AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Graphic Design › NexusRAG
✦ Free & open sourceGraphic Design

NexusRAG

Parses complex documents and images into a hybrid vector search and LightRAG knowledge graph with citations.

Hybrid RAG pipeline with knowledge graphs and citations

Combines vector search, LightRAG entity mapping, and vision LLMs to answer questions from visual documents.

Free forever · open source · MIT
✓ Needs IT✓ Browser-based✓ Real-time collaboration
6
ZEKAI
Advanced hybrid graph RAG.
Free & open source · Graphic Design
Ease of setup4
Usefulness8
Maintenance5.5
Community6.5
★ 530
GITHUB
Apr 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

NexusRAG is a retrieval-augmented generation engine that processes text, tables, and images from complex documents into a structured vector and graph database. It targets developers and AI engineering teams who need grounded answers backed by precise document citations. You can deploy it locally using Ollama and sentence-transformers or connect it to external providers like Gemini.

Runs on
Web
Hosting
Self-host
Languages
Python
License
MIT

What it is

NexusRAG extracts layout structures, tables, and images using Docling or Marker, then generates visual descriptions via multimodal LLMs before chunking. It runs a three-way retrieval strategy across ChromaDB vector search, LightRAG entity traversal, and cross-encoder joint reranking. The React interface displays inline 4-character citations, document page previews, and force-directed knowledge graph network visualizers.

Who it's for

It suits software engineers, data scientists, and technical researchers building contextual search tools over complex PDFs, reports, and manuals. It is not intended for non-technical end users looking for a single-click desktop PDF reader. If you lack dedicated GPU hardware or API budget for vision models, document ingestion will be significantly slower.

Key features

Deep Layout Document Parsing

Preserves heading hierarchies, page boundaries, and section relationships using configurable Docling or Marker parsing engines.

Visual Document Intelligence

Appends vision LLM captions for images and structured markdown table summaries directly into chunk embeddings.

Three-Way Hybrid Retrieval

Executes ChromaDB vector over-fetching, LightRAG entity lookup, and cross-encoder reranking in parallel.

Precise Source Citations

Generates four-character inline citation tags that link directly to page numbers and original heading paths.

Force-Directed Graph Interface

Renders force-directed entity and relationship network graphs in the browser without requiring external graph database servers.

How to start

Up and running in 3 steps

1
Configure backend environment variables in `.env` to select your document parser and LLM provider endpoints.
2
Start the FastAPI server and ChromaDB instance using Docker Compose.
3
Launch the React frontend development server to upload files, inspect knowledge graphs, and test chat queries.
Real talk

Our honest verdict

What's great

  • Extracts and captions embedded images and tables for vector search instead of discarding visual elements.
  • Uses file-based NetworkX and NanoVectorDB for graph storage to avoid complex database server setups.
  • Allows runtime switching between Docling for hybrid chunking and Marker for formula-heavy documents.
  • Applies cross-encoder reranking to score query-document pairs jointly rather than relying solely on cosine distance.

Where it falls short

  • Demands heavy GPU resources, with Docling formula extraction taking up to 20 GB of VRAM.
  • Requires managing multiple services, including a Python FastAPI backend and a React frontend application.
  • Lacks built-in user authentication, multi-tenancy management, or access control mechanisms out of the box.
Cost

Pricing & license

NexusRAG is free and open-source software under the MIT license. The repository author does not offer a paid managed cloud platform. Your operational costs depend entirely on self-hosted GPU infrastructure or commercial model API usage such as Gemini.

Paid work

Open remote AI-training roles

877 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives
Get more

Use it, or have us set it up

📄 Free PDF: NexusRAG for Graphic Design
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure NexusRAG for you — and train your team.
Get it done for you ↗
Questions

FAQ

Can NexusRAG run entirely offline?

Yes, you can configure NexusRAG to use local Ollama models and sentence-transformers, running parsing, embedding, and chat locally.

Which file formats can NexusRAG parse?

Depending on the active parser configuration, it accepts PDF, DOCX, PPTX, XLSX, HTML, EPUB, and TXT files.

How are images indexed for text queries?

Vision models generate text captions for extracted images during upload, which are embedded alongside the text on that page.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Graphic Design — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google