MCP ExplorerExplorer

Minima

@dmayborodaon 13 days ago
738 MPLv2
FreeCommunity
Knowledge Base
#ChatGPT#Integration#Local#Open Source
MCP server for RAG on local files

Overview

What is Minima

Minima is an open-source Retrieval-Augmented Generation (RAG) platform designed to operate on-premises using containers. It allows for integration with ChatGPT and Anthropic Claude while also providing the capability to operate entirely locally without external dependencies. This ensures that sensitive data remains secure and under user control.

Use cases

Minima can be utilized in various scenarios, including fully on-premises operations, querying local documents through a custom GPT interface on ChatGPT, and accessing local document queries via the Anthropic Claude app. It is particularly useful for organizations needing secure handling of sensitive documents and information.

How to use

To set up Minima, users must create a .env file with specific environment variables, including paths and model IDs. Depending on the desired mode of operation, users execute different Docker commands to launch the service. For local installations, users can also launch an Electron app to interact with Minima’s capabilities.

Key features

Minima supports multiple modes such as fully isolated installations, custom GPT integrations, and Anthropic Claude functionality. It offers a range of configuration options for embedding models, rerankers, and local file paths, enabling users to tailor the solution to their needs.

Where to use

Minima is suitable for deployment in cloud environments or local systems where data privacy is paramount. It can be used in various industries that require document retrieval and query capabilities, such as legal, academic, or corporate settings.

Content

MNMA Logo

MseeP.ai Security Assessment Badge

Minima is an open source RAG on-premises containers, with ability to integrate with ChatGPT and MCP.
Minima can also be used as a fully local RAG.

Minima currently supports three modes:

  1. Isolated installation – Operate fully on-premises with containers, free from external dependencies such as ChatGPT or Claude. All neural networks (LLM, reranker, embedding) run on your cloud or PC, ensuring your data remains secure.

  2. Custom GPT – Query your local documents using ChatGPT app or web with custom GPTs. The indexer running on your cloud or local PC, while the primary LLM remains ChatGPT.

  3. Anthropic Claude – Use Anthropic Claude app to query your local documents. The indexer operates on your local PC, while Anthropic Claude serves as the primary LLM.

Running as Containers

  1. Create a .env file in the project’s root directory (where you’ll find env.sample). Place .env in the same folder and copy all environment variables from env.sample to .env.

  2. Ensure your .env file includes the following variables:

  • LOCAL_FILES_PATH
  • EMBEDDING_MODEL_ID
  • EMBEDDING_SIZE
  • OLLAMA_MODEL
  • RERANKER_MODEL
  • USER_ID
    • - required for ChatGPT integration, just use your email
  • PASSWORD
    • - required for ChatGPT integration, just use any password

  1. For fully local installation use: docker compose -f docker-compose-ollama.yml --env-file .env up --build.

  2. For ChatGPT enabled installation use: docker compose -f docker-compose-chatgpt.yml --env-file .env up --build.

  3. For MCP integration (Anthropic Desktop app usage): docker compose -f docker-compose-mcp.yml --env-file .env up --build.

  4. In case of ChatGPT enabled installation copy OTP from terminal where you launched docker and use Minima GPT

  5. If you use Anthropic Claude, just add folliwing to /Library/Application\ Support/Claude/claude_desktop_config.json

{
    "mcpServers": {
      "minima": {
        "command": "uv",
        "args": [
          "--directory",
          "/path_to_cloned_minima_project/mcp-server",
          "run",
          "minima"
        ]
      }
    }
  }

  1. To use fully local installation go to cd electron, then run npm install and npm start which will launch Minima electron app.

  2. Ask anything, and you’ll get answers based on local files in {LOCAL_FILES_PATH} folder.

Variables Explained

LOCAL_FILES_PATH: Specify the root folder for indexing (on your cloud or local pc). Indexing is a recursive process, meaning all documents within subfolders of this root folder will also be indexed. Supported file types: .pdf, .xls, .docx, .txt, .md, .csv.

EMBEDDING_MODEL_ID: Specify the embedding model to use. Currently, only Sentence Transformer models are supported. Testing has been done with sentence-transformers/all-mpnet-base-v2, but other Sentence Transformer models can be used.

EMBEDDING_SIZE: Define the embedding dimension provided by the model, which is needed to configure Qdrant vector storage. Ensure this value matches the actual embedding size of the specified EMBEDDING_MODEL_ID.

OLLAMA_MODEL: Set up the Ollama model, use an ID available on the Ollama site. Please, use LLM model here, not an embedding.

RERANKER_MODEL: Specify the reranker model. Currently, we have tested with BAAI rerankers. You can explore all available rerankers using this link.

USER_ID: Just use your email here, this is needed to authenticate custom GPT to search in your data.

PASSWORD: Put any password here, this is used to create a firebase account for the email specified above.

Examples

Example of .env file for on-premises/local usage:

LOCAL_FILES_PATH=/Users/davidmayboroda/Downloads/PDFs/
EMBEDDING_MODEL_ID=sentence-transformers/all-mpnet-base-v2
EMBEDDING_SIZE=768
OLLAMA_MODEL=qwen2:0.5b # must be LLM model id from Ollama models page
RERANKER_MODEL=BAAI/bge-reranker-base # please, choose any BAAI reranker model

To use a chat ui, please navigate to http://localhost:3000

Example of .env file for Claude app:

LOCAL_FILES_PATH=/Users/davidmayboroda/Downloads/PDFs/
EMBEDDING_MODEL_ID=sentence-transformers/all-mpnet-base-v2
EMBEDDING_SIZE=768

For the Claude app, please apply the changes to the claude_desktop_config.json file as outlined above.

To use MCP with GitHub Copilot:

  1. Create a .env file in the project’s root directory (where you’ll find env.sample). Place .env in the same folder and copy all environment variables from env.sample to .env.

  2. Ensure your .env file includes the following variables:

    • LOCAL_FILES_PATH
    • EMBEDDING_MODEL_ID
    • EMBEDDING_SIZE

  3. Create or update the .vscode/mcp.json with the following configuration:

{
  "servers": {
    "minima": {
      "type": "stdio",
      "command": "path_to_cloned_minima_project/run_in_copilot.sh",
      "args": [
        "path_to_cloned_minima_project"
      ]
    }
  }
}

Example of .env file for ChatGPT custom GPT usage:

LOCAL_FILES_PATH=/Users/davidmayboroda/Downloads/PDFs/
EMBEDDING_MODEL_ID=sentence-transformers/all-mpnet-base-v2
EMBEDDING_SIZE=768
[email protected] # your real email
PASSWORD=password # you can create here password that you want

Also, you can run minima using run.sh.

Installing via Smithery (MCP usage)

To install Minima for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install minima --client claude

For MCP usage, please be sure that your local machines python is >=3.10 and ‘uv’ installed.

Minima (https://github.com/dmayboroda/minima) is licensed under the Mozilla Public License v2.0 (MPLv2).

Tools

query
Find a context in local files (PDF, CSV, DOCX, MD, TXT)

Comments