Skip to main content
Glama
deenesjakoruzh
Bisma474

RAG Config Generator MCP

by Bisma474
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

RAG Config Generator MCP

Un servidor MCP (Model Context Protocol) que genera configuraciones de pipeline RAG (Retrieval-Augmented Generation) a partir de descripciones en lenguaje natural.

Demo en vivo

Related MCP server: Pipelex MCP Server

Características

  • Generar configuración completa: Describe tu caso de uso de RAG en lenguaje natural

  • Estrategia de chunking: Obtén recomendaciones de chunking según el tipo de documento

  • Embeddings: Obtén recomendaciones de modelos de embedding según el caso de uso y el presupuesto

  • Vector Store: Obtén recomendaciones de almacenes de vectores según el tamaño de los datos y la latencia

Endpoints de la API

Endpoint

Descripción

GET /

Información del servidor

GET /generate-rag-config?description=...

Generar configuración RAG completa

GET /suggest-chunking?doc_type=...&doc_size=...

Recomendaciones de chunking

GET /suggest-embeddings?use_case=...&budget=...

Recomendaciones de embeddings

GET /suggest-vector-store?data_size=...&latency=...

Recomendaciones de almacén de vectores

Instalación

pip install -r requirements.txt

Uso

Ejecutar la interfaz de Gradio

python app.py

Se abre en http://localhost:7860

Ejecutar el servidor MCP

python server.py

El servidor MCP estará disponible en http://localhost:8000/mcp

Estructura del proyecto

mcp/
├── server.py           # FastAPI + MCP server
├── rag_configs.py      # RAG config templates and logic
├── app.py              # Gradio UI
├── api/
│   └── index.py        # Vercel serverless function
├── requirements.txt    # Python dependencies
├── vercel.json         # Vercel configuration
└── README.md           # Documentation

Stack tecnológico

  • Backend: Python, FastAPI, FastAPI-MCP

  • Frontend: Gradio, HTML/CSS/JS

  • Deployment: Vercel (API), Hugging Face Spaces (UI)

Licencia

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • IndexFoundry MCP

    Mnehmos
    A
    license
    Not graded
    quality
    B
    maintenance
    Creates deterministic, auditable vector databases from any content source with deployable RAG applications. Supports multiple embedding providers and vector databases with fine-grained pipeline control or project-based workflows.
    9 npm
    6
    Academic Free v1.1

  • RAG Factory

    Zyxac24
    A
    license
    Not graded
    quality
    C
    maintenance
    Automated RAG pipeline optimization and serving. It interviews users, builds and evaluates candidate configurations on their data, and registers the best ones as a fleet queryable via MCP.
    MIT