Ingest PDFs into a RAGFlow dataset with chunking and metadata enrichment.
npx skills add https://github.com/hepai-lab/drsai --skill ragflow-knowledge
Please help me install this Agent Skill. Skill: ragflow-knowledge Source: https://github.com/hepai-lab/drsai/tree/main/agent_skills/skills/ragflow-knowledge Command: npx skills add https://github.com/hepai-lab/drsai --skill ragflow-knowledge
PDFs and long documents are hard to organize and retrieve across personal libraries. This skill provides a structured workflow to ingest PDFs, upload them to a RAGFlow vector knowledge base, and enable efficient retrieval, summarization, and cross-document search.
Upload PDFs to your RAGFlow dataset and run a retrieval workflow to search across your documents.
High-intent search queries and answers about installing and using this skill.
To search across multiple PDF documents, this skill ingests your PDFs into a RAGFlow vector knowledge base, applying chunking and metadata enrichment to enable precise, cross-document retrieval of specific topics.
Building a searchable knowledge base from PDFs involves uploading them to a RAGFlow dataset, where the documents are chunked, enriched with metadata, and indexed for efficient vector search and cross-language retrieval.
Yes, RAGFlow supports cross-language content retrieval and synthesis, allowing you to query your PDF knowledge base and retrieve relevant chunks across documents in multiple languages using its rerank capabilities.
Chunk-level retrieval works by dividing ingested PDFs into smaller segments enriched with metadata, enabling the RAGFlow vector knowledge base to return precise document sections with cross-referenced markdown mappings.
Yes, you must upload PDFs to a RAGFlow dataset first. The skill requires this ingestion step to perform chunking, metadata enrichment, and indexing before vector search can be executed.
Metadata enrichment and chunking are required to structure long PDFs into searchable segments, allowing the RAGFlow vector knowledge base to perform accurate index-based retrieval rather than scanning entire documents.
elasticdotventuresAutomate loading of per-project environment variables via direnv and dotenv with Rust validation.
bettercallfanOrganize and summarize legal documents into structured briefings and risk notes.
Himanshu040604Developes RAG systems integrating vector databases and advanced retrieval strategies for LLM applications.
rukikotooQuery the econometrics RAG knowledge base to retrieve relevant document chunks.
