Models

The Model module is an extension of ModelInference with langchain support, which enables you to get a WatsonxLLM wrapper for watsonx foundation models.

Modules

• ModelInference
  • ModelInference
    • ModelInference.aclose_persistent_connection()
    • ModelInference.agenerate()
    • ModelInference.chat()
    • ModelInference.chat_stream()
    • ModelInference.close_persistent_connection()
    • ModelInference.generate()
    • ModelInference.generate_text()
    • ModelInference.generate_text_stream()
    • ModelInference.get_details()
    • ModelInference.get_identifying_params()
    • ModelInference.set_api_client()
    • ModelInference.to_langchain()
    • ModelInference.tokenize()
  • Enums
    • TextModels
• Model
  • Model
    • Model.chat()
    • Model.chat_stream()
    • Model.generate()
    • Model.generate_text()
    • Model.generate_text_stream()
    • Model.get_details()
    • Model.to_langchain()
    • Model.tokenize()
  • Enums
    • GenTextParamsMetaNames
    • GenTextReturnOptMetaNames
    • DecodingMethods
      • DecodingMethods.GREEDY
      • DecodingMethods.SAMPLE
    • ModelTypes
• ModelInference for Deployments
  • Infer text with deployments
  • Creating ModelInference instance
  • Generate methods