Building and querying knowledge graphs from unstructured sources.
Build a pipeline that turns YouTube podcasts into a knowledge graph: extract speakers, statements, and entities with an LLM, then dedupe them with embeddings.
CocoIndex updates: production-ready resilience, a structured error system, expanded integrations, and always-fresh context for agents.
Build a self-updating Neo4j knowledge graph from meeting notes with CocoIndex v1: LLM-extracted decisions, tasks, and owners, with embedding-based dedupe.
CocoIndex updates: in-process setup/drop API, EmbedText building block, SplitRecursively improvements, union/NumPy types, and the Kuzu graph target.
Build a real-time knowledge graph with Kuzu as a native CocoIndex target: incremental updates, high-performance graph queries.
An LLM extracts each product's taxonomy and complements; CocoIndex turns the labels into a Neo4j knowledge graph that answers 'bought this, also need…'.
CocoIndex updates: knowledge graph support, Qdrant and Supabase targets, KTable and LTable data types, additional LLM providers, and more.
Turn a folder of Markdown docs into a Neo4j knowledge graph: an LLM extracts subject-predicate-object triples, and CocoIndex keeps the graph in sync as the docs change.
CocoIndex is a data indexing platform for AI: ingestion, chunking, embedding, and pipeline management for RAG, semantic search, and knowledge graphs.