ndjordjevic/pinrag

v0.7.0 Feature

This release adds 4 notable features for engineering teams evaluating rollout.

Published 2mo MCP Developer Tools

✓ No known CVEs patched

✓ 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

YouTube transcript indexing added via a consolidated add_document_tool.

Full changelog

YouTube transcript indexing, consolidated add_document_tool, document_type metadata and query filter, plus bug fixes and MCP polish.

YouTube indexing — Index YouTube video transcripts via URL or video ID. Auto-detects format, chunks segments, stores document_type metadata.
add_document_tool — Single indexing tool (replaces add_file_tool and add_files_tool). Accepts paths list; supports PDF, Discord, YouTube in one call.
document_type metadata — PDF, Discord, and YouTube chunks now include document_type. Query filter: document_type=pdf|youtube|discord.
Release command — Cursor command for cutting releases (bump, tag, gh release).

Local path vs YouTube ID — Existing local files/dirs named like YouTube IDs (e.g. dQw4w9WgXcQ.pdf) are now indexed as local content, not YouTube.
Transcript None edge case — Fixed crash when fallback transcript fetches return None without raising; now raises RuntimeError with clear message.
Rerank fallback logging — Log warning only once per process when Cohere rerank is requested but unavailable.

Server config resource — MCP resource shows effective config and API key status.
ask_about_documents — Prompt updated with document_type filter.
Cursor commands — git-commit-push, run-mcp-tool, release.

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.

About ndjordjevic/pinrag

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