Using PostgreSQL and pgvector as a source or target for CocoIndex.
Rank trending HackerNews topics in Postgres with an incremental CocoIndex v1 pipeline: scrape threads and comments, extract topics with an LLM.
Build a custom CocoIndex source for the HackerNews API: fetch threads and comments in async Python, extract topics with an LLM, keep Postgres in sync.
Production-ready upgrades: durable execution, faster incremental processing over large datasets, GPU isolation, and richer native building blocks.
Use an existing PostgreSQL table as a CocoIndex source: derive fields, embed each row, and store the vectors in Postgres with pgvector, incrementally.
Extract structured data from PDF manuals locally with Ollama and CocoIndex: docling converts PDFs to Markdown, a local LLM fills typed Postgres rows.