This project provides a RAG (Retrieval-Augmented Generation) Search API, designed for developers and researchers looking to integrate advanced search capabilities into their applications. It offers a flexible backend for querying and retrieving relevant information, enhancing AI models with external knowledge.

How It Works

The API leverages a combination of search providers and vector databases for efficient retrieval. It supports configurable parameters for reranking, detail extraction, and filtering based on similarity scores, allowing for fine-tuned search results. The architecture is built around FastAPI, enabling a robust and scalable API service.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Start server: uvicorn main:app --reload --port 8069
• Requires API keys for Serper and OpenAI, and optionally Zilliz.
• Configuration is managed via a .env file.

Highlighted Details

• Supports multiple search providers (e.g., Google via Serper).
• Integrates with vector databases like Zilliz.
• Offers advanced filtering and reranking options.
• Configurable detail extraction with minimum score and top-k parameters.

Maintenance & Community

No information on maintainers, community channels, or roadmap is available in the provided README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial use or closed-source linking is not detailed.

Limitations & Caveats

The project appears to be in an early stage, with no explicit versioning or stability guarantees mentioned. The README lacks comprehensive documentation, setup details, and licensing information, which may hinder adoption.