Okada-Agentic-Systems

Contents:
Setup Instructions
Create Environment variables
Running app.py
API Testing
Notes
Sample
Contributors

Required Tools:

• Python 3.11.9 (via pyenv)
• Postman (for testing endpoints)
• Pinecone (for vector-based retrieval)
• OpenAI API Key

Setup Instructions:

1. Clone the repository

git clone https://github.com/your-org/Okada-Agentic-Systems.git
cd Okada-Agentic-Systems

2. Install Python (via pyenv)

Ensure Python 3.11.9 is installed and used for this project.

For MacOS users:

• Install pyenv via Homebrew:

brew install pyenv

• Install Python 3.11.9 with pyenv:

pyenv install 3.11.9
pyenv local 3.11.9

• Check version:

python --version
# Should output: Python 3.11.9

For Windows Users:

• Download Python 3.11.9 from the official Python site
• During installation, ensure you check this box: ✅ Add Python 3.11 to PATH
• Confirm installation:

python --version
# Should output: Python 3.11.9

3. Set Up Virtual Environment

python3.11 -m venv venv

# For macOS/ Linux users
source venv/bin/activate

# Or if you're using Windows
venv/Scripts/activate

4. Install Dependencies

Update pip:

pip update && pip upgrade

Install the packages from the requirements.txt

pip install -r requirements.txt

If any errors occur, especially around pandas and openai, ensure you're using the latest version of Python (3.10+) and the packages.

Creating Environment Variables

• Create a .env file at the root of the project (variable templates are in the .env.example)

OPENAI_API_KEY=insert-api-key-here

PINECONE_API_KEY=your-pinecone-api-key
PINECONE_ENVIRONMENT=aws-us-east-1
PINECONE_INDEX_NAME=your-index-name

Run the Application on the Development server:

• From the root directory:

python app.py

• Server should run on: http://localhost:5001
• Make sure your OpenAI package is up-to-date:

pip install --upgrade openai

API Testing via Postman

Example Routes

• Speech-To-Text (STT)

Endpoint: /transcribe
Method: POST
Body: form-data
- file: [Upload a .wav or .mp3 audio file]

• LLM Chat

Endpoint: /chat
Method: POST
Body: JSON
{
  "message": "What is the monthly rent?"
}

• Upload RAG Documents

Endpoint: /upload_rag_docs
Method: POST
Body: form-data
- file: [Upload PDF, TXT, CSV, or JSON files]

More routes are available under the /routes.

Notes

• Keep all document uploads in the uploads/documents/ directory.
• Document formats supported: .pdf, .txt, .csv, .json
• Audio formats supported: .wav, .mp3, .m4a, etc. (see OpenAI Whisper supported formats)

Sample

Contributors:

Nico Henry 
Sabrina Ira
Isaac Mbambo

---

Return To Top