cocoindex

CocoIndex is an ultra-performant real-time data transformation framework for AI with incremental processing. This skill enables building indexing flows that extract data from sources, apply transformations (chunking, embedding, LLM extraction), and export to targets (vector databases, graph databases, relational databases). Core capabilities: Key features: For detailed documentation: Search documentation: Use when users request: Ask clarifying questions to understand: Data source: Transformations: Target: Guide user to add CocoIndex with appropriate extras to their project based on their needs: Required dependency: Optional extras (add as needed): What's included: Users can install using their preferred package manager (pip, uv, poetry, etc.) or add to pyproject.toml . For installation details: Check existing environment first: Check if COCOINDEX_DATABASE_URL exists in environment variables For flows requiring LLM APIs (embeddings, extraction): Guide user to create .env file: For more LLM options: Create basic project structure: Follow this structure: Key principles: Common mistakes to avoid: ❌ Wrong: Using local variables for transformations ✅ Correct: Assigning to row fields ❌ Wrong: Creating unnecessary dataclasses to mirror flow fields IMPORTANT: The patterns listed below are common starting points, but you cannot exhaustively enumerate all possible scenarios . When user...