Table of Contents

• Title and Copyright Information
• Preface
  • Audience
• About Oracle Private AI Services Container
• Install the Private AI Services Container
• Configure the Private AI Services Container
  • Install with HTTP
  • Install with Self-Signed SSL Certificates
• Use the Inference Service
  • Considerations for the Inference Service
    • Private AI Environment Variables
    • Inference Service Model Property
• Use the Vector Embedding Service
  • Configure the Embedding Service
    • Install with HTTP and Default Models
    • Install with HTTP with Models and Advanced Options
    • Install with HTTP/SSL with Models and Advanced Options
    • Use the OpenAI Python SDK Client with HTTP or HTTP/SSL
  • Considerations for the Embedding Service
    • Available Embedding Models
    • Container Input Validation
    • Container Automatic Image Conversion
    • Multi-threaded Scaling
• Use the Private Large Language Model Service
  • Configure the Private Large Language Model Service
  • Considerations for the Private Large Language Model Service
    • Private Large Language Model Service Runtime Engines
    • Models Available to the Private Large Language Model Service
    • Download Models from Hugging Face
    • Guardrails
• Use the Reranking Service
  • Configure a Reranking Model
  • Send a Reranking Request
• Use the Text Classification Service
  • Configure a Text Classification Model
  • Send a Text Classification Request
• Use the Vector Index Service
  • Configure the Vector Index Service
    • Configure the Container
    • Configure the RDBMS
    • Advanced Configuration Options
    • Install with Self-Signed SSL Certificates for the Vector Index Service
  • Considerations for the Vector Index Service
    • Memory Restrictions
    • Deploy Behind a Proxy
• General Considerations for Container Configuration
  • Rate Limiting
  • HTTP Request Input Validation
  • Use API Keys in Clients
  • Support for Multiple API Keys
  • Transport Layer Security
  • Container Log Files
• Private AI Services Container API Reference