thinkany-ai/rag-search
RAG Search API
Combines web search (via Serper/Google), vector embedding (OpenAI), and semantic reranking against a Milvus vector database to deliver hybrid RAG results with configurable filtering and relevance scoring. Built on FastAPI with pluggable search providers and optional result reranking for precision-tuned retrieval. Supports Bearer token authentication and configurable embedding dimensions for flexible vector storage backends.
1,181 stars. No commits in the last 6 months.
Stars
1,181
Forks
169
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/thinkany-ai/rag-search"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
brevia-ai/brevia
Extensible API and framework to build your Retrieval Augmented Generation (RAG) and Information...
swirlai/swirl-search
AI Search & RAG Without Moving Your Data. Get instant answers from your company's knowledge...
wzdavid/ThinkRAG
A LLM RAG system runs on your laptop. 大模型检索增强生成系统，可以轻松部署在笔记本电脑上，实现本地知识库智能问答。企业级SaaS版本请访问：
sankalp1999/code_qa
RAG on codebases using treesitter and LanceDB
Piazza-tech/Piazza-Updater
Piazza-Updater automates updates to a Weaviate database with real-time vectorial data. By...