An interface defining the input to the ChatGoogleGenerativeAI class.
interface GoogleGenerativeAIChatInputBaseChatModelParamsPick<GoogleGenerativeAIChatCallOptions, "streamUsage">Google API key to use
Google API version to use
Google API base URL to use
Whether or not model supports system instructions. The following models support system instructions:
Google API custom headers to use
Whether to disable streaming.
If streaming is bypassed, then stream() will defer to
invoke().
Whether or not to force the model to respond with JSON.
Available for gemini-1.5 models and later.
The maximum number of concurrent calls that can be made.
Defaults to Infinity, which means no limit.
Maximum number of tokens to generate in the completion.
The maximum number of retries that can be made for a single call, with an exponential backoff between each attempt. Defaults to 6.
Model Name to use
Note: The format must follow the pattern - {model}
Custom handler to handle failed attempts. Takes the originally thrown error object as input, and should itself throw an error if the input error is not retryable.
Version of AIMessage output format to store in message content.
AIMessage.contentBlocks will lazily parse the contents of content into a
standard format. This flag can be used to additionally store the standard format
as the message content, e.g., for serialization purposes.
.contentBlocks).contentBlocks)You can also set LC_OUTPUT_VERSION as an environment variable to "v1" to
enable this by default.
A list of unique SafetySetting instances for blocking unsafe content. The API will block
any prompts and responses that fail to meet the thresholds set by these settings. If there
is no SafetySetting for a given SafetyCategory provided in the list, the API will use
the default safety setting for that category.
The set of character sequences (up to 5) that will stop output generation. If specified, the API will stop at the first appearance of a stop sequence.
Note: The stop sequence will not be included as part of the response. Note: stopSequences is only supported for Gemini models
Whether to stream the results or not
Whether or not to include usage data, like token counts in the streamed response chunks.
Controls the randomness of the output.
Values can range from [0.0,2.0], inclusive. A value closer to 2.0 will produce responses that are more varied and creative, while a value closer to 0.0 will typically result in less surprising responses from the model.
Note: The default value varies by model
Optional. Config for thinking features. An error will be returned if this field is set for models that don't support thinking.
Top-k changes how the model selects tokens for output.
A top-k of 1 means the selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-k of 3 means that the next token is selected from among the 3 most probable tokens (using temperature).
Note: The default value varies by model
Top-p changes how the model selects tokens for output.
Tokens are selected from most probable to least until the sum of their probabilities equals the top-p value.
For example, if tokens A, B, and C have a probability of .3, .2, and .1 and the top-p value is .5, then the model will select either A or B as the next token (using temperature).
Note: The default value varies by model