LLMpedia is a Streamlit application that provides a user-friendly interface to explore and interact with Large Language Model research papers.

• Browse and search LLM research papers from arXiv.
• View paper summaries, illustrations, and key insights generated by AI models.
• Explore topics through interactive visualizations (e.g., UMAP clusters).
• Chat with an AI assistant about LLM research, with configurable models and source citations.
• Access weekly research reviews summarizing key developments.
• Discover related code repositories.

The data displayed in LLMpedia originates primarily from arXiv. Raw paper data is processed, analyzed, and enriched through a separate pipeline managed in the llmpedia_workflows repository. This includes:

• Fetching new papers
• Generating summaries and artwork
• Extracting key information
• Topic modeling and embedding generation

The processed data is then stored in the PostgreSQL database used by this application.

1. Clone this repository: git clone <repository_url>
2. Navigate to the project directory: cd llmpedia
3. Install dependencies: pip install -r requirements.txt
4. Copy the environment template: cp .env.template .env
5. Configure your environment variables in the .env file (see below).
6. Ensure you have access to the PostgreSQL database populated by the llmpedia_workflows pipeline.
7. Run the Streamlit app locally: streamlit run app.py

This app requires access to a PostgreSQL database containing LLMpedia data. Configure the database connection in the .env file.

The following environment variables are required to run the app:

# Database Configuration
DB_NAME
DB_HOST
DB_PORT
DB_USER
DB_PASSWORD

# LLM API Keys (for chat functionality)
OPENAI_API_KEY
ANTHROPIC_API_KEY
COHERE_API_KEY
HUGGINGFACE_API_KEY
GROQ_API_KEY

# AWS Configuration (for S3 access)
AWS_ACCESS_KEY_ID
AWS_SECRET_ACCESS_KEY
AWS_REGION