public static class CohereChatRequest.Builder extends Object
Constructor and Description |
---|
Builder() |
Modifier and Type | Method and Description |
---|---|
CohereChatRequest |
build() |
CohereChatRequest.Builder |
chatHistory(List<CohereMessage> chatHistory)
A list of previous messages between the user and the model, meant to give the model
conversational context for responding to the user’s message.
|
CohereChatRequest.Builder |
copy(CohereChatRequest model) |
CohereChatRequest.Builder |
documents(List<Object> documents)
list of relevant documents that the model can cite to generate a more accurate reply.
|
CohereChatRequest.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.
|
CohereChatRequest.Builder |
isSearchQueriesOnly(Boolean isSearchQueriesOnly)
When true, the response will only contain a list of generated search queries, but no
search will take place, and no reply from the model to the user’s message will be
generated.
|
CohereChatRequest.Builder |
isStream(Boolean isStream)
Whether to stream back partial progress.
|
CohereChatRequest.Builder |
maxTokens(Integer maxTokens)
The maximum number of tokens to predict for each response.
|
CohereChatRequest.Builder |
message(String message)
Text input for the model to respond to.
|
CohereChatRequest.Builder |
preambleOverride(String preambleOverride)
When specified, the default Cohere preamble will be replaced with the provided one.
|
CohereChatRequest.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.
|
CohereChatRequest.Builder |
temperature(Double temperature)
A number that sets the randomness of the generated output.
|
CohereChatRequest.Builder |
topK(Integer topK)
An integer that sets up the model to use only the top k most likely tokens in the
generated output.
|
CohereChatRequest.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.
|
public CohereChatRequest.Builder message(String message)
Text input for the model to respond to.
message
- the value to setpublic CohereChatRequest.Builder chatHistory(List<CohereMessage> chatHistory)
A list of previous messages between the user and the model, meant to give the model conversational context for responding to the user’s message.
chatHistory
- the value to setpublic CohereChatRequest.Builder documents(List<Object> documents)
list of relevant documents that the model can cite to generate a more accurate reply. Some suggested keys are “text”, “author”, and “date”. For better generation quality, it is recommended to keep the total word count of the strings in the dictionary to under 300 words.
documents
- the value to setpublic CohereChatRequest.Builder isSearchQueriesOnly(Boolean isSearchQueriesOnly)
When true, the response will only contain a list of generated search queries, but no search will take place, and no reply from the model to the user’s message will be generated.
isSearchQueriesOnly
- the value to setpublic CohereChatRequest.Builder preambleOverride(String preambleOverride)
When specified, the default Cohere preamble will be replaced with the provided one. Preambles are a part of the prompt used to adjust the model’s overall behavior and conversation style. Default preambles vary for different models.
preambleOverride
- the value to setpublic CohereChatRequest.Builder isStream(Boolean isStream)
Whether to stream back partial progress. If set, tokens are sent as data-only server-sent events as they become available.
isStream
- the value to setpublic CohereChatRequest.Builder maxTokens(Integer maxTokens)
The maximum number of tokens to predict for each response. Includes input plus output tokens.
maxTokens
- the value to setpublic CohereChatRequest.Builder temperature(Double temperature)
A number that sets the randomness of the generated output. A lower temperature means a less random generations. Use lower numbers for tasks with a correct answer such as question answering or summarizing. High temperatures can generate hallucinations or factually incorrect information. Start with temperatures lower than 1.0 and increase the temperature for more creative outputs, as you regenerate the prompts to refine the outputs.
temperature
- the value to setpublic CohereChatRequest.Builder topK(Integer topK)
An integer that sets up the model to use only the top k most likely tokens in the generated output. A higher k introduces more randomness into the output making the output text sound more natural. Default value is 0 which disables this method and considers all tokens. To set a number for the likely tokens, choose an integer between 1 and 500.
If also using top p, then the model considers only the top tokens whose probabilities add up to p percent and ignores the rest of the k tokens. For example, if k is 20, but the probabilities of the top 10 add up to .75, then only the top 10 tokens are chosen.
topK
- the value to setpublic CohereChatRequest.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.
To eliminate tokens with low likelihood, assign p a minimum percentage for the next token's likelihood. For example, when p is set to 0.75, the model eliminates the bottom 25 percent for the next token. Set to 1.0 to consider all tokens and set to 0 to disable. If both k and p are enabled, p acts after k.
topP
- the value to setpublic CohereChatRequest.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. Greater numbers encourage the model to use new tokens, while lower numbers encourage the model to repeat the tokens. Set to 0 to disable.
frequencyPenalty
- the value to setpublic CohereChatRequest.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. Greater numbers encourage the model to use new tokens, while lower numbers encourage the model to repeat the tokens.
Similar to frequency penalty, a penalty is applied to previously present tokens, except that this penalty is applied equally to all tokens that have already appeared, regardless of how many times they've appeared. Set to 0 to disable.
presencePenalty
- the value to setpublic CohereChatRequest build()
public CohereChatRequest.Builder copy(CohereChatRequest model)
Copyright © 2016–2024. All rights reserved.