Back to directory

Oracle VecDB Python SDK

A Python SDK for building vector search, retrieval-augmented generation and AI applications directly on Oracle AI Database, combining semantic similarity with relational and spatial filtering.

Oracle VecDB Python SDK

Oracle VecDB Python SDK lets Python applications store vectors alongside operational data in Oracle AI Database, so semantic similarity search can be combined with relational and spatial filtering without running a separate vector database. It connects to an Oracle AI Database instance through Oracle REST Data Services and supports creating vector tables, upserting data, and querying with integrated embeddings plus metadata filters, for example combining a text query with a genre filter and a result limit.

Sample applications built with the SDK include semantic search combined with geospatial filtering, semantic code search over a codebase, and a retrieval-augmented-generation document chatbot. It requires Python 3.10 or newer, Oracle AI Database 23.26.3 or newer, and Oracle REST Data Services 26.2.2 or newer, and is released under the UPL-1.0 license.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.