BjornMelin / 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.
Why this job: says: llama.cpp; topics: llama-cpp, llamacpp, ollama, local-llm, vllm
What it does
- Privacy-focused, local-first. Remote LLM endpoints are blocked by default; enable explicitly when needed.
- CPU-safe ingestion pipeline. LlamaIndex IngestionPipeline fed by DocMind's local parser service: Docling conversion, pypdfium2 PDF inspection/rasterization, RapidOCR CPU OCR, TokenTextSplitter, and optional spaCy enrichment.
- Multi-format parsing. Docling covers PDFs and common office/HTML formats; only explicit text formats use the direct UTF-8 loader. Binary parser failures stop ingestion instead of decoding source bytes as text.
- Hybrid retrieval with routing. RouterQueryEngine with required
- Qdrant server-side fusion. Query API RRF (default) or DBSF over named vectors text-dense and text-sparse; sparse queries use FastEmbed BM42/BM25 when available.
Get started
git clone https://github.com/BjornMelin/docmind-ai-llm.git
cd docmind-ai-llm You need: One supported LLM backend running locally: Ollama (default), vLLM OpenAI-compatible server, LM Studio, or a llama.cpp server.; Python >=3.12,<3.14; CPython 3.12.13 is the primary CI and container; (Optional) Docker and Docker Compose for containerized deployment.
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 155
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v2.0.1
- Released 3 months ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 39% closed
- 19 still open
- Pull requests
- 102 merged
- 8 waiting
- Releases
- 16
- 16 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Leon-Sander / Local-Multimodal-AI-Chat | 208 | 4 months ago | GPL-3.0 | No downloads |
| llamastash / llamastash | 289 | 6 days ago | MIT | Mac, Windows, Linux |
| maximpri / mlxtop | 148 | 6 days ago | MIT | Mac, Windows, Linux |
More: languages, topics and project record
Languages
- Python 100%
- Dockerfile <1%
- Shell <1%
Topics
- ai-agents
- document-analysis
- hybrid-search
- langchain
- langgraph-supervisor-py
- llama-cpp
- llamacpp
- lmstudio
- local-llm
- multimodal-embeddings
- ollama
- private-ai-agents
Project record
- JobLocal LLMs
- StatusListed
- Commits1,406
- Forks29
- Watching4
- Stars in 28 days0
- CreatedJan 21, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026