ai-science-vision-rag

Name: ai-science-vision-rag
Author: Pavel-Kravchenko

SKILLFlusso di lavorocommunity

v0.0.0Pavel-KravchenkoUnknownAggiornato 1 mesi faFonte →

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 →

4Stelle del repo

1Client

1Formati

1 mesi faUltimo aggiornamento

Skill

AutorePavel-Kravchenko

Versione0.0.0

LicenzaUnknown

CategoriaFlusso di lavoro

Formatiskill.md

PromptNon pubblicato

Compatibilità

Claude✓ Supportato

Cursor—

Copilot—

ChatGPT—

Gemini—

Descrizione

Parole chiave

skillclaude