Skip to content

ndjordjevic/pinrag

v0.2.0 Breaking

This release includes breaking changes for platform teams planning a safe upgrade.

Published 2mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

chromadb cursor discord github-repos langchain mcp
+8 more
mcp-server model-context-protocol pdf pypi python llm vscode youtube

Summary

AI summary

Added optional per-document tagging and filtering by document ID, page range, or tag.

Full changelog

v0.2.0 — Phase 2: Enhanced Features

Document management, better metadata, improved retrieval, and a modernized RAG chain.

Document tag

  • Per-document tag — Optional tag at indexing time (e.g. tag: "AMIGA").
  • Persistence — Tag stored on all chunks for filtering.
  • Exposure — Tag shown in list_pdfs document_details.

Metadata filtering

  • Filter by documentdocument_id on query_index, run_rag, query_pdf.
  • Filter by page rangepage_min, page_max (single page: e.g. page_min=64, page_max=64).
  • Filter by tagtag parameter (e.g. search only AMIGA-tagged docs).

RAG chain

  • Plain Pythonrun_rag() with @traceable; LCEL removed.

PDF & metadata

  • Batch loadingadd_pdfs MCP tool; partial success/failure reported per file.
  • Chunk metadata — Character offsets (start_index) on chunks; section/heading labels.
  • Document stats — Upload timestamp, doc size (pages, bytes, total chunks) in list_pdfs.

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track ndjordjevic/pinrag

Get notified when new releases ship.

Sign up free

About ndjordjevic/pinrag

RAG for PDFs, YouTube, GitHub repos, Discord exports; index documents and query with citations.

All releases →

Beta — feedback welcome: [email protected]