cs_year_explorer

A Python package that provides a structured summary of key developments in computer science for a given year. Quickly access concise and relevant information about major breakthroughs, notable research papers, technological advancements, and influential events in CS history.

---

📦 Installation

Install the package using pip:

pip install cs_year_explorer

---

🚀 Usage

Basic Usage (uses default LLM7 model)

from cs_year_explorer import cs_year_explorer

# Example: Get CS developments for the year 2023
response = cs_year_explorer("2023")
print(response)

Custom LLM Integration

You can replace the default LLM (ChatLLM7) with any LangChain-compatible model:

Using OpenAI

from langchain_openai import ChatOpenAI
from cs_year_explorer import cs_year_explorer

llm = ChatOpenAI()
response = cs_year_explorer("2020", llm=llm)
print(response)

Using Anthropic

from langchain_anthropic import ChatAnthropic
from cs_year_explorer import cs_year_explorer

llm = ChatAnthropic()
response = cs_year_explorer("2019", llm=llm)
print(response)

Using Google Generative AI

from langchain_google_genai import ChatGoogleGenerativeAI
from cs_year_explorer import cs_year_explorer

llm = ChatGoogleGenerativeAI()
response = cs_year_explorer("2022", llm=llm)
print(response)

---

🔧 Parameters

Parameter	Type	Description
user_input	str	The year (e.g., "2023") or query to analyze (e.g., "major CS events in 2020")
api_key	Optional[str]	LLM7 API key (default: fetched from LLM7_API_KEY environment variable)
llm	Optional[BaseChatModel]	Custom LangChain LLM instance (default: ChatLLM7)

---

🔑 API Key

• Default LLM: Uses ChatLLM7 from langchain_llm7.
• Free Tier: Sufficient for most use cases.
• Custom API Key: Pass via environment variable LLM7_API_KEY or directly:

  cs_year_explorer("2021", api_key="your_api_key_here")

• Get a Free Key: Register at https://token.llm7.io/.

---

📜 Features

• Structured summary of major CS breakthroughs for any year.
• Covers research papers, tech advancements, and influential events.
• Works with multiple LLM providers (OpenAI, Anthropic, Google, etc.).
• Regex-validated output for consistency.

---

📝 Example Output

For cs_year_explorer("2023"), the response might include:

[
    "2023: Foundation Models Breakthroughs",
    "   - GPT-4 released by OpenAI (March)",
    "   - Claude 2 by Anthropic (July)",
    "   - Research papers: 'Scaling Laws' (Kaplan et al.)",
    "2023: Quantum Computing Milestones",
    "   - IBM's 433-qubit Osprey processor",
    "   - Google's error-corrected logical qubit demo"
]

---

🔧 Dependencies

• Python 3.8+
• langchain-core, langchain_llm7 (default), or any LangChain-compatible LLM.

---

📢 Support & Issues

For bugs or feature requests, open an issue on GitHub.

---

👤 Author

• Eugene Evstafev (@chigwell)
• Email: hi@euegne.plus

---

📜 License

MIT License (see LICENSE).