Skip to main content
Glama

RAG MCP Server

by NSANTRA
Config.py665 B
import os from dotenv import load_dotenv from langchain_huggingface import HuggingFaceEmbeddings from langchain_community.cross_encoders import HuggingFaceCrossEncoder load_dotenv() DEVICE = os.getenv("DEVICE") DOCUMENT_DIR = os.getenv("DOCUMENT_DIR") os.makedirs(DOCUMENT_DIR, exist_ok = True) CHROMA_DB_PERSIST_DIR = os.getenv("CHROMA_DB_PERSIST_DIR") os.makedirs(CHROMA_DB_PERSIST_DIR, exist_ok = True) EMBEDDING_FUNCTION = HuggingFaceEmbeddings( model_name = os.getenv("EMBEDDING_MODEL"), model_kwargs = {"device": DEVICE} ) RERANKER = HuggingFaceCrossEncoder( model_name = os.getenv("RERANKER_MODEL"), model_kwargs = {"device": DEVICE} )

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/NSANTRA/RAG-MCP-Server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server