View source on GitHub
|
A collection of type definitions used throughout the library.
Classes
class AuthorError: Raised by the chat (or reply) functions when the author list can't be normalized.
class BlockedReason: A list of reasons why content may have been blocked.
class ChatResponse: A chat response from the model.
class CitationMetadataDict: A collection of source attributions for a piece of content.
class CitationSourceDict: A citation to a source for a portion of a specific response.
class Completion: The result returned by generativeai.generate_text.
class ContentFilterDict: Content filtering metadata associated with processing a single request.
class ExampleDict: A dict representation of a glm.Example.
class HarmBlockThreshold: Block at and beyond a specified harm probability.
class HarmCategory: The category of a rating.
class HarmProbability: The probability that a piece of content is harmful.
class MessageDict: A dict representation of a glm.Message.
class MessagePromptDict: A dict representation of a glm.MessagePrompt.
class Model: A dataclass representation of a glm.Model.
class ResponseDict: A dict representation of a glm.GenerateMessageResponse.
class SafetyFeedbackDict: Safety feedback for an entire request.
class SafetyRatingDict: Safety rating for a piece of content.
class SafetySettingDict: Safety setting, affecting the safety-blocking behavior.
class TunedModel: A dataclass representation of a glm.TunedModel.
class TunedModelState: The state of the tuned model.