Table of Contents
- Title and Copyright Information
- Preface
- What’s New for Oracle AI Vector Search
- Overview
- Get Started
- Generate Vector Embeddings
- About Vector Generation
- Import Pretrained Models in ONNX Format
- Convert Pretrained Models to ONNX Model: End-to-End Instructions for Text Embedding
- Python Classes to Convert Pretrained Models to ONNX Models
- ONNX Pipeline Models: Text Embedding
- ONNX Pipeline Models: Image Embedding
- ONNX Pipeline Models: CLIP Multi-Modal Embedding
- ONNX Pipeline Models: Text Classification
- ONNX Pipeline Models: Reranking Pipeline
- Load Custom Models from The Local Filesystem
- Support For Large ONNX Format Model
- Model Summary
- Import ONNX Models into Oracle AI Database End-to-End Example
- Access Third-Party Models for Vector Generation Leveraging Third-Party REST APIs
- Vector Generation Examples
- Generate Embeddings
- Convert Text String to Embedding Within Oracle AI Database
- Convert Text String to BINARY Embedding Outside Oracle AI Database
- Convert Text String to Embedding Using Public REST Providers
- Convert Text String to Embedding Using the Local REST Provider Ollama
- Convert Image to Embedding Using Public REST Providers
- Generate Multi-modal Embeddings Using CLIP
- Vectorize Relational Tables Using OML Feature Extraction Algorithms
- Perform Chunking With Embedding
- Configure Chunking Parameters
- Generate Embeddings
- Store Vector Embeddings
- Create Vector Indexes and Hybrid Vector Indexes
- Size the Vector Pool
- Manage the Different Categories of Vector Indexes
- In-Memory Neighbor Graph Vector Index
- Neighbor Partition Vector Index
- Partition Maintenance Operations and Vector indexes
- Guidelines for Using Vector Indexes
- Index Accuracy Report
- Vector Index Status, Checkpoint, and Advisor Procedures
- Manage Hybrid Vector Indexes
- Vector Indexes in a Globally Distributed Database
- IVF Indexing on External Iceberg Tables
- Use SQL Functions for Vector Operations
- Query Data With Similarity and Hybrid Searches
- Work with LLM-Powered APIs and Retrieval Augmented Generation
- Supported Clients and Languages
- Vector Diagnostics
- Vector Search PL/SQL Packages
- DBMS_VECTOR
- CREATE_CREDENTIAL
- CREATE_INDEX
- DISABLE_CHECKPOINT
- DROP_CREDENTIAL
- DROP_ONNX_MODEL Procedure
- ENABLE_CHECKPOINT
- GET_INDEX_STATUS
- INDEX_ACCURACY_QUERY
- INDEX_ACCURACY_REPORT
- INDEX_VECTOR_MEMORY_ADVISOR
- INMEMORY_ONNX_MODEL
- LOAD_ONNX_MODEL
- LOAD_ONNX_MODEL_CLOUD
- QUERY
- REBUILD_INDEX
- UTL_TO_RERANK
- UTL_TO_EMBEDDING and UTL_TO_EMBEDDINGS
- UTL_TO_GENERATE_TEXT
- DBMS_VECTOR_CHAIN
- DBMS_HYBRID_VECTOR
- DBMS_VECTOR_ADMIN
- DBMS_VECTOR
- Python Classes to Convert Pretrained Models to ONNX Models (Deprecated)
- Glossary