The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
-
Updated
Sep 7, 2026 - Python
#
colqwen2
Here are 17 public repositories matching this topic...
The repo provides the code for Qdrant for efficient image indexing and retrieval using models such as ColPali, ColQwen, and VDR-2B-Multi-V1, jina embeddings v4 etc enhancing multimodal search capabilities across various applications.
vlm rag qdrant jinaai qdrant-vector-database llamaindex colpali colqwen2 vdr-2b-multi-v1 jina-embeddings
-
Updated
Jan 2, 2026 - Python
Search your Mac by what a page looks like. ColQwen2 over page images, everything local.
-
Updated
Sep 11, 2026 - Python
Vision-first document RAG for PDF, DOCX, and image QA/extraction with ColQwen2, Qwen2.5-VL, Qdrant, and FastAPI.
document-retrieval rag vector-search document-understanding pdf-extraction document-ai qdrant vision-language-model retrieval-augmented-generation local-ai pdf-qa multimodal-rag colpali qwen2-vl colqwen2 vision-rag qwen2-5-vl document-question-answering multivector-search visual-retrieval
-
Updated
Aug 10, 2026 - Python
Python library for MUVERA multi-vector retrieval via Fixed Dimensional Encodings. ColBERT / ColQwen2 / ColQwen3.5 compatible.
simhash embeddings approximate-nearest-neighbor-search rag colbert approximate-nearest-neighbor late-interaction colqwen2 muvera multi-vector-retrieval
-
Updated
May 25, 2026 - Python
Multimodal RAG that retrieves document pages as images using ColQwen2 late-interaction search, fused with dense and lexical retrieval. Modality-routed generation with page-level citations. Runs on a 4GB laptop GPU.
-
Updated
Sep 13, 2026 - Python
Multimodal RAG with per-query routing to text / visual / hybrid retrieval paths. Vision-LLM answers and regression-gated evals.
docker multimodal rag mlops fastapi vector-search cloud-run qdrant retrieval-augmented-generation openrouter llm-ops llm-evaluation multimodal-rag bge-m3 colqwen2 vision-llm visual-retrieval
-
Updated
Sep 2, 2026 - Python
A high-performance RAG system for PDFs using multi-vector embeddings (ColPali / ColQwen / ColSmol) with vector search in Qdrant, prefetch optimization, and reranking for improved relevance. Designed for speed, accuracy, and scalability, this system is ideal for building intelligent search, document understanding, and QA applications.
-
Updated
Sep 12, 2025 - Python
Healthcare Multimodal RAG system for medical visual question answering and retrieval-augmented reasoning using LLaVA, QLoRA, OpenI chest X-rays, and scalable modular architecture with future ColQwen2, BM25, CLIP, RRF, and Qwen2-VL integration.
nlp computer-vision deep-learning transformers pytorch clip bm25 multimodal-learning rag medical-ai medical-vqa healthcare-ai vision-language-model llava qlora multimodal-rag qwen2-vl colqwen2
-
Updated
May 16, 2026 - Python
Visual RAG system for financial document analysis using ColQwen2.5, Qdrant, Claude Opus/Sonnet
-
Updated
May 28, 2026 - Python
VisRAG playground for finding your perfect embedding + VLM combo. Index PDFs with multimodal models, compare responses side-by-side.
-
Updated
Aug 26, 2025 - Python
Vision RAG over PDF pages: ColQwen2 + Qdrant retrieval, Gemini returns a bounding region that's cropped to show the exact chart slice an answer came from.
gemini rag document-ai qdrant vision-language-model retrieval-augmented-generation llm-evaluation langgraph multimodal-rag colpali colqwen2 pdf-question-answering
-
Updated
Aug 26, 2026 - Python
Sovereign multimodal RAG for German industrial documentation. EU AI Act-aware by design. Built with ColQwen2/ColPali, LangGraph, FastAPI, Next.js, pgvector.
nextjs gdpr rag industrial-ai fastapi ml-engineering llm pgvector ollama langfuse langgraph multimodal-rag eu-ai-act colpali colqwen2 qwen3 sovereign-ai mittelstand
-
Updated
Jun 3, 2026 - Python
Add this topic to your repo
To associate your repository with the colqwen2 topic, visit your repo's landing page and select "manage topics."