Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/thinkany-ai/rag-search
RAG Search API
https://github.com/thinkany-ai/rag-search
ai-search-engine rag
Last synced: about 2 months ago
JSON representation
RAG Search API
- Host: GitHub
- URL: https://github.com/thinkany-ai/rag-search
- Owner: thinkany-ai
- License: apache-2.0
- Created: 2024-03-25T14:40:03.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-07-29T14:12:46.000Z (5 months ago)
- Last Synced: 2024-07-30T08:28:43.585Z (5 months ago)
- Topics: ai-search-engine, rag
- Language: Python
- Homepage: https://thinkany.ai
- Size: 396 KB
- Stars: 911
- Watchers: 5
- Forks: 121
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- StarryDivineSky - thinkany-ai/rag-search
README
# rag-search
RAG Search API by [thinkany.ai](https://thinkany.ai)
![apitest](./apitest.png)
## quick start
1. put .env file under root dir, set values like below:
```ini
SERPER_API_KEY=OPENAI_BASE_URL=
OPENAI_API_KEY=
OPENAI_MODEL=gpt-3.5-turbo
OPENAI_EMBED_MODEL=text-embedding-ada-002ZILLIZ_URI=
ZILLIZ_TOKEN=
ZILLIZ_DIM=1536
ZILLIZ_COLLECTION=AUTH_API_KEY=
```2. install dependencies
```shell
pip install -r requirements.txt
```3. start FastAPI server
```shell
uvicorn main:app --reload --port 8069
```4. make api request
```txt
@baseUri=http://127.0.0.1:8069
@apiKey=xxx### ping
GET {{baseUri}}/### rag search
POST {{baseUri}}/rag-search
Content-Type: application/json
Authorization: Bearer {{apiKey}}{
"query": "ThinkAny.AI",
"search_n": 10,
"search_provider": "google",
"is_reranking": true,
"is_detail": true,
"detail_min_score": 0.7,
"detail_top_k": 3,
"is_filter": true,
"filter_min_score": 0.8,
"filter_top_k": 6
}
```