ai-science-vision-rag

SKILLWorkflowcommunity
v0.0.0Pavel-KravchenkoUnknownUpdated 1mo agoSource →

ColPali-style Vision RAG: embed rendered PDF pages, retrieve via ColBERT MaxSim, feed top-k pages to Qwen2-VL, no OCR. Use for PDF/document QA over figures and tables, multimodal retrieval, or Recall@k/MRR eval.

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
4Repo stars
1Clients
1Formats
1mo agoLast update
Skill
AuthorPavel-Kravchenko
Version0.0.0
LicenseUnknown
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

ColPali-style Vision RAG: embed rendered PDF pages, retrieve via ColBERT MaxSim, feed top-k pages to Qwen2-VL, no OCR. Use for PDF/document QA over figures and tables, multimodal retrieval, or Recall@k/MRR eval.

Keywords
skillclaude