Expand description
google.ai.generativelanguage.v1beta2 protos.
Modules§
- content_
filter - Nested message and enum types in
ContentFilter
. - discuss_
service_ client - Generated client implementations.
- model_
service_ client - Generated client implementations.
- safety_
rating - Nested message and enum types in
SafetyRating
. - safety_
setting - Nested message and enum types in
SafetySetting
. - text_
service_ client - Generated client implementations.
Structs§
- Citation
Metadata - A collection of source attributions for a piece of content.
- Citation
Source - A citation to a source for a portion of a specific response.
- Content
Filter - Content filtering metadata associated with processing a single request.
- Count
Message Tokens Request - Counts the number of tokens in the
prompt
sent to a model. - Count
Message Tokens Response - A response from
CountMessageTokens
. - Embed
Text Request - Request to get a text embedding from the model.
- Embed
Text Response - The response to a EmbedTextRequest.
- Embedding
- A list of floats representing the embedding.
- Example
- An input/output example used to instruct the Model.
- Generate
Message Request - Request to generate a message response from the model.
- Generate
Message Response - The response from the model.
- Generate
Text Request - Request to generate a text completion response from the model.
- Generate
Text Response - The response from the model, including candidate completions.
- GetModel
Request - Request for getting information about a specific Model.
- List
Models Request - Request for listing all Models.
- List
Models Response - Response from
ListModel
containing a paginated list of Models. - Message
- The base unit of structured text.
- Message
Prompt - All of the structured input text passed to the model as a prompt.
- Model
- Information about a Generative Language Model.
- Safety
Feedback - Safety feedback for an entire request.
- Safety
Rating - Safety rating for a piece of content.
- Safety
Setting - Safety setting, affecting the safety-blocking behavior.
- Text
Completion - Output text returned from a model.
- Text
Prompt - Text given to the model as a prompt.
Enums§
- Harm
Category - The category of a rating.