_token_count\": 78,\n", + " \"prompt_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 63\n", + " }\n", + " ],\n", + " \"response_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 15\n", + " }\n", + " ]\n", + " }\n", + "}\n", + "{\n", + " \"session_resumption_update\": {\n", + " \"new_handle\": \"CihyNDg4YTkxanl5cThzYmo4a29lMHRveDJlY3U1amRyNHlqeWF0bWU2\",\n", + " \"resumable\": true\n", + " }\n", + "}\n" + ] + } + ], + "source": [ + "await async_main(last_handle)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ietchD8GbcXt" + }, + "source": [ + "## Next steps\n", + "\n", + "\n", + "\n", + "This tutorial just shows basic usage of the Live API, using the Python GenAI SDK.\n", + "\n", + "- If you aren't looking for code, and just want to try multimedia streaming use [Live API in Google AI Studio](https://aistudio.google.com/app/live).\n", + "- If you want to see how to setup streaming interruptible audio and video using the Live API see the [Audio and Video input Tutorial](../quickstarts/Get_started_LiveAPI.py).\n", + "- If you're interested in the low level details of using the websockets directly, see the [websocket version of this tutorial](../quickstarts/websockets/Get_started_LiveAPI.ipynb).\n", + "- Try the [Tool use in the live API tutorial](../quickstarts/Get_started_LiveAPI_tools.ipynb) for an walkthrough of Gemini-2.5's new use capabilities.\n", + "- There is a [Streaming audio in Colab example](../quickstarts/websockets/LiveAPI_streaming_in_colab.ipynb), but this is more of a **demo**, it's **not optimized for readability**.\n", + "- Other nice Gemini 2.5 examples can also be found in the [Cookbook's example\n", + " directory](https://github.com/google-gemini/cookbook/tree/main/examples/), in particular the [video understanding](../quickstarts/Video_understanding.ipynb) and the [spatial understanding](../quickstarts/Spatial_understanding.ipynb) ones." + ] + }, + { + "cell_type": "markdown", + "source": [ + "# New Section" + ], + "metadata": { + "id": "TKJvxpqBlBEl" + } + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "bNlAkeqHlCkN" + }, + "execution_count": null, + "outputs": [] + } + ], + "metadata": { + "colab": { + "collapsed_sections": [ + "Tce3stUlHN0L" + ], + "name": "Get_started_LiveAPI.ipynb", + "toc_visible": true, + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file From a004805d7811440fbd3d833ee56158257932c058 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 30 Aug 2025 19:12:11 -0700 Subject: [PATCH 12/20] Created using Colab --- .../vertex_ai_prompt_optimizer_ui.ipynb | 498 ++++++++++++++++++ 1 file changed, 498 insertions(+) create mode 100644 gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb new file mode 100644 index 0000000..4e6a675 --- /dev/null +++ b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb @@ -0,0 +1,498 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "hlI1rYKa2IGx" + }, + "outputs": [], + "source": [ + "# Copyright 2024 Google LLC\n", + "#\n", + "# Licensed under the Apache License, Version 2.0 (the \"License\");\n", + "# you may not use this file except in compliance with the License.\n", + "# You may obtain a copy of the License at\n", + "#\n", + "# https://www.apache.org/licenses/LICENSE-2.0\n", + "#\n", + "# Unless required by applicable law or agreed to in writing, software\n", + "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", + "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", + "# See the License for the specific language governing permissions and\n", + "# limitations under the License." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "RN8N3O43QDT5" + }, + "source": [ + "# Vertex Prompt Optimizer Notebook UI (Preview)\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \"Google
Open in Colab\n", + " \n", + " 		\n", + " \n", + " \"Google
Open in Colab Enterprise\n", + " \n", + " 		\n", + " \n", + " \"Vertex
Open in Vertex AI Workbench\n", + " \n", + " 		\n", + " \n", + " \"GitHub
View on GitHub\n", + " \n", + "
\n", + "\n", + "
\n", + "\n", + "Share to:\n", + "\n", + "\n", + " \"LinkedIn\n", + "\n", + "\n", + "\n", + " \"Bluesky\n", + "\n", + "\n", + "\n", + " \"X\n", + "\n", + "\n", + "\n", + " \"Reddit\n", + "\n", + "\n", + "\n", + " \"Facebook\n", + " " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "pHyuJTFr2IGx" + }, + "source": [ + "# Overview\n", + "This Notebook showcases the Vertex AI prompt optimizer, a tool that iteratively optimizes prompts to suit a target model (e.g., `gemini-2.0-flash`) using target-specific metric(s).\n", + "\n", + "Key Use Cases:\n", + "\n", + "* Prompt Optimization: Enhance the quality of an initial prompt by refining its structure and content to match the target model's optimal input characteristics.\n", + "\n", + "* Prompt Translation: Adapt prompts optimized for one model to work effectively with a different target model.\n", + "\n", + "For the detailed documentation please see [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "61RBz8LLbxCR" + }, + "source": [ + "## Getting Started" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "dmWOrTJ3gx13" + }, + "source": [ + "### Authenticate your notebook environment (Colab only)\n", + "\n", + "Authenticate your environment on Google Colab.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "NyKGtVQjgx13" + }, + "outputs": [], + "source": [ + "import sys\n", + "\n", + "if \"google.colab\" in sys.modules:\n", + " from google.colab import auth\n", + "\n", + " auth.authenticate_user()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tTtKHedrO1Rx" + }, + "source": [ + "# Step 0: Install packages and libraries" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "8-Zw72vFORz_", + "outputId": "98b34e63-ec34-4799-adf8-fce2af428b25", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "--2025-08-31 02:12:00-- https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", + "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n", + "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n", + "HTTP request sent, awaiting response... 200 OK\n", + "Length: 37206 (36K) [text/plain]\n", + "Saving to: ‘vapo_lib.py’\n", + "\n", + "\rvapo_lib.py 0%[ ] 0 --.-KB/s \rvapo_lib.py 100%[===================>] 36.33K --.-KB/s in 0.006s \n", + "\n", + "2025-08-31 02:12:00 (5.64 MB/s) - ‘vapo_lib.py’ saved [37206/37206]\n", + "\n" + ] + } + ], + "source": [ + "!wget https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", + "import vapo_lib" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-p59jd5rOp4q" + }, + "source": [ + "# Step 1: Create a prompt template and system instructions\n", + "Provide your system intruction and prompt template below. Refer to [here]( https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#template-si) for instructions.\n", + "\n", + "Prompts consist of two key components:\n", + "\n", + "- System Instruction: System instruction is the instruction that get passed to the model before any user input in the prompt. This is the fixed part of the prompt template shared across all queries for a given task.\n", + "- Prompt template: A task is the text in the prompt that you want the model to provide a response for. Context is information that you include in the prompt that the model uses or references when generating a response. These are the dynamic parts of the prompt template that changes based on the task.\n", + "\n", + "Prompt Optimizer enables the optimization or translation of the System Instruction template, while the prompt template remains essential for evaluating and selecting the best System Instruction template." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "rJG1pVZO317x" + }, + "outputs": [], + "source": [ + "SYSTEM_INSTRUCTION = (\n", + " \"Answer the following question. Let's think step by step.\\n\" # @param\n", + ")\n", + "PROMPT_TEMPLATE = \"Question: {question}\\n\\nAnswer: {target}\" # @param" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5y-cmg0TQP6v" + }, + "source": [ + "# Step 2: Configure project settings\n", + "To optimize the prompt for your target Google model, provide a CSV or JSONL file containing labeled validation samples (input, ground truth output pairs). Refer to [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#prepare-sample-prompts) for instructions.\n", + "\n", + "Focus on examples that specifically demonstrate the issues you want to address.\n", + "Recommendation: Use 50-100 distinct samples for reliable results. However, the tool can still be effective with as few as 5 samples.\n", + "For prompt translation (e.g. 3P model to Google model, PaLM 2 to Gemini):\n", + "\n", + "Consider using the source model to label examples that the target model struggles with, helping to identify areas for improvement.\n", + "When you select a source model, you don't need to provide labels for the input examples.\n", + "While the source model selection is limited to Google models, it still supports labeled inputs from non-Google models. If you wish to select a non-Google source model, you will need to provide labels for your input examples.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "mfgi_oR6tTIB" + }, + "outputs": [], + "source": [ + "# @markdown **Project setup**:
\n", + "PROJECT_ID = \"[YOUR_PROJECT]\" # @param {type:\"string\"}\n", + "LOCATION = \"us-central1\" # @param {type:\"string\"}\n", + "OUTPUT_PATH = \"[OUTPUT_PATH]\" # @param {type:\"string\"}\n", + "INPUT_DATA_PATH = \"[INPUT_DATA_PATH]\" # @param {type:\"string\"}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ucebZHkHRxKH" + }, + "source": [ + "# Step 3: Configure optimization settings\n", + "The optimization configurations are defaulted to the values that are most commonly used, which we recommend using as the initial set-up.\n", + "\n", + "The most important settings are:\n", + "\n", + "* Target Model: Which model you are trying to optimize your prompts to.\n", + "* Thinking Budget: The thinking budget for thinking models like Gemini-2.5. Default to -1, which means no thinking for non-thinking models and auto thinking for thinking models. Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/thinking) to learn more about manual budget settings.\n", + "* Optimization Mode: The mode in which you are trying to optimize your prompt with.\n", + "* Evaluation Metrics: The evaluation metrics in which you are trying to optimize your prompts against.\n", + "* Translation Source Field Name: fill in with the corresponding field name of the source text in the data if translation metrics like Comet or MetricX are selected. Otherwise, leave it as empty.\n", + "\n", + "Note that all evaluation metrics are expected to have the larger-the-better property. Therefore, we have modified the MetricX value to between 0 (worst) and 25 (best).\n", + "Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#configuration) to learn more about the different configuration settings and how to best utilize them." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "B2R3P8mMvK9q" + }, + "outputs": [], + "source": [ + "TARGET_MODEL = \"gemini-2.0-flash-001\" # @param [\"gemini-2.5-flash-lite\", \"gemini-2.5-flash\", \"gemini-2.5-pro\", \"gemini-2.0-flash-lite-001\", \"gemini-2.0-flash-001\"]\n", + "THINKING_BUDGET = -1 # @param {type:\"integer\"}\n", + "OPTIMIZATION_MODE = \"instruction_and_demo\" # @param [\"instruction\", \"demonstration\", \"instruction_and_demo\"]\n", + "EVAL_METRIC = \"question_answering_correctness\" # @param [\"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "TRANSLATION_SOURCE_FIELD_NAME = \"\" # @param {type:\"string\"}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kO7fO0qTSNLs" + }, + "source": [ + "# Step 4: Configure advanced optimization settings [Optional]\n", + "Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#configuration) to learn more about the different configuration settings and how to best utilize them." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "fRHHTpaV4Xyo" + }, + "outputs": [], + "source": [ + "# @markdown **Instruction Optimization Configs**:
\n", + "NUM_INST_OPTIMIZATION_STEPS = 10 # @param {type:\"integer\"}\n", + "\n", + "# @markdown **Demonstration Optimization Configs**:
\n", + "NUM_DEMO_OPTIMIZATION_STEPS = 10 # @param {type:\"integer\"}\n", + "NUM_DEMO_PER_PROMPT = 3 # @param {type:\"integer\"}\n", + "\n", + "# @markdown **Model Configs**:
\n", + "TARGET_MODEL_QPS = 3.0 # @param {type:\"number\"}\n", + "EVAL_QPS = 3.0 # @param {type:\"number\"}\n", + "\n", + "# @markdown **Multi-metric Configs**:
\n", + "# @markdown Use this section only if you need more than one metric for optimization. This will override the metric you picked above.\n", + "EVAL_METRIC_1 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_1_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "EVAL_METRIC_2 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_2_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "EVAL_METRIC_3 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_3_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "METRIC_AGGREGATION_TYPE = \"weighted_sum\" # @param [\"weighted_sum\", \"weighted_average\"]\n", + "\n", + "# @markdown **Misc Configs**:
\n", + "PLACEHOLDER_TO_VALUE = \"{}\" # @param\n", + "RESPONSE_MIME_TYPE = \"text/plain\" # @param [\"text/plain\", \"application/json\", \"text/x.enum\"] {type:\"string\"}\n", + "RESPONSE_SCHEMA = \"\"\n", + "TARGET_LANGUAGE = \"English\" # @param [\"English\", \"French\", \"German\", \"Hebrew\", \"Hindi\", \"Italian\", \"Japanese\", \"Korean\", \"Portuguese\", \"Simplified Chinese\", \"Spanish\", \"Traditional Chinese\"] {type:\"string\"}\n", + "TOOLS = \"\" # @param\n", + "TOOL_CONFIG = \"\" # @param" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "X7Mgb0EHSSFk" + }, + "source": [ + "# Step 5: Run Prompt Optimizer\n", + "A progress bar will appear to let you know how long the job takes." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Z8NvNLTfxPTf" + }, + "outputs": [], + "source": [ + "import datetime\n", + "import json\n", + "import time\n", + "\n", + "timestamp = datetime.datetime.now().strftime(\"%Y-%m-%dT%H:%M:%S\")\n", + "display_name = f\"pt_{timestamp}\"\n", + "\n", + "label_enforced = vapo_lib.is_run_target_required(\n", + " [\n", + " EVAL_METRIC,\n", + " EVAL_METRIC_1,\n", + " EVAL_METRIC_2,\n", + " EVAL_METRIC_3,\n", + " ],\n", + " \"\",\n", + ")\n", + "input_data_path = f\"{INPUT_DATA_PATH}\"\n", + "vapo_lib.validate_prompt_and_data(\n", + " \"\\n\".join([SYSTEM_INSTRUCTION, PROMPT_TEMPLATE]),\n", + " input_data_path,\n", + " PLACEHOLDER_TO_VALUE,\n", + " label_enforced,\n", + ")\n", + "\n", + "output_path = f\"{OUTPUT_PATH}/{display_name}\"\n", + "\n", + "params = {\n", + " \"project\": PROJECT_ID,\n", + " \"num_steps\": NUM_INST_OPTIMIZATION_STEPS,\n", + " \"system_instruction\": SYSTEM_INSTRUCTION,\n", + " \"prompt_template\": PROMPT_TEMPLATE,\n", + " \"target_model\": TARGET_MODEL,\n", + " \"target_model_qps\": TARGET_MODEL_QPS,\n", + " \"target_model_location\": LOCATION,\n", + " \"optimizer_model_location\": LOCATION,\n", + " \"eval_qps\": EVAL_QPS,\n", + " \"optimization_mode\": OPTIMIZATION_MODE,\n", + " \"num_demo_set_candidates\": NUM_DEMO_OPTIMIZATION_STEPS,\n", + " \"demo_set_size\": NUM_DEMO_PER_PROMPT,\n", + " \"aggregation_type\": METRIC_AGGREGATION_TYPE,\n", + " \"data_limit\": 50,\n", + " \"input_data_path\": input_data_path,\n", + " \"output_path\": output_path,\n", + " \"response_mime_type\": RESPONSE_MIME_TYPE,\n", + " \"response_schema\": RESPONSE_SCHEMA,\n", + " \"language\": TARGET_LANGUAGE,\n", + " \"placeholder_to_content\": json.loads(PLACEHOLDER_TO_VALUE),\n", + " \"tools\": TOOLS,\n", + " \"tool_config\": TOOL_CONFIG,\n", + " \"translation_source_field_name\": TRANSLATION_SOURCE_FIELD_NAME,\n", + " \"thinking_budget\": THINKING_BUDGET,\n", + "}\n", + "\n", + "if EVAL_METRIC_1 == \"NA\":\n", + " params[\"eval_metrics_types\"] = [EVAL_METRIC]\n", + " params[\"eval_metrics_weights\"] = [1.0]\n", + "else:\n", + " metrics = []\n", + " weights = []\n", + " for metric, weight in zip(\n", + " [EVAL_METRIC_1, EVAL_METRIC_2, EVAL_METRIC_3],\n", + " [EVAL_METRIC_1_WEIGHT, EVAL_METRIC_2_WEIGHT, EVAL_METRIC_3_WEIGHT],\n", + " ):\n", + " if metric == \"NA\":\n", + " break\n", + " metrics.append(metric)\n", + " weights.append(weight)\n", + " params[\"eval_metrics_types\"] = metrics\n", + " params[\"eval_metrics_weights\"] = weights\n", + "\n", + "job = vapo_lib.run_apd(params, OUTPUT_PATH, display_name)\n", + "print(f\"Job ID: {job.name}\")\n", + "\n", + "progress_form = vapo_lib.ProgressForm(params)\n", + "while progress_form.monitor_progress(job):\n", + " time.sleep(5)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "lo5mcTzwSgBP" + }, + "source": [ + "# Step 6: Inspect the results\n", + "For a clearer look at the specific responses generated by each prompt template during the optimization process, use the cell below.\n", + "This will allow you to inspect all the predictions made by all the\n", + "generated templates during one or multiple vertex prompt optimizer runs.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "1x6HSty759jY" + }, + "outputs": [], + "source": [ + "from IPython.display import HTML, display\n", + "\n", + "RESULT_PATH = \"[OUTPUT_PATH]\" # @param {type:\"string\"}\n", + "\n", + "results_ui = vapo_lib.ResultsUI(RESULT_PATH)\n", + "\n", + "results_df_html = \"\"\"\n", + "\n", + "\"\"\"\n", + "\n", + "display(HTML(results_df_html))\n", + "display(results_ui.get_container())" + ] + } + ], + "metadata": { + "colab": { + "name": "vertex_ai_prompt_optimizer_ui.ipynb", + "toc_visible": true, + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file From 58d01bdef4e5d439eadb8ee676af9188f7e0cd19 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 30 Aug 2025 19:14:31 -0700 Subject: [PATCH 13/20] Created using Colab --- .../vertex_ai_prompt_optimizer_ui.ipynb | 40 ++++++++++++++----- 1 file changed, 30 insertions(+), 10 deletions(-) diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb index 4e6a675..f45ebd3 100644 --- a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb +++ b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb @@ -154,13 +154,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": { "id": "8-Zw72vFORz_", - "outputId": "98b34e63-ec34-4799-adf8-fce2af428b25", "colab": { "base_uri": "https://localhost:8080/" - } + }, + "outputId": "98b34e63-ec34-4799-adf8-fce2af428b25" }, "outputs": [ { @@ -205,7 +205,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": { "id": "rJG1pVZO317x" }, @@ -237,7 +237,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": { "id": "mfgi_oR6tTIB" }, @@ -273,7 +273,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": { "id": "B2R3P8mMvK9q" }, @@ -298,7 +298,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": { "id": "fRHHTpaV4Xyo" }, @@ -346,11 +346,31 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": { - "id": "Z8NvNLTfxPTf" + "id": "Z8NvNLTfxPTf", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 356 + }, + "outputId": "f61609e6-408a-404f-eb7f-af7a992723a0" }, - "outputs": [], + "outputs": [ + { + "output_type": "error", + "ename": "ValueError", + "evalue": "Unsupported file location. Only GCS paths starting with 'gs://' are supported.", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/tmp/ipython-input-3874795059.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 16\u001b[0m )\n\u001b[1;32m 17\u001b[0m \u001b[0minput_data_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"{INPUT_DATA_PATH}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m vapo_lib.validate_prompt_and_data(\n\u001b[0m\u001b[1;32m 19\u001b[0m \u001b[0;34m\"\\n\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mSYSTEM_INSTRUCTION\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mPROMPT_TEMPLATE\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[0minput_data_path\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/content/vapo_lib.py\u001b[0m in \u001b[0;36mvalidate_prompt_and_data\u001b[0;34m(template, dataset_path, placeholder_to_content, label_enforced)\u001b[0m\n\u001b[1;32m 159\u001b[0m ) -> None:\n\u001b[1;32m 160\u001b[0m \u001b[0;34m\"\"\"Validates the prompt template and the dataset.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 161\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 162\u001b[0m \u001b[0mplaceholder_to_content_json\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mplaceholder_to_content\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 163\u001b[0m \u001b[0mtemplate\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mre\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mr\"(? 139\u001b[0;31m \u001b[0mdata_str\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_file_from_gcs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 140\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 141\u001b[0m \u001b[0;31m# Parse based on file type\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/content/vapo_lib.py\u001b[0m in \u001b[0;36mload_file_from_gcs\u001b[0;34m(dataset)\u001b[0m\n\u001b[1;32m 86\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 88\u001b[0;31m raise ValueError(\n\u001b[0m\u001b[1;32m 89\u001b[0m \u001b[0;34m\"Unsupported file location. Only GCS paths starting with 'gs://' are\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 90\u001b[0m \u001b[0;34m\" supported.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mValueError\u001b[0m: Unsupported file location. Only GCS paths starting with 'gs://' are supported." + ] + } + ], "source": [ "import datetime\n", "import json\n", From 6721823b18b29bfd7bf309d7512d7c175beb907b Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Mon, 1 Sep 2025 16:33:14 -0700 Subject: [PATCH 14/20] Created using Colab --- .../vertex_ai_prompt_optimizer_ui.ipynb | 67 ++++--------------- 1 file changed, 13 insertions(+), 54 deletions(-) diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb index f45ebd3..ff4350c 100644 --- a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb +++ b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb @@ -12,7 +12,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": { "id": "hlI1rYKa2IGx" }, @@ -129,7 +129,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": null, "metadata": { "id": "NyKGtVQjgx13" }, @@ -154,33 +154,11 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": { - "id": "8-Zw72vFORz_", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "98b34e63-ec34-4799-adf8-fce2af428b25" + "id": "8-Zw72vFORz_" }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "--2025-08-31 02:12:00-- https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", - "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n", - "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n", - "HTTP request sent, awaiting response... 200 OK\n", - "Length: 37206 (36K) [text/plain]\n", - "Saving to: ‘vapo_lib.py’\n", - "\n", - "\rvapo_lib.py 0%[ ] 0 --.-KB/s \rvapo_lib.py 100%[===================>] 36.33K --.-KB/s in 0.006s \n", - "\n", - "2025-08-31 02:12:00 (5.64 MB/s) - ‘vapo_lib.py’ saved [37206/37206]\n", - "\n" - ] - } - ], + "outputs": [], "source": [ "!wget https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", "import vapo_lib" @@ -205,7 +183,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "metadata": { "id": "rJG1pVZO317x" }, @@ -237,7 +215,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": { "id": "mfgi_oR6tTIB" }, @@ -273,7 +251,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "metadata": { "id": "B2R3P8mMvK9q" }, @@ -298,7 +276,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": { "id": "fRHHTpaV4Xyo" }, @@ -346,31 +324,11 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": { - "id": "Z8NvNLTfxPTf", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 356 - }, - "outputId": "f61609e6-408a-404f-eb7f-af7a992723a0" + "id": "Z8NvNLTfxPTf" }, - "outputs": [ - { - "output_type": "error", - "ename": "ValueError", - "evalue": "Unsupported file location. Only GCS paths starting with 'gs://' are supported.", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m/tmp/ipython-input-3874795059.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 16\u001b[0m )\n\u001b[1;32m 17\u001b[0m \u001b[0minput_data_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"{INPUT_DATA_PATH}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m vapo_lib.validate_prompt_and_data(\n\u001b[0m\u001b[1;32m 19\u001b[0m \u001b[0;34m\"\\n\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mSYSTEM_INSTRUCTION\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mPROMPT_TEMPLATE\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[0minput_data_path\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/content/vapo_lib.py\u001b[0m in \u001b[0;36mvalidate_prompt_and_data\u001b[0;34m(template, dataset_path, placeholder_to_content, label_enforced)\u001b[0m\n\u001b[1;32m 159\u001b[0m ) -> None:\n\u001b[1;32m 160\u001b[0m \u001b[0;34m\"\"\"Validates the prompt template and the dataset.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 161\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 162\u001b[0m \u001b[0mplaceholder_to_content_json\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mplaceholder_to_content\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 163\u001b[0m \u001b[0mtemplate\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mre\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mr\"(? 139\u001b[0;31m \u001b[0mdata_str\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_file_from_gcs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 140\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 141\u001b[0m \u001b[0;31m# Parse based on file type\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/content/vapo_lib.py\u001b[0m in \u001b[0;36mload_file_from_gcs\u001b[0;34m(dataset)\u001b[0m\n\u001b[1;32m 86\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 88\u001b[0;31m raise ValueError(\n\u001b[0m\u001b[1;32m 89\u001b[0m \u001b[0;34m\"Unsupported file location. Only GCS paths starting with 'gs://' are\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 90\u001b[0m \u001b[0;34m\" supported.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mValueError\u001b[0m: Unsupported file location. Only GCS paths starting with 'gs://' are supported." - ] - } - ], + "outputs": [], "source": [ "import datetime\n", "import json\n", @@ -506,6 +464,7 @@ "name": "vertex_ai_prompt_optimizer_ui.ipynb", "toc_visible": true, "provenance": [], + "private_outputs": true, "include_colab_link": true }, "kernelspec": { From fb8ba12b43cd3faa4af00f08e5844d50cf2a5593 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Tue, 2 Sep 2025 05:36:47 +0600 Subject: [PATCH 15/20] Rename gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb to gemini/prompts/AXEE (#5) --- .../vertex_ai_prompt_optimizer_ui.ipynb => AXEE} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename gemini/prompts/{prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb => AXEE} (99%) diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/AXEE similarity index 99% rename from gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb rename to gemini/prompts/AXEE index ff4350c..a58a21f 100644 --- a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb +++ b/gemini/prompts/AXEE @@ -474,4 +474,4 @@ }, "nbformat": 4, "nbformat_minor": 0 -} \ No newline at end of file +} From 71b7e65979e4746178940d0bd2b1e9615726068d Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Tue, 2 Sep 2025 05:37:35 +0600 Subject: [PATCH 16/20] Created using Colab --- .../vertex_ai_prompt_optimizer_ui.ipynb | 477 ++++++++++++++++++ 1 file changed, 477 insertions(+) create mode 100644 gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb new file mode 100644 index 0000000..ff4350c --- /dev/null +++ b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb @@ -0,0 +1,477 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "hlI1rYKa2IGx" + }, + "outputs": [], + "source": [ + "# Copyright 2024 Google LLC\n", + "#\n", + "# Licensed under the Apache License, Version 2.0 (the \"License\");\n", + "# you may not use this file except in compliance with the License.\n", + "# You may obtain a copy of the License at\n", + "#\n", + "# https://www.apache.org/licenses/LICENSE-2.0\n", + "#\n", + "# Unless required by applicable law or agreed to in writing, software\n", + "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", + "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", + "# See the License for the specific language governing permissions and\n", + "# limitations under the License." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "RN8N3O43QDT5" + }, + "source": [ + "# Vertex Prompt Optimizer Notebook UI (Preview)\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \"Google
Open in Colab\n", + " \n", + " 		\n", + " \n", + " \"Google
Open in Colab Enterprise\n", + " \n", + " 		\n", + " \n", + " \"Vertex
Open in Vertex AI Workbench\n", + " \n", + " 		\n", + " \n", + " \"GitHub
View on GitHub\n", + " \n", + "
\n", + "\n", + "
\n", + "\n", + "Share to:\n", + "\n", + "\n", + " \"LinkedIn\n", + "\n", + "\n", + "\n", + " \"Bluesky\n", + "\n", + "\n", + "\n", + " \"X\n", + "\n", + "\n", + "\n", + " \"Reddit\n", + "\n", + "\n", + "\n", + " \"Facebook\n", + " " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "pHyuJTFr2IGx" + }, + "source": [ + "# Overview\n", + "This Notebook showcases the Vertex AI prompt optimizer, a tool that iteratively optimizes prompts to suit a target model (e.g., `gemini-2.0-flash`) using target-specific metric(s).\n", + "\n", + "Key Use Cases:\n", + "\n", + "* Prompt Optimization: Enhance the quality of an initial prompt by refining its structure and content to match the target model's optimal input characteristics.\n", + "\n", + "* Prompt Translation: Adapt prompts optimized for one model to work effectively with a different target model.\n", + "\n", + "For the detailed documentation please see [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "61RBz8LLbxCR" + }, + "source": [ + "## Getting Started" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "dmWOrTJ3gx13" + }, + "source": [ + "### Authenticate your notebook environment (Colab only)\n", + "\n", + "Authenticate your environment on Google Colab.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "NyKGtVQjgx13" + }, + "outputs": [], + "source": [ + "import sys\n", + "\n", + "if \"google.colab\" in sys.modules:\n", + " from google.colab import auth\n", + "\n", + " auth.authenticate_user()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tTtKHedrO1Rx" + }, + "source": [ + "# Step 0: Install packages and libraries" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "8-Zw72vFORz_" + }, + "outputs": [], + "source": [ + "!wget https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", + "import vapo_lib" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-p59jd5rOp4q" + }, + "source": [ + "# Step 1: Create a prompt template and system instructions\n", + "Provide your system intruction and prompt template below. Refer to [here]( https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#template-si) for instructions.\n", + "\n", + "Prompts consist of two key components:\n", + "\n", + "- System Instruction: System instruction is the instruction that get passed to the model before any user input in the prompt. This is the fixed part of the prompt template shared across all queries for a given task.\n", + "- Prompt template: A task is the text in the prompt that you want the model to provide a response for. Context is information that you include in the prompt that the model uses or references when generating a response. These are the dynamic parts of the prompt template that changes based on the task.\n", + "\n", + "Prompt Optimizer enables the optimization or translation of the System Instruction template, while the prompt template remains essential for evaluating and selecting the best System Instruction template." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "rJG1pVZO317x" + }, + "outputs": [], + "source": [ + "SYSTEM_INSTRUCTION = (\n", + " \"Answer the following question. Let's think step by step.\\n\" # @param\n", + ")\n", + "PROMPT_TEMPLATE = \"Question: {question}\\n\\nAnswer: {target}\" # @param" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5y-cmg0TQP6v" + }, + "source": [ + "# Step 2: Configure project settings\n", + "To optimize the prompt for your target Google model, provide a CSV or JSONL file containing labeled validation samples (input, ground truth output pairs). Refer to [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#prepare-sample-prompts) for instructions.\n", + "\n", + "Focus on examples that specifically demonstrate the issues you want to address.\n", + "Recommendation: Use 50-100 distinct samples for reliable results. However, the tool can still be effective with as few as 5 samples.\n", + "For prompt translation (e.g. 3P model to Google model, PaLM 2 to Gemini):\n", + "\n", + "Consider using the source model to label examples that the target model struggles with, helping to identify areas for improvement.\n", + "When you select a source model, you don't need to provide labels for the input examples.\n", + "While the source model selection is limited to Google models, it still supports labeled inputs from non-Google models. If you wish to select a non-Google source model, you will need to provide labels for your input examples.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "mfgi_oR6tTIB" + }, + "outputs": [], + "source": [ + "# @markdown **Project setup**:
\n", + "PROJECT_ID = \"[YOUR_PROJECT]\" # @param {type:\"string\"}\n", + "LOCATION = \"us-central1\" # @param {type:\"string\"}\n", + "OUTPUT_PATH = \"[OUTPUT_PATH]\" # @param {type:\"string\"}\n", + "INPUT_DATA_PATH = \"[INPUT_DATA_PATH]\" # @param {type:\"string\"}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ucebZHkHRxKH" + }, + "source": [ + "# Step 3: Configure optimization settings\n", + "The optimization configurations are defaulted to the values that are most commonly used, which we recommend using as the initial set-up.\n", + "\n", + "The most important settings are:\n", + "\n", + "* Target Model: Which model you are trying to optimize your prompts to.\n", + "* Thinking Budget: The thinking budget for thinking models like Gemini-2.5. Default to -1, which means no thinking for non-thinking models and auto thinking for thinking models. Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/thinking) to learn more about manual budget settings.\n", + "* Optimization Mode: The mode in which you are trying to optimize your prompt with.\n", + "* Evaluation Metrics: The evaluation metrics in which you are trying to optimize your prompts against.\n", + "* Translation Source Field Name: fill in with the corresponding field name of the source text in the data if translation metrics like Comet or MetricX are selected. Otherwise, leave it as empty.\n", + "\n", + "Note that all evaluation metrics are expected to have the larger-the-better property. Therefore, we have modified the MetricX value to between 0 (worst) and 25 (best).\n", + "Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#configuration) to learn more about the different configuration settings and how to best utilize them." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "B2R3P8mMvK9q" + }, + "outputs": [], + "source": [ + "TARGET_MODEL = \"gemini-2.0-flash-001\" # @param [\"gemini-2.5-flash-lite\", \"gemini-2.5-flash\", \"gemini-2.5-pro\", \"gemini-2.0-flash-lite-001\", \"gemini-2.0-flash-001\"]\n", + "THINKING_BUDGET = -1 # @param {type:\"integer\"}\n", + "OPTIMIZATION_MODE = \"instruction_and_demo\" # @param [\"instruction\", \"demonstration\", \"instruction_and_demo\"]\n", + "EVAL_METRIC = \"question_answering_correctness\" # @param [\"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "TRANSLATION_SOURCE_FIELD_NAME = \"\" # @param {type:\"string\"}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kO7fO0qTSNLs" + }, + "source": [ + "# Step 4: Configure advanced optimization settings [Optional]\n", + "Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#configuration) to learn more about the different configuration settings and how to best utilize them." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "fRHHTpaV4Xyo" + }, + "outputs": [], + "source": [ + "# @markdown **Instruction Optimization Configs**:
\n", + "NUM_INST_OPTIMIZATION_STEPS = 10 # @param {type:\"integer\"}\n", + "\n", + "# @markdown **Demonstration Optimization Configs**:
\n", + "NUM_DEMO_OPTIMIZATION_STEPS = 10 # @param {type:\"integer\"}\n", + "NUM_DEMO_PER_PROMPT = 3 # @param {type:\"integer\"}\n", + "\n", + "# @markdown **Model Configs**:
\n", + "TARGET_MODEL_QPS = 3.0 # @param {type:\"number\"}\n", + "EVAL_QPS = 3.0 # @param {type:\"number\"}\n", + "\n", + "# @markdown **Multi-metric Configs**:
\n", + "# @markdown Use this section only if you need more than one metric for optimization. This will override the metric you picked above.\n", + "EVAL_METRIC_1 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_1_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "EVAL_METRIC_2 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_2_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "EVAL_METRIC_3 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_3_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "METRIC_AGGREGATION_TYPE = \"weighted_sum\" # @param [\"weighted_sum\", \"weighted_average\"]\n", + "\n", + "# @markdown **Misc Configs**:
\n", + "PLACEHOLDER_TO_VALUE = \"{}\" # @param\n", + "RESPONSE_MIME_TYPE = \"text/plain\" # @param [\"text/plain\", \"application/json\", \"text/x.enum\"] {type:\"string\"}\n", + "RESPONSE_SCHEMA = \"\"\n", + "TARGET_LANGUAGE = \"English\" # @param [\"English\", \"French\", \"German\", \"Hebrew\", \"Hindi\", \"Italian\", \"Japanese\", \"Korean\", \"Portuguese\", \"Simplified Chinese\", \"Spanish\", \"Traditional Chinese\"] {type:\"string\"}\n", + "TOOLS = \"\" # @param\n", + "TOOL_CONFIG = \"\" # @param" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "X7Mgb0EHSSFk" + }, + "source": [ + "# Step 5: Run Prompt Optimizer\n", + "A progress bar will appear to let you know how long the job takes." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Z8NvNLTfxPTf" + }, + "outputs": [], + "source": [ + "import datetime\n", + "import json\n", + "import time\n", + "\n", + "timestamp = datetime.datetime.now().strftime(\"%Y-%m-%dT%H:%M:%S\")\n", + "display_name = f\"pt_{timestamp}\"\n", + "\n", + "label_enforced = vapo_lib.is_run_target_required(\n", + " [\n", + " EVAL_METRIC,\n", + " EVAL_METRIC_1,\n", + " EVAL_METRIC_2,\n", + " EVAL_METRIC_3,\n", + " ],\n", + " \"\",\n", + ")\n", + "input_data_path = f\"{INPUT_DATA_PATH}\"\n", + "vapo_lib.validate_prompt_and_data(\n", + " \"\\n\".join([SYSTEM_INSTRUCTION, PROMPT_TEMPLATE]),\n", + " input_data_path,\n", + " PLACEHOLDER_TO_VALUE,\n", + " label_enforced,\n", + ")\n", + "\n", + "output_path = f\"{OUTPUT_PATH}/{display_name}\"\n", + "\n", + "params = {\n", + " \"project\": PROJECT_ID,\n", + " \"num_steps\": NUM_INST_OPTIMIZATION_STEPS,\n", + " \"system_instruction\": SYSTEM_INSTRUCTION,\n", + " \"prompt_template\": PROMPT_TEMPLATE,\n", + " \"target_model\": TARGET_MODEL,\n", + " \"target_model_qps\": TARGET_MODEL_QPS,\n", + " \"target_model_location\": LOCATION,\n", + " \"optimizer_model_location\": LOCATION,\n", + " \"eval_qps\": EVAL_QPS,\n", + " \"optimization_mode\": OPTIMIZATION_MODE,\n", + " \"num_demo_set_candidates\": NUM_DEMO_OPTIMIZATION_STEPS,\n", + " \"demo_set_size\": NUM_DEMO_PER_PROMPT,\n", + " \"aggregation_type\": METRIC_AGGREGATION_TYPE,\n", + " \"data_limit\": 50,\n", + " \"input_data_path\": input_data_path,\n", + " \"output_path\": output_path,\n", + " \"response_mime_type\": RESPONSE_MIME_TYPE,\n", + " \"response_schema\": RESPONSE_SCHEMA,\n", + " \"language\": TARGET_LANGUAGE,\n", + " \"placeholder_to_content\": json.loads(PLACEHOLDER_TO_VALUE),\n", + " \"tools\": TOOLS,\n", + " \"tool_config\": TOOL_CONFIG,\n", + " \"translation_source_field_name\": TRANSLATION_SOURCE_FIELD_NAME,\n", + " \"thinking_budget\": THINKING_BUDGET,\n", + "}\n", + "\n", + "if EVAL_METRIC_1 == \"NA\":\n", + " params[\"eval_metrics_types\"] = [EVAL_METRIC]\n", + " params[\"eval_metrics_weights\"] = [1.0]\n", + "else:\n", + " metrics = []\n", + " weights = []\n", + " for metric, weight in zip(\n", + " [EVAL_METRIC_1, EVAL_METRIC_2, EVAL_METRIC_3],\n", + " [EVAL_METRIC_1_WEIGHT, EVAL_METRIC_2_WEIGHT, EVAL_METRIC_3_WEIGHT],\n", + " ):\n", + " if metric == \"NA\":\n", + " break\n", + " metrics.append(metric)\n", + " weights.append(weight)\n", + " params[\"eval_metrics_types\"] = metrics\n", + " params[\"eval_metrics_weights\"] = weights\n", + "\n", + "job = vapo_lib.run_apd(params, OUTPUT_PATH, display_name)\n", + "print(f\"Job ID: {job.name}\")\n", + "\n", + "progress_form = vapo_lib.ProgressForm(params)\n", + "while progress_form.monitor_progress(job):\n", + " time.sleep(5)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "lo5mcTzwSgBP" + }, + "source": [ + "# Step 6: Inspect the results\n", + "For a clearer look at the specific responses generated by each prompt template during the optimization process, use the cell below.\n", + "This will allow you to inspect all the predictions made by all the\n", + "generated templates during one or multiple vertex prompt optimizer runs.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "1x6HSty759jY" + }, + "outputs": [], + "source": [ + "from IPython.display import HTML, display\n", + "\n", + "RESULT_PATH = \"[OUTPUT_PATH]\" # @param {type:\"string\"}\n", + "\n", + "results_ui = vapo_lib.ResultsUI(RESULT_PATH)\n", + "\n", + "results_df_html = \"\"\"\n", + "\n", + "\"\"\"\n", + "\n", + "display(HTML(results_df_html))\n", + "display(results_ui.get_container())" + ] + } + ], + "metadata": { + "colab": { + "name": "vertex_ai_prompt_optimizer_ui.ipynb", + "toc_visible": true, + "provenance": [], + "private_outputs": true, + "include_colab_link": true + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file From 06379fe5aefddc1f6ab9aeca16f00912d462742a Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Tue, 2 Sep 2025 05:38:38 +0600 Subject: [PATCH 17/20] Rename vertex_ai_prompt_optimizer_ui.ipynb to AXEE.ipynb --- .../{vertex_ai_prompt_optimizer_ui.ipynb => AXEE.ipynb} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename gemini/prompts/prompt_optimizer/{vertex_ai_prompt_optimizer_ui.ipynb => AXEE.ipynb} (99%) diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/AXEE.ipynb similarity index 99% rename from gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb rename to gemini/prompts/prompt_optimizer/AXEE.ipynb index ff4350c..a58a21f 100644 --- a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb +++ b/gemini/prompts/prompt_optimizer/AXEE.ipynb @@ -474,4 +474,4 @@ }, "nbformat": 4, "nbformat_minor": 0 -} \ No newline at end of file +} From 68ac3b5c5acf2dd58304bfb873e88a2d4360ac3b Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 27 Sep 2025 20:18:08 +0600 Subject: [PATCH 18/20] Rename AXEE to AXEE Synthesis --- gemini/prompts/{AXEE => AXEE Synthesis} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename gemini/prompts/{AXEE => AXEE Synthesis} (100%) diff --git a/gemini/prompts/AXEE b/gemini/prompts/AXEE Synthesis similarity index 100% rename from gemini/prompts/AXEE rename to gemini/prompts/AXEE Synthesis From 59efc0a9c93d084ff3b130f0ddbd7837472a9842 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 4 Oct 2025 19:33:08 +0600 Subject: [PATCH 19/20] Add initial project IDE configuration files Added .idea directory with project-specific configuration files, including code style settings, module definitions, and device streaming preferences for the development environment. --- .idea/.github.iml | 9 + .idea/.gitignore | 3 + .idea/SweepConfig.xml | 15 + .idea/codeStyles/Project.xml | 120 +++ .idea/codeStyles/codeStyleConfig.xml | 5 + .idea/misc.xml | 1176 ++++++++++++++++++++++++++ .idea/modules.xml | 8 + .idea/vcs.xml | 6 + 8 files changed, 1342 insertions(+) create mode 100644 .idea/.github.iml create mode 100644 .idea/.gitignore create mode 100644 .idea/SweepConfig.xml create mode 100644 .idea/codeStyles/Project.xml create mode 100644 .idea/codeStyles/codeStyleConfig.xml create mode 100644 .idea/misc.xml create mode 100644 .idea/modules.xml create mode 100644 .idea/vcs.xml diff --git a/.idea/.github.iml b/.idea/.github.iml new file mode 100644 index 0000000..d6ebd48 --- /dev/null +++ b/.idea/.github.iml @@ -0,0 +1,9 @@ + + + + + + + + + \ No newline at end of file diff --git a/.idea/.gitignore b/.idea/.gitignore new file mode 100644 index 0000000..26d3352 --- /dev/null +++ b/.idea/.gitignore @@ -0,0 +1,3 @@ +# Default ignored files +/shelf/ +/workspace.xml diff --git a/.idea/SweepConfig.xml b/.idea/SweepConfig.xml new file mode 100644 index 0000000..d39be4f --- /dev/null +++ b/.idea/SweepConfig.xml @@ -0,0 +1,15 @@ + + + + + + \ No newline at end of file diff --git a/.idea/codeStyles/Project.xml b/.idea/codeStyles/Project.xml new file mode 100644 index 0000000..57b2461 --- /dev/null +++ b/.idea/codeStyles/Project.xml @@ -0,0 +1,120 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/codeStyles/codeStyleConfig.xml b/.idea/codeStyles/codeStyleConfig.xml new file mode 100644 index 0000000..a55e7a1 --- /dev/null +++ b/.idea/codeStyles/codeStyleConfig.xml @@ -0,0 +1,5 @@ + + + + \ No newline at end of file diff --git a/.idea/misc.xml b/.idea/misc.xml new file mode 100644 index 0000000..3fe2d8e --- /dev/null +++ b/.idea/misc.xml @@ -0,0 +1,1176 @@ + + + + + + + + + \ No newline at end of file diff --git a/.idea/modules.xml b/.idea/modules.xml new file mode 100644 index 0000000..854e742 --- /dev/null +++ b/.idea/modules.xml @@ -0,0 +1,8 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/vcs.xml b/.idea/vcs.xml new file mode 100644 index 0000000..35eb1dd --- /dev/null +++ b/.idea/vcs.xml @@ -0,0 +1,6 @@ + + + + + + \ No newline at end of file From b20864972003d3ffc03a078954c503f5de6d5e9f Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 4 Oct 2025 19:36:48 +0600 Subject: [PATCH 20/20] Add device streaming and device manager configs Added .idea/caches/deviceStreaming.xml and .idea/deviceManager.xml to configure device streaming and device manager settings. Updated .idea/misc.xml with related changes for improved IDE device management. --- .idea/caches/deviceStreaming.xml | 1174 ++++++++++++++++++++++++++++++ .idea/deviceManager.xml | 13 + .idea/misc.xml | 1170 ----------------------------- 3 files changed, 1187 insertions(+), 1170 deletions(-) create mode 100644 .idea/caches/deviceStreaming.xml create mode 100644 .idea/deviceManager.xml diff --git a/.idea/caches/deviceStreaming.xml b/.idea/caches/deviceStreaming.xml new file mode 100644 index 0000000..c833fcf --- /dev/null +++ b/.idea/caches/deviceStreaming.xml @@ -0,0 +1,1174 @@ + + + + + + \ No newline at end of file diff --git a/.idea/deviceManager.xml b/.idea/deviceManager.xml new file mode 100644 index 0000000..91f9558 --- /dev/null +++ b/.idea/deviceManager.xml @@ -0,0 +1,13 @@ + + + + + + \ No newline at end of file diff --git a/.idea/misc.xml b/.idea/misc.xml index 3fe2d8e..1945ce5 100644 --- a/.idea/misc.xml +++ b/.idea/misc.xml @@ -1,1175 +1,5 @@ - - -