View source on GitHub
|
A collection of type definitions used throughout the library.
Classes
class AsyncGenerateContentResponse: This is the async version of genai.GenerateContentResponse.
class AuthorError: Raised by the chat (or reply) functions when the author list can't be normalized.
class BlobDict: dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list.
class BlockedPromptException: Common base class for all non-exit exceptions.
class BlockedReason: A list of reasons why content may have been blocked.
class BrokenResponseError: Common base class for all non-exit exceptions.
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 ContentDict: dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list.
class ContentFilterDict: Content filtering metadata associated with processing a single request.
class ExampleDict: A dict representation of a glm.Example.
class GenerateContentResponse: Instances of this class manage the response of the generate_content_async method.
class GenerationConfigDict: dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list.
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 IncompleteIterationError: Common base class for all non-exit exceptions.
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 PartDict: dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list.
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 StopCandidateException: Common base class for all non-exit exceptions.
class TunedModel: A dataclass representation of a glm.TunedModel.
class TunedModelState: The state of the tuned model.