Record Class CohereChatBedrockApi.CohereChatRequest

java.lang.Object
java.lang.Record
org.springframework.ai.bedrock.cohere.api.CohereChatBedrockApi.CohereChatRequest
Record Components:
prompt - The input prompt to generate the response from.
temperature - (optional) Use a lower value to decrease randomness in the response.
topP - (optional) Use a lower value to ignore less probable options. Set to 0 or 1.0 to disable.
topK - (optional) Specify the number of token choices the model uses to generate the next token.
maxTokens - (optional) Specify the maximum number of tokens to use in the generated response.
stopSequences - (optional) Configure up to four sequences that the model recognizes. After a stop sequence, the model stops generating further tokens. The returned text doesn't contain the stop sequence.
returnLikelihoods - (optional) Specify how and if the token likelihoods are returned with the response.
stream - (optional) Specify true to return the response piece-by-piece in real-time and false to return the complete response after the process finishes.
numGenerations - (optional) The maximum number of generations that the model should return.
logitBias - (optional) prevents the model from generating unwanted tokens or incentivize the model to include desired tokens. The format is {token_id: bias} where bias is a float between -10 and 10. Tokens can be obtained from text using any tokenization service, such as Cohere’s Tokenize endpoint.
truncate - (optional) Specifies how the API handles inputs longer than the maximum token length.
Enclosing class:
CohereChatBedrockApi

public static record CohereChatBedrockApi.CohereChatRequest(String prompt, Float temperature, Float topP, Integer topK, Integer maxTokens, List<String> stopSequences, CohereChatBedrockApi.CohereChatRequest.ReturnLikelihoods returnLikelihoods, boolean stream, Integer numGenerations, CohereChatBedrockApi.CohereChatRequest.LogitBias logitBias, CohereChatBedrockApi.CohereChatRequest.Truncate truncate) extends Record
CohereChatRequest encapsulates the request parameters for the Cohere command model.