MCP.so
Sign In

Installation and Setup Guide

@ricardoborges

About Installation and Setup Guide

LLM chat app for integration tests using llama-stack-client, llama, Ollama, MCP, Tools

Basic information

Category

AI & Agents

Runtime

python

Transports

stdio

Publisher

ricardoborges

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "chatlab": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Installation and Setup Guide?

This document provides step-by-step instructions for setting up the development environment and running the ChatLab application. It uses Ollama or Together.ai for LLM inference and LLama-Stack to manage the inference environment.

How to use Installation and Setup Guide?

Follow the installation steps sequentially: install Ollama or obtain a Together.ai API key, set up LLama-Stack using uv and a virtual environment, clone the repository, install dependencies via uv pip install -r myproject.toml, set environment variables (TAVILY_SEARCH_API_KEY, TOGETHER_API_KEY or DEFAULT_STACK="Ollama"), then run gradio main.py.

Key features of Installation and Setup Guide

  • Step-by-step guide for Ollama and Together.ai setup
  • Uses LLama-Stack to manage inference environments
  • Gradio-based web application interface
  • Supports local and cloud inference models

Use cases of Installation and Setup Guide

  • Setting up a local LLM environment with Ollama
  • Configuring cloud inference via Together.ai API
  • Running the ChatLab application with Gradio UI

FAQ from Installation and Setup Guide

What prerequisites are needed?

Ollama must be installed (unless using Together.ai API) and the virtual environment must be activated correctly.

What dependencies are required?

Ollama or Together.ai API key, LLama-Stack, Python packages as listed in myproject.toml, and a Tavily search API key for search functionality.

Where does data live?

API keys are stored in a .env file (TAVILY_SEARCH_API_KEY, TOGETHER_API_KEY). Model inference runs either locally (Ollama) or on Together.ai servers.

What are known limitations?

The guide does not mention any specific limits; troubleshooting covers checking services and dependencies.

What transports or authentication are used?

No transports are mentioned. Authentication uses API keys for Together.ai and Tavily; local Ollama requires no external auth.

Comments

More AI & Agents MCP servers