OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

DocMind AI

DocMind AI is an open-source Python and Streamlit application for ingesting, searching, and analyzing documents with configurable language-model runtimes. It combines LlamaIndex retrieval with LangGraph-supervised analysis and uses Qdrant for vector storage.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

DocMind AI — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use DocMind AI when you want a self-hosted workflow that separates document ingestion from chat and lets you choose a local language-model runtime.

Who it is for

  • People who want to summarize, question, or extract findings from document collections using locally run language models.
  • Developers interested in adapting a Python application built around document parsing, retrieval, and agent coordination.

Documented uses

  • Ingest PDFs, common office and HTML files, and explicit text formats into a document snapshot.
  • Ask questions about ingested documents and request summaries or key findings.
  • Configure a local model runtime and select among supported retrieval tools.
Before you choose

Requirements & limits

The project is open source under the MIT License and is presented as a self-hosted application.

  • The application is built with Python and Streamlit and uses LlamaIndex, LangGraph, and Qdrant.
  • Remote LLM endpoints are blocked by default; allowing remote endpoints requires explicit configuration.
  • The README describes operation as local-first but says the release benchmark does not independently measure zero network egress.
  • Searchable-PDF export requires POSIX and the OCRmyPDF and Tesseract executables; native Windows is unsupported for that feature.
  • NVIDIA acceleration is optional, and vLLM runs as an external OpenAI-compatible server.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install DocMind AI and prepare its model artifacts

Clone the repository, install its locked dependencies, and prefetch the default retrieval and parser artifacts.

Before you start

  • Git
  • uv

Steps

  1. Clone https://github.com/BjornMelin/docmind-ai-llm and change into the repository directory.

  2. Run the command below to install dependencies.

    Documented command
    uv sync --frozen

  3. Run the README's the command below command to prefetch artifacts.

    Documented command
    uv run python tools/models/pull.py --all --cache_dir ./models_cache --parser-defaults --parser-cache-dir ./cache/models

  4. Run the command below to check the parser manifests.

    Documented command
    uv run python scripts/parser_health.py --check

Expected outcome

The repository dependencies are installed and the README's default retrieval and parser artifacts have been prefetched, followed by a parser-manifest check.

Guide limitations

  • This guide covers setup and artifact preparation, not starting the application or completing document analysis.
  • The README's optional searchable-PDF export extra is POSIX-only and requires OCRmyPDF and Tesseract.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
BjornMelin/docmind-ai-llm · Official homepage title · retained in its source language
How we review sourcesSuggest a correction