mcpField
I
Installation and Setup Guide

Installation and Setup Guide

Local
github.com/ricardoborgesAI & Agents3Updated 77w ago
Repository

About Installation and Setup Guide

A Gradio LLM chat application for developers setting up a chat interface and integration tests. It can be configured with Ollama or Together.ai and uses Llama-Stack for its inference environment.

Key features

  1. 01Gradio chat interface
  2. 02Ollama or Together.ai support
  3. 03Inference setup with Llama-Stack
  4. 04Tavily Search API key configuration

Use cases

  1. 01Running the chat app with local Ollama
  2. 02Using Together.ai API for model inference
#mcp#chat-application#gradio#llm#ollama#llama-stack#mcp-server#mcp-client

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Installation and Setup Guide

This document provides step-by-step instructions for setting up the development environment and running the application.

Screenshot

screenshot

Prerequisites

Before starting, ensure that you have all the necessary tools installed on your system.

Installation Steps

1. Installing and Running Ollama (skip if you will use Together.ai API)

Ollama is required to provide model inference capabilities.

  1. Download and install Ollama from https://ollama.com/
  2. Start the Ollama service with the command: 
    ollama serve

    ollama pull llama3.2:3b
2. Setting Up LLama-Stack

LLama-Stack will be used to manage our inference environment.

  1. Install the uv package manager
  2. Set up a virtual environment (venv)
  3. Run the following command inside the virtual environment: 
    INFERENCE_MODEL=llama3.2:3b llama stack build --template ollama --image-type venv --run
    or 
    INFERENCE_MODEL=meta-llama/Llama-3.3-70B-Instruct llama stack build --template together --image-type venv --run
3. Project Setup

Clone this repository and install the necessary dependencies:

  1. Clone the repository:

    git clone [https://github.com/ricardoborges/chatlab.git]
cd [chatlab]

  2. Create a virtual environment and install dependencies:

    uv venv
uv pip install -r myproject.toml
4. Running the Application

Create togetherAI account if you won't start Ollama local service. So, you would first get an API key from Together if you dont have one already.

How to get your API key: https://docs.google.com/document/d/1Vg998IjRW_uujAPnHdQ9jQWvtmkZFt74FldW2MblxPY/edit?tab=t.0

You will need this env variables in your .env file:

TAVILY_SEARCH_API_KEY= TOGETHER_API_KEY=

Or just ignore and set DEFAULT_STACK="Ollama" in main.py (if you will run local Ollama service)

Start the Gradio application with the following command:

gradio main.py

After running this command, the application interface will be available in your browser.

Troubleshooting

If you encounter any issues during installation, check:

  • That the Ollama service is running
  • That the virtual environment was activated correctly
  • That all dependencies were successfully installed

Additional Resources

For more information about LLama-Stack, refer to the official documentation.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.