google_generative_language_api library
Adds a rest client for the Google Generative Language API.
Classes
- ContentFilter
- Content filtering metadata associated with processing a single request.
- CountMessageTokensRequest
- Represents a request to count the number of tokens in a message.
- EmbeddedText
- The response to a EmbedTextRequest.
- Embedding
- A list of floats representing the embedding.
- EmbedTextRequest
- The request body to generate an embedding from text.
- Example
- An input/output example used to instruct the Model.
- GeneratedMessage
-
Represents the output of a
generateMessage
response from the model. -
GeneratedResponseBase<
T> - Represents an abstract generated response from the model.
- GeneratedText
-
Represents the output of a
generateText
response from the model. - GenerateMessageRequest
- Represents a request to generate a message.
-
GenerateRequestBase<
T extends Prompt> - Represents an abstract request to generate text or a message.
- GenerateTextRequest
- Represents a request to generate text.
- GenerativeLanguageAPI
- The GenerativeLanguageAPI class provides methods for interacting with the Generative Language API.
- ListModelResponse
-
Represents the response from the
listModels
API call, containing a paginated list of models. - Message
- The base unit of structured text.
- MessagePrompt
- All of the structured input text passed to the model as a prompt.
- Model
- Information about a Generative Language Model.
- Prompt
- Represents an abstract prompt for generating text.
- SafetyFeedback
- Safety feedback for an entire request.
- SafetyRating
- Safety rating for a piece of content.
- SafetySetting
- Safety setting, affecting the safety-blocking behavior.
- TextCompletion
- Output text returned from a model.
- TextPrompt
- Text given to the model as a prompt.
Enums
- BlockedReason
- A list of reasons why content may have been blocked.
- HarmBlockThreshold
- Block at and beyond a specified harm probability.
- HarmCategory
- The category of a rating.
- HarmProbability
- The probability that a piece of content is harmful.