Hugging Face's logo

Spaces:
Agents-MCP-Hackathon
/
mcp-rag-workflow
Running

App Files Community
mcp-rag-workflow / README.md
betki's picture
betki
Update README.md
bea97d8 verified
preview code
|
raw
history blame
1.9 kB
metadata
title: MCP-Powered RAG and Research Topic
emoji: 🌍
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 5.32.1
app_file: app.py
pinned: false
license: mit
short_description: MCP-Powered RAG and Research Topic
tag: mcp-server-track

👁 MCP Powered RAG and Research Topic 🌍

I present to you an MCP-powered RAG and Research Topic. The Tools are hosted and executed on Modal Labs

RAG Tool uses the GroundX storage by eyelevel.ai to fetch the knowledge base. The knowledge base is a document that contains information about the SU-35 aircraft, including its features, capabilities, and specifications. Please check this PDF to formulate queries on Sukhoi.

The Research Tool is implemented using a multi-agent workflow using LlamaIndex (ResearchAgent, WriteAgent, and ReviewAgent).
The Agents use Nebius provided LLM.

Available Tools

search_knowledge_base_for_context

  • Description: Searches and retrieves relevant context from a knowledge base based on the user's query.
  • Example Queries:
    • "What are the main features of fuel system of SU-35?"
    • "What is the combat potential of SU-35?"

research_write_review_topic

  • Description: Helps with writing a report with research, writing, and review on any topic.
  • Example Queries:
    • "Write me a report on the history of the internet."
    • "Write me a report on origin of the universe."
    • "Write me a report on the impact of climate change on polar bears."

How to Use

  • Use the MCP RAG Tool tab above to query the knowledge base.
  • Use the Research Tool tab above to write a report on any topic.

Watch the Demo Video here

Link to Demo on Youtube

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference