Hybrid Search RAG - A Model Context Protocol (MCP) server for RAG-based document search
Project description
RAG-based MCP Server
English
This package provides an MCP (Model Context Protocol) server that uses a Retrieval Augmented Generation (RAG) approach. It allows you to specify a folder containing PDF files for augmentation, and leverages an OpenAI API key to perform hybrid search.
Installation
Install the package from PyPI using UV or pip:
uv pip install mcp-hybrid-search
or
pip install mcp-hybrid-search
Configuration
To run your project in the Claude app, add the following entry to your claude_desktop_config.json:
{
"rag-mcp": {
"command": "uvx",
"args": [
"mcp-hybrid-search",
"path/to/your/allowed/folder"
],
"env": {
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY"
}
}
}
- Replace
path/to/your/allowed/folderwith the actual path where you want to store and access your data. - In that folder, create a subfolder named
dataand place any PDF files you want to use for augmentation in thisdatafolder.
Usage
- Install and configure the server as described above.
- Start or restart your MCP setup or application to enable the RAG-based MCP server.
- The server will use the PDF files within the
datafolder to generate context and augment your prompts.
License
MIT
한국어
이 패키지는 RAG(Retrieval Augmented Generation) 방식을 사용하는 MCP(Model Context Protocol) 서버를 제공합니다. PDF 파일을 증강 자료로 활용할 수 있도록 설정된 폴더를 지정하고, OpenAI API 키를 이용하여 하이브리드 검색을 수행합니다.
설치 방법
UV 또는 pip를 이용하여 PyPI에서 패키지를 설치합니다:
uv pip install mcp-hybrid-search
또는
pip install mcp-hybrid-search
설정 방법
Claude 앱에서 프로젝트를 실행하기 위해 claude_desktop_config.json에 다음과 같이 설정을 추가하세요:
{
"rag-mcp": {
"command": "uvx",
"args": [
"mcp-hybrid-search",
"접근을 허용할 폴더 경로"
],
"env": {
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY"
}
}
}
접근을 허용할 폴더 경로부분을 실제 PDF 파일을 저장할 경로로 바꾸세요.- 해당 폴더 안에
data라는 이름의 하위 폴더를 만들고, 여기에 증강 자료로 사용할 PDF 파일을 넣으세요.
사용 방법
- 위 설치 및 설정 과정을 완료합니다.
- MCP 설정을 실행하거나 애플리케이션을 재시작하여 RAG 기반 MCP 서버를 활성화하세요.
data폴더 내 PDF 파일을 이용하여 메시지에 대한 맥락을 생성하고 증강된 응답을 받아볼 수 있습니다.
라이센스
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mcp_hybrid_search-1.0.7.tar.gz.
File metadata
- Download URL: mcp_hybrid_search-1.0.7.tar.gz
- Upload date:
- Size: 9.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9cc8ad318c701f220ac9555932ef1baef5248771efaf3543abf0cccb09bb489c
|
|
| MD5 |
4b5623c2f7bcf91fb7f32c8bbf20a538
|
|
| BLAKE2b-256 |
db0e600b728a84bd8fdf25a47946dbf411bd4442383f9e32af4d2825fcc83b10
|
File details
Details for the file mcp_hybrid_search-1.0.7-py3-none-any.whl.
File metadata
- Download URL: mcp_hybrid_search-1.0.7-py3-none-any.whl
- Upload date:
- Size: 9.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ec1692c67978c115fe78a40f47a490db0ee5226dba9849122ff9c0d7defa64bc
|
|
| MD5 |
e9df2f0bfd1ee769131e8088d8c0e5b2
|
|
| BLAKE2b-256 |
f4ec40bc0d9f7d7407e6c61b276028b3f05e93fd004ac22fce9b9f1124c9375f
|