PaLM๏ƒ

pydantic model llama_index.llms.palm.PaLM๏ƒ

PaLM LLM.

Show JSON schema
{
   "title": "PaLM",
   "description": "PaLM LLM.",
   "type": "object",
   "properties": {
      "callback_manager": {
         "title": "Callback Manager"
      },
      "model_name": {
         "title": "Model Name",
         "description": "The PaLM model to use.",
         "type": "string"
      },
      "num_output": {
         "title": "Num Output",
         "description": "The number of tokens to generate.",
         "type": "integer"
      },
      "generate_kwargs": {
         "title": "Generate Kwargs",
         "description": "Kwargs for generation.",
         "type": "object"
      }
   },
   "required": [
      "model_name",
      "num_output"
   ]
}

Config
  • arbitrary_types_allowed: bool = True

Fields
Validators
  • _validate_callback_manager ยป callback_manager

field generate_kwargs: dict [Optional]๏ƒ

Kwargs for generation.

field model_name: str [Required]๏ƒ

The PaLM model to use.

field num_output: int [Required]๏ƒ

The number of tokens to generate.

classmethod class_name() str๏ƒ

Get the class name, used as a unique ID in serialization.

This provides a key that makes serialization robust against actual class name changes.

complete(*args: Any, **kwargs: Any) Any๏ƒ

Completion endpoint for LLM.

stream_complete(*args: Any, **kwargs: Any) Any๏ƒ

Streaming completion endpoint for LLM.

property metadata: LLMMetadata๏ƒ

Get LLM metadata.