You're reading an old version of this documentation. If you want up-to-date information, please have a look at v3.0.0.
Contents Menu Expand Light mode Dark mode Auto light/dark mode
IBM Generative AI Python SDK (Tech Preview)
IBM Generative AI Python SDK (Tech Preview)
  • Getting Started
  • V2 Migration Guide
  • Examples
    • Text
      • Stream answer from a model
      • Moderate text data
      • Chat with a model
      • Get embedding vectors for text data
      • Simple text generation
      • Compare a set of hyperparameters
      • Complex text generation example with a progress bar
      • Tokenize text data
    • Models
      • Show information about supported models
    • Tunes
      • Tune a custom model (Prompt Tuning)
    • Prompts
      • Create a custom prompt with variables
    • System Prompts
      • Working with system prompts
    • Files
      • Working with files
    • Users
      • Show information about current user
    • Requests
      • Working with your requests
    • Extra
      • Overriding built-in services
      • Enable/Disable logging for SDK
      • Error Handling
      • Shutdown Handling
      • Text generation with custom concurrency limit and multiple processes
      • Retrieve metadata for given service method
      • Customize underlying API (httpx) Client
      • Vector Databases
        • Chroma DB
          • Create ChromaDB Embedding Function
    • Extensions
      • Transformers (HuggingFace)
        • Run Transformers Agents
      • LangChain
        • Streaming response from LangChain
        • Chat with a model using LangChain
        • Use LangChain generation with a custom template.
        • LangChain SQL Agent
        • Text generation using LangChain
        • LangChain agent
        • LangChain Embeddings
        • Serialize LangChain model to a file
        • QA using native LangChain features
      • LLamaIndex
        • Use a model through LLamaIndex
        • LlamaIndex Embeddings
      • LocalServer
        • Customize behavior of local client
        • Use a local server with a custom model
  • FAQ
  • Changelog

Versions

  • main (unreleased)
  • v3.0.0
  • v2.3.0
  • v2.2.0
  • v2.1.1
  • v2.1.0
  • v2.0.0
Back to top

Text#

The following module contains examples of Text Generation, Tokenization, Moderation, Embeddings and more.

  • Stream answer from a model
  • Moderate text data
  • Chat with a model
  • Get embedding vectors for text data
  • Simple text generation
  • Compare a set of hyperparameters
  • Complex text generation example with a progress bar
  • Tokenize text data
Next
Stream answer from a model
Previous
Examples
Copyright © 2024, IBM Research
Made with Sphinx and @pradyunsg's Furo