Mcp_agent_streamlit_rag

Mcp_agent_streamlit_rag

By saqadri GitHub

-

Overview

what is Mcp_agent_streamlit_rag?

Mcp_agent_streamlit_rag is a project that allows users to run a Streamlit application for interacting with MCP servers and QDrant for retrieval-augmented generation (RAG).

how to use Mcp_agent_streamlit_rag?

To use the project, follow these steps:

  1. Copy the example secrets file and update it with your OpenAI API key.
  2. Use the command uv sync to synchronize.
  3. Run the Streamlit application with uv run streamlit run main.py. For QDrant, additional steps include pulling the QDrant Docker image and running it with specific parameters.

key features of Mcp_agent_streamlit_rag?

  • Integration with MCP servers for data fetching and finding.
  • Support for QDrant to enhance retrieval-augmented generation capabilities.
  • Streamlit interface for easy interaction and visualization.

use cases of Mcp_agent_streamlit_rag?

  1. Building applications that require real-time data fetching from MCP servers.
  2. Enhancing machine learning models with retrieval-augmented generation using QDrant.
  3. Creating interactive data applications using Streamlit.

FAQ from Mcp_agent_streamlit_rag?

  • What is required to run this project?

You need an OpenAI API key and Docker installed for QDrant.

  • Is there a graphical interface?

Yes, the project uses Streamlit to provide a user-friendly interface.

  • Can I use this project for production?

It is recommended to test thoroughly before deploying in a production environment.

Content

Run instructions:

For using fetch or finder MCP servers:

  1. cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml --> then update with your API key (openai api key is enough)
  2. uv sync
  3. uv run streamlit run main.py

For using QDrant for RAG:

  1. Uncomment line 63-70 in main.py, and comment out the current instruction and server_names
  2. docker pull qdrant/qdrant
  3. docker run -p 6333:6333 -v $(pwd)/qdrant_storage:/qdrant/storage qdrant/qdrant
  4. uv run streamlit run main.py
No tools information available.
No content found.