Loading...
Loading...
Found 6 Skills
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
Use when the user wants embeddings, vector indexing, retrieval, or retrieval-backed answers, including embedding-agent setup, Chroma-backed collections, collection add/query, and KB-to-answer flows.
Use when reranking search candidates is needed with Alibaba Cloud Model Studio rerank models, including hybrid retrieval, top-k refinement, and multilingual relevance sorting.
Use OpenSearch vector search edition via the Python SDK (ha3engine) to push documents and run HA/SQL searches. Ideal for RAG and vector retrieval pipelines in Claude Code/Codex.
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
Use the Polygres Python SDK to write individual standard-project application records and build retrieval on standard or synchronized projects with Polygres AI Context, graph, text, hybrid, and existing vector queries; manage supported pgContext collections, points, and durable operations; configure safe Runtime API clients; paginate typed results; and handle SDK errors. Use for Python backend code calling a project's Runtime API. Do not use for sync control-plane administration, bulk imports, migrations, or interactive CLI workflows.