# thinkany-ai/rag-search

RAG Search API

Repository: https://github.com/thinkany-ai/rag-search
Canonical: https://ross.abutalabs.com/products/rag-search
Homepage: https://thinkany.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai-search-engine, rag
Last push: 2024-07-29T14:12:46+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 63
- inputs: {"age_days": 891, "days_push": 765, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1180, forks 157 (observed 2026-08-28T04:03:53.602283+00:00)

## What it is
A RAG (retrieval-augmented generation) search API service built with FastAPI by the ThinkAny AI search engine team. It combines web search (via Serper/Google), OpenAI embeddings, Zilliz vector storage, and optional reranking/filtering to return relevant search results for RAG pipelines.

## Use cases
- build a rag search api for my ai search engine
- retrieve web search results with embeddings and reranking
- self-host a retrieval service backed by zilliz vector database
- add google search plus semantic filtering to my llm app
- serve rag search results over a rest api

## When to choose
- you want a ready-made RAG search pipeline combining web search, embeddings, and reranking
- you use Zilliz/Milvus and OpenAI-compatible embedding models
- you need a simple FastAPI-based REST endpoint to plug into an AI search app

## When to avoid
- you need a full RAG framework with document ingestion and chunking
- you want a managed service rather than self-hosting with your own API keys
- you don't use OpenAI-compatible models or Zilliz/Milvus

## Facets
- artifact type: service
- maturity: active
- function: rag, search-engine, api-framework, llm-inference, web-scraping
- domain: artificial-intelligence, apis
- platform: python, self-hosted
- tags: fastapi, serper, zilliz, milvus, reranking, ai-search, embeddings, openai, retrieval-augmented-generation, search, docker, web-server

## Member repositories
- thinkany-ai/rag-search (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:53.602283+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:25:21.943782+00:00, confidence not recorded.
  - readme: https://github.com/thinkany-ai/rag-search (fetched 2026-08-28T04:03:53.602283+00:00, sha a08e578e4938)
  - homepage: https://thinkany.ai (fetched 2026-08-29T12:32:30.535698+00:00, sha 6b4286509ffc)
- Data as of 2026-08-30T08:39:29.467469+00:00.