Class CohereChatRequest
Details for the chat request for Cohere models.
Inheritance
CohereChatRequest
Assembly: OCI.DotNetSDK.Generativeaiinference.dll
Syntax
public class CohereChatRequest : BaseChatRequest
Properties
ChatHistory
Declaration
[JsonProperty(PropertyName = "chatHistory")]
public List<CohereMessage> ChatHistory { get; set; }
Property Value
| Type |
Description |
| List<CohereMessage> |
The list of previous messages between the user and the model. The chat history gives the model context for responding to the user's inputs.
|
CitationQuality
Declaration
[JsonProperty(PropertyName = "citationQuality")]
[JsonConverter(typeof(StringEnumConverter))]
public CohereChatRequest.CitationQualityEnum? CitationQuality { get; set; }
Property Value
| Type |
Description |
| CohereChatRequest.CitationQualityEnum? |
When FAST is selected, citations are generated at the same time as the text output and the request will be completed sooner. May result in less accurate citations.
|
Documents
Declaration
[JsonProperty(PropertyName = "documents")]
public List<object> Documents { get; set; }
Property Value
| Type |
Description |
| List<object> |
A list of relevant documents that the model can refer to for generating grounded responses to the user's requests.
Some example keys that you can add to the dictionary are "text", "author", and "date". Keep the total word count of the strings in the dictionary to 300 words or less.
Example: [ { "title": "Tall penguins", "snippet": "Emperor penguins are the tallest." }, { "title": "Penguin habitats", "snippet": "Emperor penguins only live in Antarctica." }]
|
FrequencyPenalty
Declaration
[JsonProperty(PropertyName = "frequencyPenalty")]
public double FrequencyPenalty { get; set; }
Property Value
| Type |
Description |
| double |
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.
|
IsEcho
Declaration
[JsonProperty(PropertyName = "isEcho")]
public bool? IsEcho { get; set; }
Property Value
| Type |
Description |
| bool? |
Returns the full prompt that was sent to the model when True.
|
IsForceSingleStep
Declaration
[JsonProperty(PropertyName = "isForceSingleStep")]
public bool? IsForceSingleStep { get; set; }
Property Value
| Type |
Description |
| bool? |
When enabled, the model will issue (potentially multiple) tool calls in a single step, before it receives the tool responses and directly answers the user's original message.
|
IsRawPrompting
Declaration
[JsonProperty(PropertyName = "isRawPrompting")]
public bool? IsRawPrompting { get; set; }
Property Value
| Type |
Description |
| bool? |
When enabled, the user\u2019s message will be sent to the model without any preprocessing.
|
IsSearchQueriesOnly
Declaration
[JsonProperty(PropertyName = "isSearchQueriesOnly")]
public bool? IsSearchQueriesOnly { get; set; }
Property Value
| Type |
Description |
| bool? |
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.
|
IsStream
Declaration
[JsonProperty(PropertyName = "isStream")]
public bool? IsStream { get; set; }
Property Value
| Type |
Description |
| bool? |
Whether to stream the partial progress of the model's response. When set to true, as tokens become available, they are sent as data-only server-sent events.
|
Declaration
[JsonProperty(PropertyName = "maxInputTokens")]
public int? MaxInputTokens { get; set; }
Property Value
| Type |
Description |
| int? |
The maximum number of input tokens to send to the model. If not specified, max_input_tokens is the model's context length limit minus a small buffer.
|
MaxTokens
Declaration
[JsonProperty(PropertyName = "maxTokens")]
public int? MaxTokens { get; set; }
Property Value
| Type |
Description |
| int? |
The maximum number of output tokens that the model will generate for the response.
|
Message
Declaration
[Required(ErrorMessage = "Message is required.")]
[JsonProperty(PropertyName = "message")]
public string Message { get; set; }
Property Value
| Type |
Description |
| string |
The text that the user inputs for the model to respond to.
|
PreambleOverride
Declaration
[JsonProperty(PropertyName = "preambleOverride")]
public string PreambleOverride { get; set; }
Property Value
| Type |
Description |
| string |
If specified, the default Cohere preamble is replaced with the provided preamble. A preamble is an initial guideline message that can change the model's overall chat behavior and conversation style. Default preambles vary for different models.
Example: You are a travel advisor. Answer with a pirate tone.
|
PresencePenalty
Declaration
[JsonProperty(PropertyName = "presencePenalty")]
public double PresencePenalty { get; set; }
Property Value
| Type |
Description |
| double |
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.
|
PromptTruncation
Declaration
[JsonProperty(PropertyName = "promptTruncation")]
[JsonConverter(typeof(StringEnumConverter))]
public CohereChatRequest.PromptTruncationEnum? PromptTruncation { get; set; }
Property Value
| Type |
Description |
| CohereChatRequest.PromptTruncationEnum? |
Defaults to OFF. Dictates how the prompt will be constructed. With promptTruncation set to AUTO_PRESERVE_ORDER, some elements from chatHistory and documents will be dropped to construct a prompt that fits within the model's context length limit. During this process the order of the documents and chat history will be preserved. With prompt_truncation set to OFF, no elements will be dropped.
|
Declaration
[JsonProperty(PropertyName = "responseFormat")]
public CohereResponseFormat ResponseFormat { get; set; }
Property Value
SafetyMode
Declaration
[JsonProperty(PropertyName = "safetyMode")]
[JsonConverter(typeof(StringEnumConverter))]
public CohereChatRequest.SafetyModeEnum? SafetyMode { get; set; }
Property Value
| Type |
Description |
| CohereChatRequest.SafetyModeEnum? |
Safety mode: Adds a safety instruction for the model to use when generating responses.
Contextual: (Default) Puts fewer constraints on the output. It maintains core protections by aiming to reject harmful or illegal suggestions, but it allows profanity and some toxic content, sexually explicit and violent content, and content that contains medical, financial, or legal information. Contextual mode is suited for entertainment, creative, or academic use.
Strict: Aims to avoid sensitive topics, such as violent or sexual acts and profanity. This mode aims to provide a safer experience by prohibiting responses or recommendations that it finds inappropriate. Strict mode is suited for corporate use, such as for corporate communications and customer service.
Off: No safety mode is applied.
Note: This parameter is only compatible with models cohere.command-r-08-2024, cohere.command-r-plus-08-2024 and Cohere models released after these models. See release dates.
|
Seed
Declaration
[JsonProperty(PropertyName = "seed")]
public int? Seed { get; set; }
Property Value
| Type |
Description |
| int? |
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. However, determinism cannot be fully guaranteed.
|
StopSequences
Declaration
[JsonProperty(PropertyName = "stopSequences")]
public List<string> StopSequences { get; set; }
Property Value
| Type |
Description |
| List<string> |
Stop the model generation when it reaches a stop sequence defined in this parameter.
|
StreamOptions
Declaration
[JsonProperty(PropertyName = "streamOptions")]
public StreamOptions StreamOptions { get; set; }
Property Value
Temperature
Declaration
[JsonProperty(PropertyName = "temperature")]
public double Temperature { get; set; }
Property Value
| Type |
Description |
| double |
A number that sets the randomness of the generated output. A lower temperature means less random generations.
Use lower numbers for tasks 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.
|
Declaration
[JsonProperty(PropertyName = "toolResults")]
public List<CohereToolResult> ToolResults { get; set; }
Property Value
| Type |
Description |
| List<CohereToolResult> |
A list of results from invoking tools recommended by the model in the previous chat turn.
|
Declaration
[JsonProperty(PropertyName = "tools")]
public List<CohereTool> Tools { get; set; }
Property Value
| Type |
Description |
| List<CohereTool> |
A list of available tools (functions) that the model may suggest invoking before producing a text response.
|
TopK
Declaration
[JsonProperty(PropertyName = "topK")]
public int? TopK { get; set; }
Property Value
| Type |
Description |
| int? |
A sampling method in which the model chooses the next token randomly from the top k most likely tokens. A higher value for k generates more random output, which makes the output text sound more natural. The default value for k 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 only the probabilities of the top 10 add up to the value of p, then only the top 10 tokens are chosen.
|
TopP
Declaration
[JsonProperty(PropertyName = "topP")]
public double TopP { get; set; }
Property Value