docmind-ai-llm
DocMind AI is a powerful, open-source Streamlit application leveraging LlamaIndex, LangGraph, and local Large Language Models (LLMs) via Ollama, LMStudio, llama
What is docmind-ai-llm?
DocMind AI is a powerful, open-source Streamlit application leveraging LlamaIndex, LangGraph, and local Large Language Models (LLMs) via Ollama, LMStudio, llama.cpp, or vLLM for advanced document analysis. Analyze, summarize, and extract insights from a wide array of file formats, securely and privately, all offline.
Overview of docmind-ai-llm
What it is
DocMind AI is an open-source Streamlit application that uses LlamaIndex, LangGraph, and local Large Language Models (LLMs) via Ollama, LMStudio, llama.cpp, or vLLM for advanced document analysis. It allows users to analyze, summarize, and extract insights from various file formats securely and privately, all offline.
Key features
- Privacy-focused, local-first: remote LLM endpoints are blocked by default and must be explicitly enabled.
- Multi-format parsing: supports PDFs, common office formats, HTML, and explicit text formats (.txt, .md, .markdown, .rst).
- Hybrid retrieval with routing: RouterQueryEngine with semantic_search, hybrid_search, keyword_search, multimodal_search, and knowledge_graph tools.
- Multi-agent coordination: LangGraph supervisor orchestrates four agents (planner, retrieval, synthesis, validation).
- Offline-first design: designed to run locally once models are present; remote endpoints must be explicitly enabled.
- GPU acceleration: optional NVIDIA profile accelerates PyTorch-based dense/image embeddings and reranking.
Use cases
- Analyze and summarize documents locally without sending data to external servers.
- Extract insights from PDFs, office documents, and HTML files.
- Perform secure, private document analysis in environments with strict data residency requirements.
- Use offline when network access is limited or unavailable.
Getting started
pip install docmind-ai-llm streamlit run src/Home.py For Docker deployment, see the repository README.
License and pricing
This project is licensed under the MIT License and is open source.
Based on the project's public README and repository metadata.