Extract text and metadata from PDFs and index them into the nx store.
npx skills add https://github.com/Hellblazer/nexus --skill pdf-processing-hellblazer
Please help me install this Agent Skill. Skill: pdf-processing Source: https://github.com/Hellblazer/nexus/tree/main/nx/skills/pdf-processing Command: npx skills add https://github.com/Hellblazer/nexus --skill pdf-processing-hellblazer
PDFs are often scattered and not easily searchable; indexing them into the nx store enables semantic search across documents and knowledge bases.
Index PDFs into the nx store by invoking the pdf-processing skill and pointing it at your PDF assets to add them to the nx store.
High-intent search queries and answers about installing and using this skill.
To index PDFs for semantic search, the skill reads your PDF files, extracts text and metadata, chunks the content for embeddings, and stores the results in the nx store for fast retrieval.
The best way to extract text and metadata from technical manuals is using layout-preserving text extraction, which captures the title, author, and date while preparing the content for embedding and indexing.
Yes, you can import research papers into the nx store. The skill ingests the PDFs, extracts text and metadata, and indexes the chunked content to build a navigable and searchable knowledge base.
Yes, PDF indexing automatically chunks the extracted text content before creating embeddings. This chunking process ensures the content is properly formatted for fast retrieval in the nx store.
The metadata does not specify explicit limitations for layout-preserving text extraction, but successful indexing depends on the PDF having selectable text rather than scanned images for accurate extraction and chunking.
gracefullightConvert PDF documents into structured Markdown for LLM and RAG use.
tocadaoncamodExtract insights, summaries, and cited answers from PDF documents via RAG.
christian-bromannConvert text into embeddings and index them into vector stores for semantic search.
spoonboboConvert PDFs, DOCX, and images to text, markdown, or searchable PDFs.
