This project provides a full-stack, locally-runnable RAG application powered by the DSPy framework, targeting developers and researchers who need to build and deploy NLP solutions with enhanced privacy and control. It integrates Ollama, Chroma DB, and Arize Phoenix for a comprehensive, self-contained ecosystem.

How It Works

The application leverages DSPy as the core orchestration layer for language models, enabling efficient prompt engineering and retrieval-augmented generation. Ollama serves local LLMs and embedding models, while Chroma DB handles vector storage for semantic search. Arize Phoenix provides observability into the system's performance and traces queries. A FastAPI backend exposes API endpoints for NLP tasks, and a Streamlit frontend offers an interactive user interface.

Quick Start & Requirements

• Installation: Clone the repository, set up a local Ollama instance, and use poetry for backend/frontend environment management.
• Prerequisites: Docker and Docker-Compose are recommended for easier setup. Requires a local Ollama instance.
• Setup: Detailed instructions are provided for both local development and Docker Compose deployment.
• Links: Backend OpenAPI docs, Streamlit frontend, Phoenix UI.

Highlighted Details

• Fully local execution for enhanced privacy and security.
• Integrates DSPy, Ollama, Chroma DB, and Arize Phoenix.
• FastAPI backend for robust API endpoints.
• Streamlit frontend for an intuitive user experience.

Maintenance & Community

Contributions are welcome via pull requests and issues.

Licensing & Compatibility

The repository does not explicitly state a license. Compatibility for commercial or closed-source use is not specified.

Limitations & Caveats

The project does not specify a license, which may impact commercial adoption. Detailed performance benchmarks or comparisons are not provided in the README.