@sap-ai-sdk/foundation-models

import type { AzureOpenAiChatCompletionsRequestCommon } from './chat-completions-request-common.js'; import type { AzureOpenAiChatCompletionRequestMessage } from './chat-completion-request-message.js'; import type { AzureOpenAiAzureChatExtensionConfiguration } from './azure-chat-extension-configuration.js'; import type { AzureOpenAiParallelToolCalls } from './parallel-tool-calls.js'; import type { AzureOpenAiResponseFormatText } from './response-format-text.js'; import type { AzureOpenAiResponseFormatJsonObject } from './response-format-json-object.js'; import type { AzureOpenAiResponseFormatJsonSchema } from './response-format-json-schema.js'; import type { AzureOpenAiChatCompletionTool } from './chat-completion-tool.js'; import type { AzureOpenAiChatCompletionToolChoiceOption } from './chat-completion-tool-choice-option.js'; import type { AzureOpenAiChatCompletionFunctionCallOption } from './chat-completion-function-call-option.js'; import type { AzureOpenAiChatCompletionFunctions } from './chat-completion-functions.js'; /** * Representation of the 'AzureOpenAiCreateChatCompletionRequest' schema. */ export type AzureOpenAiCreateChatCompletionRequest = AzureOpenAiChatCompletionsRequestCommon & { /** * A list of messages comprising the conversation so far. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb). * Min Items: 1. */ messages: AzureOpenAiChatCompletionRequestMessage[]; /** * The configuration entries for Azure OpenAI chat extensions that use them. * This additional specification is only compatible with Azure OpenAI. */ data_sources?: AzureOpenAiAzureChatExtensionConfiguration[]; /** * Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. * * Maximum: 2. * Minimum: -2. */ frequency_penalty?: number | null; /** * Modify the likelihood of specified tokens appearing in the completion. * * Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. * */ logit_bias?: Record<string, number> | null; /** * 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`. */ logprobs?: boolean | null; /** * An integer between 0 and 20 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. * Maximum: 20. */ top_logprobs?: number | null; /** * The maximum number of [tokens](/tokenizer) 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. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. * */ max_tokens?: number | null; /** * How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. * @example 1 * Default: 1. * Maximum: 128. * Minimum: 1. */ n?: number | null; /** * Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. * * Maximum: 2. * Minimum: -2. */ presence_penalty?: number | null; parallel_tool_calls?: AzureOpenAiParallelToolCalls; /** * An object specifying the format that the model must output. Compatible with [GPT-4o](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-models), [GPT-4o mini](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-models), [GPT-4 Turbo](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-models) and all [GPT-3.5](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-35) Turbo models newer than `gpt-3.5-turbo-1106`. * * Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which guarantees the model will match your supplied JSON schema. * * Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. * * **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. * */ response_format?: AzureOpenAiResponseFormatText | AzureOpenAiResponseFormatJsonObject | AzureOpenAiResponseFormatJsonSchema; /** * This feature is in Beta. * If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. * Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. * * Maximum: 9223372036854776000. * Minimum: -9223372036854776000. */ seed?: number | null; /** * Up to 4 sequences where the API will stop generating further tokens. * */ stop?: string | string[]; /** * If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). * */ stream?: boolean | null; /** * What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. * * We generally recommend altering this or `top_p` but not both. * * @example 1 * Default: 1. * Maximum: 2. */ temperature?: number | null; /** * An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. * * We generally recommend altering this or `temperature` but not both. * * @example 1 * Default: 1. * Maximum: 1. */ top_p?: number | null; /** * A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. * */ tools?: AzureOpenAiChatCompletionTool[]; tool_choice?: AzureOpenAiChatCompletionToolChoiceOption; /** * Deprecated in favor of `tool_choice`. * * Controls which (if any) function is called by the model. * `none` means the model will not call a function and instead generates a message. * `auto` means the model can pick between generating a message or calling a function. * Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. * * `none` is the default when no functions are present. `auto` is the default if functions are present. * * @deprecated */ function_call?: 'none' | 'auto' | AzureOpenAiChatCompletionFunctionCallOption; /** * Deprecated in favor of `tools`. * * A list of functions the model may generate JSON inputs for. * * @deprecated * Min Items: 1. * Max Items: 128. */ functions?: AzureOpenAiChatCompletionFunctions[]; /** * A unique identifier representing your end-user, which can help to monitor and detect abuse. * * @example "user-1234" */ user?: string; } & Record<string, any>; //# sourceMappingURL=create-chat-completion-request.d.ts.map