interface WatsonxGatewayChatParamsPenalizes repeated tokens according to frequency
Version of AIMessage output format to store in message content.
Maximum number of times a call can recurse. If not provided, defaults to 25.
Callbacks for this call and any sub-calls (eg. a Chain calling an LLM). Tags are passed to all callbacks, metadata is passed to handle*Start callbacks.
Runtime values for attributes previously made configurable on this Runnable, or sub-Runnables.
Penalizes repeated tokens according to frequency
Dictionary used to adjust the probability of specific tokens being generated
Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.
Describes the format of structured outputs. This should be provided if an output is considered to be structured
The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. Set to 0 for the model's configured max generated tokens.
Maximum number of parallel calls to make.
Metadata for this call and any sub-calls (eg. a Chain calling an LLM). Keys should be strings, values should be JSON-serializable.
Model name to use. Available options are: qwen-turbo, qwen-plus, qwen-max, or Other compatible models.
Additional parameters usable only in model gateway
Number of completions to generate for each prompt
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.
Penalizes repeated tokens
A lower reasoning effort can result in faster responses, fewer tokens used, and shorter reasoning_content in the responses. Supported values are low, medium, and high.
Maximum number of times a call can recurse. If not provided, defaults to 25.
The tool response format.
If "content" then the output of the tool is interpreted as the contents of a ToolMessage. If "content_and_artifact" then the output is expected to be a two-tuple corresponding to the (content, artifact) of a ToolMessage.
Unique identifier for the tracer run for this call. If not provided, a new UUID will be generated.
Name for the tracer run for this call. Defaults to the name of the class.
Abort signal for this call. If provided, the call will be aborted when the signal is aborted.
Stop tokens to use for this call. If not provided, the default stop tokens for the model will be used.
Tags for this call and any sub-calls (eg. a Chain calling an LLM). You can use these to filter calls.
Amount of randomness injected into the response. Ranges from 0 to 1 (0 is not included). Use temp closer to 0 for analytical / multiple choice, and temp closer to 1 for creative and generative tasks. Defaults to 0.95.
Timeout for this call in milliseconds.
Specifies how the chat model should use tools.
An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.
Total probability mass of tokens to consider at each step. Range from 0 to 1.0. Defaults to 0.8.