ai-science-vision-rag

SKILLWorkflowcommunauté
v0.0.0Pavel-KravchenkoUnknownMis à jour il y a 1 moisSource →

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 →
4Étoiles du dépôt
1Clients
1Formats
il y a 1 moisDernière mise à jour
Skill
AuteurPavel-Kravchenko
Version0.0.0
LicenceUnknown
CatégorieWorkflow
Formatsskill.md
PromptNon publié
Compatibilité
Claude✓ Pris en charge
Cursor—
Copilot—
ChatGPT—
Gemini—
À propos

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.

Mots-clés
skillclaude