static CohereChatRequestV2.Builder |
CohereChatRequestV2.builder() |
Create a new builder.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.citationOptions(CitationOptionsV2 citationOptions) |
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.copy(CohereChatRequestV2 model) |
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.documents(List<Object> documents) |
A list of relevant documents that the model can refer to for generating grounded
responses to the user’s requests.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.frequencyPenalty(Double frequencyPenalty) |
To reduce repetitiveness of generated tokens, this number penalizes new tokens based on
their frequency in the generated text so far.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.isLogProbsEnabled(Boolean isLogProbsEnabled) |
The log probabilities of the generated tokens will be included in the response.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.isRawPrompting(Boolean isRawPrompting) |
When enabled, the user\u2019s message will be sent to the model without any
preprocessing.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.isSearchQueriesOnly(Boolean isSearchQueriesOnly) |
When set to true, the response contains only a list of generated search queries without
the search results and the model will not respond to the user’s message.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.isStream(Boolean isStream) |
Whether to stream the partial progress of the model’s response.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.isStrictToolsEnabled(Boolean isStrictToolsEnabled) |
When set to true, tool calls in the Assistant message will be forced to follow the tool
definition strictly.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.maxTokens(Integer maxTokens) |
The maximum number of output tokens that the model will generate for the response.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.messages(List<CohereMessageV2> messages) |
A list of chat messages in chronological order, representing a conversation between the
user and the model.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.presencePenalty(Double presencePenalty) |
To reduce repetitiveness of generated tokens, this number penalizes new tokens based on
whether they’ve appeared in the generated text so far.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.priority(Integer priority) |
The priority of the request (lower means earlier handling; default 0 highest priority).
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.responseFormat(CohereResponseFormat responseFormat) |
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.safetyMode(CohereChatRequestV2.SafetyMode safetyMode) |
Safety mode: Adds a safety instruction for the model to use when generating responses.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.seed(Integer seed) |
If specified, the backend will make a best effort to sample tokens deterministically, so
that repeated requests with the same seed and parameters yield the same result.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.stopSequences(List<String> stopSequences) |
Stop the model generation when it reaches a stop sequence defined in this parameter.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.streamOptions(StreamOptions streamOptions) |
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.temperature(Double temperature) |
A number that sets the randomness of the generated output.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.thinking(CohereThinkingV2 thinking) |
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.toBuilder() |
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.tools(List<CohereToolV2> tools) |
A list of available tools (functions) that the model may suggest invoking before
producing a text response.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.toolsChoice(CohereChatRequestV2.ToolsChoice toolsChoice) |
Used to control whether or not the model will be forced to use a tool when answering.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.topK(Integer topK) |
A sampling method in which the model chooses the next token randomly from the top k most
likely tokens.
|
CohereChatRequestV2.Builder |
CohereChatRequestV2.Builder.topP(Double topP) |
If set to a probability 0.0 < p < 1.0, it ensures that only the most likely tokens, with
total probability mass of p, are considered for generation at each step.
|