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

Search code, repositories, users, issues, pull requests...

submited by

Style Pass

2024-12-02 21:00:06

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

Minima supports 3 modes right now. You can use fully local (minimal) installation, you can use Custom GPT to query your local documents via ChatGPT and use an Anthropic Claude for for querying local files.

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.

LOCAL_FILES_PATH: Specify the root folder for indexing. 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.