{ "openapi": "3.0.0", "info": { "title": "Azure OpenAI Service API", "description": "Azure OpenAI APIs for completions and search", "version": "2024-02-01" }, "servers": [ { "url": "https://{endpoint}/openai", "variables": { "endpoint": { "default": "your-resource-name.openai.azure.com" } } } ], "security": [ { "bearer": [ "api.read" ] }, { "apiKey": [] } ], "paths": { "/deployments/{deployment-id}/completions": { "post": { "summary": "Creates a completion for the provided prompt, parameters and chosen model.", "operationId": "Completions_Create", "parameters": [ { "in": "path", "name": "deployment-id", "required": true, "schema": { "type": "string", "example": "davinci", "description": "Deployment id of the model which was deployed." } }, { "in": "query", "name": "api-version", "required": true, "schema": { "type": "string", "example": "2024-02-01", "description": "api version" } } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "prompt": { "description": "The prompt(s) to generate completions for, encoded as a string or array of strings.\nNote that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. Maximum allowed size of string list is 2048.", "oneOf": [ { "type": "string", "default": "", "example": "This is a test.", "nullable": true }, { "type": "array", "items": { "type": "string", "default": "", "example": "This is a test.", "nullable": false }, "description": "Array size minimum of 1 and maximum of 2048" } ] }, "max_tokens": { "description": "The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096). Has minimum of 0.", "type": "integer", "default": 16, "example": 16, "nullable": true }, "temperature": { "description": "What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer.\nWe generally recommend altering this or top_p but not both.", "type": "number", "default": 1, "example": 1, "nullable": true }, "top_p": { "description": "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.\nWe generally recommend altering this or temperature but not both.", "type": "number", "default": 1, "example": 1, "nullable": true }, "logit_bias": { "description": "Defaults to 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 GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs. 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. As an example, you can pass {\"50256\" : -100} to prevent the <|endoftext|> token from being generated.", "type": "object", "nullable": false }, "user": { "description": "A unique identifier representing your end-user, which can help monitoring and detecting abuse", "type": "string", "nullable": false }, "n": { "description": "How many completions to generate for each prompt. Minimum of 1 and maximum of 128 allowed.\nNote: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.", "type": "integer", "default": 1, "example": 1, "nullable": true }, "stream": { "description": "Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.", "type": "boolean", "nullable": true, "default": false }, "logprobs": { "description": "Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response.\nMinimum of 0 and maximum of 5 allowed.", "type": "integer", "default": null, "nullable": true }, "suffix": { "type": "string", "nullable": true, "description": "The suffix that comes after a completion of inserted text." }, "echo": { "description": "Echo back the prompt in addition to the completion", "type": "boolean", "default": false, "nullable": true }, "stop": { "description": "Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.", "oneOf": [ { "type": "string", "default": "<|endoftext|>", "example": "\n", "nullable": true }, { "type": "array", "items": { "type": "string", "example": "\n", "nullable": false }, "description": "Array minimum size of 1 and maximum of 4" } ] }, "completion_config": { "type": "string", "nullable": true }, "presence_penalty": { "description": "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.", "type": "number", "default": 0 }, "frequency_penalty": { "description": "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.", "type": "number", "default": 0 }, "best_of": { "description": "Generates best_of completions server-side and returns the \"best\" (the one with the highest log probability per token). Results cannot be streamed.\nWhen used with n, best_of controls the number of candidate completions and n specifies how many to return - best_of must be greater than n.\nNote: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop. Has maximum value of 128.", "type": "integer" } } }, "example": { "prompt": "Negate the following sentence.The price for bubblegum increased on thursday.\n\n Negated Sentence:", "max_tokens": 50 } } } }, "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "type": "object", "properties": { "id": { "type": "string" }, "object": { "type": "string" }, "created": { "type": "integer" }, "model": { "type": "string" }, "prompt_filter_results": { "$ref": "#/components/schemas/promptFilterResults" }, "choices": { "type": "array", "items": { "type": "object", "properties": { "text": { "type": "string" }, "index": { "type": "integer" }, "logprobs": { "type": "object", "properties": { "tokens": { "type": "array", "items": { "type": "string" } }, "token_logprobs": { "type": "array", "items": { "type": "number" } }, "top_logprobs": { "type": "array", "items": { "type": "object", "additionalProperties": { "type": "number" } } }, "text_offset": { "type": "array", "items": { "type": "integer" } } }, "nullable": true }, "finish_reason": { "type": "string" }, "content_filter_results": { "$ref": "#/components/schemas/contentFilterChoiceResults" } } } }, "usage": { "type": "object", "properties": { "completion_tokens": { "type": "number", "format": "int32" }, "prompt_tokens": { "type": "number", "format": "int32" }, "total_tokens": { "type": "number", "format": "int32" } }, "required": [ "prompt_tokens", "total_tokens", "completion_tokens" ] } }, "required": [ "id", "object", "created", "model", "choices" ] }, "example": { "model": "davinci", "object": "text_completion", "id": "cmpl-4509KAos68kxOqpE2uYGw81j6m7uo", "created": 1637097562, "choices": [ { "index": 0, "text": "The price for bubblegum decreased on thursday.", "logprobs": null, "finish_reason": "stop" } ] } } }, "headers": { "apim-request-id": { "description": "Request ID for troubleshooting purposes", "schema": { "type": "string" } } } }, "default": { "description": "Service unavailable", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/errorResponse" } } }, "headers": { "apim-request-id": { "description": "Request ID for troubleshooting purposes", "schema": { "type": "string" } } } } }, "x-ms-examples": { "Create a completion.": { "$ref": "./examples/completions.json" } } } }, "/deployments/{deployment-id}/embeddings": { "post": { "summary": "Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.", "operationId": "embeddings_create", "parameters": [ { "in": "path", "name": "deployment-id", "required": true, "schema": { "type": "string", "example": "ada-search-index-v1" }, "description": "The deployment id of the model which was deployed." }, { "in": "query", "name": "api-version", "required": true, "schema": { "type": "string", "example": "2024-02-01", "description": "api version" } } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "additionalProperties": true, "properties": { "input": { "description": "Input text to get embeddings for, encoded as a string. To get embeddings for multiple inputs in a single request, pass an array of strings. Each input must not exceed 2048 tokens in length.\nUnless you are embedding code, we suggest replacing newlines (\\n) in your input with a single space, as we have observed inferior results when newlines are present.", "oneOf": [ { "type": "string", "default": "", "example": "This is a test.", "nullable": true }, { "type": "array", "minItems": 1, "maxItems": 2048, "items": { "type": "string", "minLength": 1, "example": "This is a test.", "nullable": false } } ] }, "user": { "description": "A unique identifier representing your end-user, which can help monitoring and detecting abuse.", "type": "string", "nullable": false }, "input_type": { "description": "input type of embedding search to use", "type": "string", "example": "query" } }, "required": [ "input" ] } } } }, "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "type": "object", "properties": { "object": { "type": "string" }, "model": { "type": "string" }, "data": { "type": "array", "items": { "type": "object", "properties": { "index": { "type": "integer" }, "object": { "type": "string" }, "embedding": { "type": "array", "items": { "type": "number" } } }, "required": [ "index", "object", "embedding" ] } }, "usage": { "type": "object", "properties": { "prompt_tokens": { "type": "integer" }, "total_tokens": { "type": "integer" } }, "required": [ "prompt_tokens", "total_tokens" ] } }, "required": [ "object", "model", "data", "usage" ] } } } } }, "x-ms-examples": { "Create a embeddings.": { "$ref": "./examples/embeddings.json" } } } }, "/deployments/{deployment-id}/chat/completions": { "post": { "summary": "Creates a completion for the chat message", "operationId": "ChatCompletions_Create", "parameters": [ { "in": "path", "name": "deployment-id", "required": true, "schema": { "type": "string", "description": "Deployment id of the model which was deployed." } }, { "in": "query", "name": "api-version", "required": true, "schema": { "type": "string", "example": "2024-02-01", "description": "api version" } } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/createChatCompletionRequest" } } } }, "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/createChatCompletionResponse" } } }, "headers": { "apim-request-id": { "description": "Request ID for troubleshooting purposes", "schema": { "type": "string" } } } }, "default": { "description": "Service unavailable", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/errorResponse" } } }, "headers": { "apim-request-id": { "description": "Request ID for troubleshooting purposes", "schema": { "type": "string" } } } } }, "x-ms-examples": { "Create a chat completion.": { "$ref": "./examples/chat_completions.json" }, "Creates a completion based on Azure Search data and system-assigned managed identity.": { "$ref": "./examples/chat_completions_azure_search_minimum.json" }, "Creates a completion based on Azure Search vector data, previous assistant message and user-assigned managed identity.": { "$ref": "./examples/chat_completions_azure_search_advanced.json" }, "Creates a completion for the provided Azure Cosmos DB.": { "$ref": "./examples/chat_completions_cosmos_db.json" } } } }, "/deployments/{deployment-id}/audio/transcriptions": { "post": { "summary": "Transcribes audio into the input language.", "operationId": "Transcriptions_Create", "parameters": [ { "in": "path", "name": "deployment-id", "required": true, "schema": { "type": "string", "example": "whisper", "description": "Deployment id of the whisper model." } }, { "in": "query", "name": "api-version", "required": true, "schema": { "type": "string", "example": "2024-02-01", "description": "api version" } } ], "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/createTranscriptionRequest" } } } }, "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "oneOf": [ { "$ref": "#/components/schemas/audioResponse" }, { "$ref": "#/components/schemas/audioVerboseResponse" } ] } }, "text/plain": { "schema": { "type": "string", "description": "Transcribed text in the output format (when response_format was one of text, vtt or srt)." } } } } }, "x-ms-examples": { "Create an audio transcription with json response format.": { "$ref": "./examples/audio_transcription_object.json" }, "Create an audio transcription with text response format.": { "$ref": "./examples/audio_transcription_text.json" } } } }, "/deployments/{deployment-id}/audio/translations": { "post": { "summary": "Transcribes and translates input audio into English text.", "operationId": "Translations_Create", "parameters": [ { "in": "path", "name": "deployment-id", "required": true, "schema": { "type": "string", "example": "whisper", "description": "Deployment id of the whisper model which was deployed." } }, { "in": "query", "name": "api-version", "required": true, "schema": { "type": "string", "example": "2024-02-01", "description": "api version" } } ], "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/createTranslationRequest" } } } }, "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "oneOf": [ { "$ref": "#/components/schemas/audioResponse" }, { "$ref": "#/components/schemas/audioVerboseResponse" } ] } }, "text/plain": { "schema": { "type": "string", "description": "Transcribed text in the output format (when response_format was one of text, vtt or srt)." } } } } }, "x-ms-examples": { "Create an audio translation with json response format.": { "$ref": "./examples/audio_translation_object.json" }, "Create an audio translation with text response format.": { "$ref": "./examples/audio_translation_text.json" } } } }, "/deployments/{deployment-id}/images/generations": { "post": { "summary": "Generates a batch of images from a text caption on a given DALLE model deployment", "operationId": "ImageGenerations_Create", "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/imageGenerationsRequest" } } } }, "parameters": [ { "in": "path", "name": "deployment-id", "required": true, "schema": { "type": "string", "example": "dalle-deployment", "description": "Deployment id of the dalle model which was deployed." } }, { "in": "query", "name": "api-version", "required": true, "schema": { "type": "string", "example": "2024-02-01", "description": "api version" } } ], "responses": { "200": { "description": "Ok", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/generateImagesResponse" } } } }, "default": { "description": "An error occurred.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/dalleErrorResponse" } } } } }, "x-ms-examples": { "Create an image.": { "$ref": "./examples/image_generation.json" } } } } }, "components": { "schemas": { "errorResponse": { "type": "object", "properties": { "error": { "$ref": "#/components/schemas/error" } } }, "errorBase": { "type": "object", "properties": { "code": { "type": "string" }, "message": { "type": "string" } } }, "error": { "type": "object", "allOf": [ { "$ref": "#/components/schemas/errorBase" } ], "properties": { "param": { "type": "string" }, "type": { "type": "string" }, "inner_error": { "$ref": "#/components/schemas/innerError" } } }, "innerError": { "description": "Inner error with additional details.", "type": "object", "properties": { "code": { "$ref": "#/components/schemas/innerErrorCode" }, "content_filter_results": { "$ref": "#/components/schemas/contentFilterPromptResults" } } }, "innerErrorCode": { "description": "Error codes for the inner error object.", "enum": [ "ResponsibleAIPolicyViolation" ], "type": "string", "x-ms-enum": { "name": "InnerErrorCode", "modelAsString": true, "values": [ { "value": "ResponsibleAIPolicyViolation", "description": "The prompt violated one of more content filter rules." } ] } }, "dalleErrorResponse": { "type": "object", "properties": { "error": { "$ref": "#/components/schemas/dalleError" } } }, "dalleError": { "type": "object", "allOf": [ { "$ref": "#/components/schemas/errorBase" } ], "properties": { "param": { "type": "string" }, "type": { "type": "string" }, "inner_error": { "$ref": "#/components/schemas/dalleInnerError" } } }, "dalleInnerError": { "description": "Inner error with additional details.", "type": "object", "properties": { "code": { "$ref": "#/components/schemas/innerErrorCode" }, "content_filter_results": { "$ref": "#/components/schemas/dalleFilterResults" }, "revised_prompt": { "type": "string", "description": "The prompt that was used to generate the image, if there was any revision to the prompt." } } }, "contentFilterResultBase": { "type": "object", "properties": { "filtered": { "type": "boolean" } }, "required": [ "filtered" ] }, "contentFilterSeverityResult": { "type": "object", "allOf": [ { "$ref": "#/components/schemas/contentFilterResultBase" }, { "properties": { "severity": { "type": "string", "enum": [ "safe", "low", "medium", "high" ], "x-ms-enum": { "name": "ContentFilterSeverity", "modelAsString": true, "values": [ { "value": "safe", "description": "General content or related content in generic or non-harmful contexts." }, { "value": "low", "description": "Harmful content at a low intensity and risk level." }, { "value": "medium", "description": "Harmful content at a medium intensity and risk level." }, { "value": "high", "description": "Harmful content at a high intensity and risk level." } ] } } } } ], "required": [ "severity", "filtered" ] }, "contentFilterDetectedResult": { "type": "object", "allOf": [ { "$ref": "#/components/schemas/contentFilterResultBase" }, { "properties": { "detected": { "type": "boolean" } } } ], "required": [ "detected", "filtered" ] }, "contentFilterDetectedWithCitationResult": { "type": "object", "allOf": [ { "$ref": "#/components/schemas/contentFilterDetectedResult" }, { "properties": { "citation": { "type": "object", "properties": { "URL": { "type": "string" }, "license": { "type": "string" } } } } } ], "required": [ "detected", "filtered" ] }, "contentFilterResultsBase": { "type": "object", "description": "Information about the content filtering results.", "properties": { "sexual": { "$ref": "#/components/schemas/contentFilterSeverityResult" }, "violence": { "$ref": "#/components/schemas/contentFilterSeverityResult" }, "hate": { "$ref": "#/components/schemas/contentFilterSeverityResult" }, "self_harm": { "$ref": "#/components/schemas/contentFilterSeverityResult" }, "profanity": { "$ref": "#/components/schemas/contentFilterDetectedResult" }, "error": { "$ref": "#/components/schemas/errorBase" } } }, "contentFilterPromptResults": { "type": "object", "description": "Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about jailbreak content and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id.", "allOf": [ { "$ref": "#/components/schemas/contentFilterResultsBase" }, { "properties": { "jailbreak": { "$ref": "#/components/schemas/contentFilterDetectedResult" } } } ] }, "contentFilterChoiceResults": { "type": "object", "description": "Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about third party text and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id.", "allOf": [ { "$ref": "#/components/schemas/contentFilterResultsBase" }, { "properties": { "protected_material_text": { "$ref": "#/components/schemas/contentFilterDetectedResult" } } }, { "properties": { "protected_material_code": { "$ref": "#/components/schemas/contentFilterDetectedWithCitationResult" } } } ] }, "promptFilterResult": { "type": "object", "description": "Content filtering results for a single prompt in the request.", "properties": { "prompt_index": { "type": "integer" }, "content_filter_results": { "$ref": "#/components/schemas/contentFilterPromptResults" } } }, "promptFilterResults": { "type": "array", "description": "Content filtering results for zero or more prompts in the request. In a streaming request, results for different prompts may arrive at different times or in different orders.", "items": { "$ref": "#/components/schemas/promptFilterResult" } }, "dalleContentFilterResults": { "type": "object", "description": "Information about the content filtering results.", "properties": { "sexual": { "$ref": "#/components/schemas/contentFilterSeverityResult" }, "violence": { "$ref": "#/components/schemas/contentFilterSeverityResult" }, "hate": { "$ref": "#/components/schemas/contentFilterSeverityResult" }, "self_harm": { "$ref": "#/components/schemas/contentFilterSeverityResult" } } }, "dalleFilterResults": { "type": "object", "description": "Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about jailbreak content and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id.", "allOf": [ { "$ref": "#/components/schemas/dalleContentFilterResults" }, { "properties": { "profanity": { "$ref": "#/components/schemas/contentFilterDetectedResult" }, "jailbreak": { "$ref": "#/components/schemas/contentFilterDetectedResult" } } } ] }, "chatCompletionsRequestCommon": { "type": "object", "properties": { "temperature": { "description": "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.\nWe generally recommend altering this or `top_p` but not both.", "type": "number", "minimum": 0, "maximum": 2, "default": 1, "example": 1, "nullable": true }, "top_p": { "description": "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.\nWe generally recommend altering this or `temperature` but not both.", "type": "number", "minimum": 0, "maximum": 1, "default": 1, "example": 1, "nullable": true }, "stream": { "description": "If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a `data: [DONE]` message.", "type": "boolean", "nullable": true, "default": false }, "stop": { "description": "Up to 4 sequences where the API will stop generating further tokens.", "oneOf": [ { "type": "string", "nullable": true }, { "type": "array", "items": { "type": "string", "nullable": false }, "minItems": 1, "maxItems": 4, "description": "Array minimum size of 1 and maximum of 4" } ], "default": null }, "max_tokens": { "description": "The maximum number of tokens allowed for the generated answer. By default, the number of tokens the model can return will be (4096 - prompt tokens).", "type": "integer", "default": 4096 }, "presence_penalty": { "description": "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.", "type": "number", "default": 0, "minimum": -2, "maximum": 2 }, "frequency_penalty": { "description": "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.", "type": "number", "default": 0, "minimum": -2, "maximum": 2 }, "logit_bias": { "description": "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.", "type": "object", "nullable": true }, "user": { "description": "A unique identifier representing your end-user, which can help Azure OpenAI to monitor and detect abuse.", "type": "string", "example": "user-1234", "nullable": false } } }, "createChatCompletionRequest": { "type": "object", "allOf": [ { "$ref": "#/components/schemas/chatCompletionsRequestCommon" }, { "properties": { "messages": { "description": "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).", "type": "array", "minItems": 1, "items": { "$ref": "#/components/schemas/chatCompletionRequestMessage" } }, "data_sources": { "type": "array", "description": " The configuration entries for Azure OpenAI chat extensions that use them.\n This additional specification is only compatible with Azure OpenAI.", "items": { "$ref": "#/components/schemas/azureChatExtensionConfiguration" } }, "n": { "type": "integer", "minimum": 1, "maximum": 128, "default": 1, "example": 1, "nullable": true, "description": "How many chat completion choices to generate for each input message." }, "seed": { "type": "integer", "minimum": -9223372036854775808, "maximum": 9223372036854775807, "default": 0, "example": 1, "nullable": true, "description": "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." }, "response_format": { "type": "object", "description": "An object specifying the format that the model must output. Used to enable JSON mode.", "properties": { "type": { "$ref": "#/components/schemas/chatCompletionResponseFormat" } } }, "tools": { "description": "A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.", "type": "array", "minItems": 1, "items": { "$ref": "#/components/schemas/chatCompletionTool" } }, "tool_choice": { "$ref": "#/components/schemas/chatCompletionToolChoiceOption" }, "functions": { "description": "Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for.", "type": "array", "minItems": 1, "maxItems": 128, "items": { "$ref": "#/components/schemas/chatCompletionFunction" } }, "function_call": { "description": "Deprecated in favor of `tool_choice`. Controls how the model responds to function calls. \"none\" means the model does not call a function, and responds to the end-user. \"auto\" means the model can pick between an end-user 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.", "oneOf": [ { "type": "string", "enum": [ "none", "auto" ], "description": "`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." }, { "type": "object", "description": "Specifying a particular function via `{\"name\": \"my_function\"}` forces the model to call that function.", "properties": { "name": { "type": "string", "description": "The name of the function to call." } }, "required": [ "name" ] } ] } } } ], "required": [ "messages" ] }, "chatCompletionResponseFormat": { "type": "string", "enum": [ "text", "json_object" ], "default": "text", "example": "json_object", "nullable": true, "description": "Setting to `json_object` enables JSON mode. This guarantees that the message the model generates is valid JSON.", "x-ms-enum": { "name": "ChatCompletionResponseFormat", "modelAsString": true, "values": [ { "value": "text", "description": "Response format is a plain text string." }, { "value": "json_object", "description": "Response format is a JSON object." } ] } }, "chatCompletionFunction": { "type": "object", "properties": { "name": { "type": "string", "description": "The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64." }, "description": { "type": "string", "description": "The description of what the function does." }, "parameters": { "$ref": "#/components/schemas/chatCompletionFunctionParameters" } }, "required": [ "name" ] }, "chatCompletionFunctionParameters": { "type": "object", "description": "The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/gpt/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format.", "additionalProperties": true }, "chatCompletionRequestMessage": { "type": "object", "properties": { "role": { "$ref": "#/components/schemas/chatCompletionRequestMessageRole" } }, "discriminator": { "propertyName": "role", "mapping": { "system": "#/components/schemas/chatCompletionRequestMessageSystem", "user": "#/components/schemas/chatCompletionRequestMessageUser", "assistant": "#/components/schemas/chatCompletionRequestMessageAssistant", "tool": "#/components/schemas/chatCompletionRequestMessageTool", "function": "#/components/schemas/chatCompletionRequestMessageFunction" } }, "required": [ "role" ] }, "chatCompletionRequestMessageRole": { "type": "string", "enum": [ "system", "user", "assistant", "tool", "function" ], "description": "The role of the messages author.", "x-ms-enum": { "name": "ChatCompletionRequestMessageRole", "modelAsString": true, "values": [ { "value": "system", "description": "The message author role is system." }, { "value": "user", "description": "The message author role is user." }, { "value": "assistant", "description": "The message author role is assistant." }, { "value": "tool", "description": "The message author role is tool." }, { "value": "function", "description": "Deprecated. The message author role is function." } ] } }, "chatCompletionRequestMessageSystem": { "allOf": [ { "$ref": "#/components/schemas/chatCompletionRequestMessage" }, { "type": "object", "properties": { "content": { "type": "string", "description": "The contents of the message.", "nullable": true } } } ], "required": [ "content" ] }, "chatCompletionRequestMessageUser": { "allOf": [ { "$ref": "#/components/schemas/chatCompletionRequestMessage" }, { "type": "object", "properties": { "content": { "oneOf": [ { "type": "string", "description": "The contents of the message." }, { "type": "array", "description": "An array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Image input is only supported when using the `gpt-4-visual-preview` model.", "minimum": 1, "items": { "$ref": "#/components/schemas/chatCompletionRequestMessageContentPart" } } ], "nullable": true } } } ], "required": [ "content" ] }, "chatCompletionRequestMessageContentPart": { "type": "object", "properties": { "type": { "$ref": "#/components/schemas/chatCompletionRequestMessageContentPartType" } }, "discriminator": { "propertyName": "type", "mapping": { "text": "#/components/schemas/chatCompletionRequestMessageContentPartText", "image_url": "#/components/schemas/chatCompletionRequestMessageContentPartImage" } }, "required": [ "type" ] }, "chatCompletionRequestMessageContentPartType": { "type": "string", "enum": [ "text", "image_url" ], "description": "The type of the content part.", "x-ms-enum": { "name": "ChatCompletionRequestMessageContentPartType", "modelAsString": true, "values": [ { "value": "text", "description": "The content part type is text." }, { "value": "image_url", "description": "The content part type is image_url." } ] } }, "chatCompletionRequestMessageContentPartText": { "allOf": [ { "$ref": "#/components/schemas/chatCompletionRequestMessageContentPart" }, { "type": "object", "properties": { "text": { "type": "string", "description": "The text content." } } } ], "required": [ "text" ] }, "chatCompletionRequestMessageContentPartImage": { "allOf": [ { "$ref": "#/components/schemas/chatCompletionRequestMessageContentPart" }, { "type": "object", "properties": { "url": { "type": "string", "description": "Either a URL of the image or the base64 encoded image data.", "format": "uri" }, "detail": { "$ref": "#/components/schemas/imageDetailLevel" } } } ], "required": [ "url" ] }, "imageDetailLevel": { "type": "string", "description": "Specifies the detail level of the image.", "enum": [ "auto", "low", "high" ], "default": "auto", "x-ms-enum": { "name": "ImageDetailLevel", "modelAsString": true, "values": [ { "value": "auto", "description": "The image detail level is auto." }, { "value": "low", "description": "The image detail level is low." }, { "value": "high", "description": "The image detail level is high." } ] } }, "chatCompletionRequestMessageAssistant": { "allOf": [ { "$ref": "#/components/schemas/chatCompletionRequestMessage" }, { "type": "object", "properties": { "content": { "type": "string", "description": "The contents of the message.", "nullable": true }, "tool_calls": { "type": "array", "description": "The tool calls generated by the model, such as function calls.", "items": { "$ref": "#/components/schemas/chatCompletionMessageToolCall" } }, "context": { "$ref": "#/components/schemas/azureChatExtensionsMessageContext" } } } ], "required": [ "content" ] }, "azureChatExtensionConfiguration": { "required": [ "type" ], "type": "object", "properties": { "type": { "$ref": "#/components/schemas/azureChatExtensionType" } }, "description": " A representation of configuration data for a single Azure OpenAI chat extension. This will be used by a chat\n completions request that should use Azure OpenAI chat extensions to augment the response behavior.\n The use of this configuration is compatible only with Azure OpenAI.", "discriminator": { "propertyName": "type", "mapping": { "azure_search": "#/components/schemas/azureSearchChatExtensionConfiguration", "azure_cosmos_db": "#/components/schemas/azureCosmosDBChatExtensionConfiguration" } } }, "azureChatExtensionType": { "type": "string", "description": " A representation of configuration data for a single Azure OpenAI chat extension. This will be used by a chat\n completions request that should use Azure OpenAI chat extensions to augment the response behavior.\n The use of this configuration is compatible only with Azure OpenAI.", "enum": [ "azure_search", "azure_cosmos_db" ], "x-ms-enum": { "name": "AzureChatExtensionType", "modelAsString": true, "values": [ { "name": "azureSearch", "value": "azure_search", "description": "Represents the use of Azure Search as an Azure OpenAI chat extension." }, { "name": "azureCosmosDB", "value": "azure_cosmos_db", "description": "Represents the use of Azure Cosmos DB as an Azure OpenAI chat extension." } ] } }, "azureSearchChatExtensionConfiguration": { "required": [ "parameters" ], "description": "A specific representation of configurable options for Azure Search when using it as an Azure OpenAI chat\nextension.", "allOf": [ { "$ref": "#/components/schemas/azureChatExtensionConfiguration" }, { "properties": { "parameters": { "$ref": "#/components/schemas/azureSearchChatExtensionParameters" } } } ], "x-ms-discriminator-value": "azure_search" }, "azureSearchChatExtensionParameters": { "required": [ "authentication", "endpoint", "index_name" ], "type": "object", "properties": { "authentication": { "oneOf": [ { "$ref": "#/components/schemas/onYourDataApiKeyAuthenticationOptions" }, { "$ref": "#/components/schemas/onYourDataSystemAssignedManagedIdentityAuthenticationOptions" }, { "$ref": "#/components/schemas/onYourDataUserAssignedManagedIdentityAuthenticationOptions" } ] }, "top_n_documents": { "type": "integer", "description": "The configured top number of documents to feature for the configured query.", "format": "int32" }, "in_scope": { "type": "boolean", "description": "Whether queries should be restricted to use of indexed data." }, "strictness": { "maximum": 5, "minimum": 1, "type": "integer", "description": "The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.", "format": "int32" }, "role_information": { "type": "string", "description": "Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit." }, "endpoint": { "type": "string", "description": "The absolute endpoint path for the Azure Search resource to use.", "format": "uri" }, "index_name": { "type": "string", "description": "The name of the index to use as available in the referenced Azure Search resource." }, "fields_mapping": { "$ref": "#/components/schemas/azureSearchIndexFieldMappingOptions" }, "query_type": { "$ref": "#/components/schemas/azureSearchQueryType" }, "semantic_configuration": { "type": "string", "description": "The additional semantic configuration for the query." }, "filter": { "type": "string", "description": "Search filter." }, "embedding_dependency": { "oneOf": [ { "$ref": "#/components/schemas/onYourDataEndpointVectorizationSource" }, { "$ref": "#/components/schemas/onYourDataDeploymentNameVectorizationSource" } ] } }, "description": "Parameters for Azure Search when used as an Azure OpenAI chat extension." }, "azureSearchIndexFieldMappingOptions": { "type": "object", "properties": { "title_field": { "type": "string", "description": "The name of the index field to use as a title." }, "url_field": { "type": "string", "description": "The name of the index field to use as a URL." }, "filepath_field": { "type": "string", "description": "The name of the index field to use as a filepath." }, "content_fields": { "type": "array", "description": "The names of index fields that should be treated as content.", "items": { "type": "string" } }, "content_fields_separator": { "type": "string", "description": "The separator pattern that content fields should use." }, "vector_fields": { "type": "array", "description": "The names of fields that represent vector data.", "items": { "type": "string" } } }, "description": "Optional settings to control how fields are processed when using a configured Azure Search resource." }, "azureSearchQueryType": { "type": "string", "description": "The type of Azure Search retrieval query that should be executed when using it as an Azure OpenAI chat extension.", "enum": [ "simple", "semantic", "vector", "vector_simple_hybrid", "vector_semantic_hybrid" ], "x-ms-enum": { "name": "azureSearchQueryType", "modelAsString": true, "values": [ { "name": "simple", "value": "simple", "description": "Represents the default, simple query parser." }, { "name": "semantic", "value": "semantic", "description": "Represents the semantic query parser for advanced semantic modeling." }, { "name": "vector", "value": "vector", "description": "Represents vector search over computed data." }, { "name": "vectorSimpleHybrid", "value": "vector_simple_hybrid", "description": "Represents a combination of the simple query strategy with vector data." }, { "name": "vectorSemanticHybrid", "value": "vector_semantic_hybrid", "description": "Represents a combination of semantic search and vector data querying." } ] } }, "azureCosmosDBChatExtensionConfiguration": { "required": [ "parameters" ], "description": "A specific representation of configurable options for Azure Cosmos DB when using it as an Azure OpenAI chat\nextension.", "allOf": [ { "$ref": "#/components/schemas/azureChatExtensionConfiguration" }, { "properties": { "parameters": { "$ref": "#/components/schemas/azureCosmosDBChatExtensionParameters" } } } ], "x-ms-discriminator-value": "azure_cosmos_db" }, "azureCosmosDBChatExtensionParameters": { "required": [ "authentication", "container_name", "database_name", "embedding_dependency", "fields_mapping", "index_name" ], "type": "object", "properties": { "authentication": { "$ref": "#/components/schemas/onYourDataConnectionStringAuthenticationOptions" }, "top_n_documents": { "type": "integer", "description": "The configured top number of documents to feature for the configured query.", "format": "int32" }, "in_scope": { "type": "boolean", "description": "Whether queries should be restricted to use of indexed data." }, "strictness": { "maximum": 5, "minimum": 1, "type": "integer", "description": "The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.", "format": "int32" }, "role_information": { "type": "string", "description": "Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit." }, "database_name": { "type": "string", "description": "The MongoDB vCore database name to use with Azure Cosmos DB." }, "container_name": { "type": "string", "description": "The name of the Azure Cosmos DB resource container." }, "index_name": { "type": "string", "description": "The MongoDB vCore index name to use with Azure Cosmos DB." }, "fields_mapping": { "$ref": "#/components/schemas/azureCosmosDBFieldMappingOptions" }, "embedding_dependency": { "oneOf": [ { "$ref": "#/components/schemas/onYourDataEndpointVectorizationSource" }, { "$ref": "#/components/schemas/onYourDataDeploymentNameVectorizationSource" } ] } }, "description": "Parameters to use when configuring Azure OpenAI On Your Data chat extensions when using Azure Cosmos DB for\nMongoDB vCore." }, "azureCosmosDBFieldMappingOptions": { "required": [ "content_fields", "vector_fields" ], "type": "object", "properties": { "title_field": { "type": "string", "description": "The name of the index field to use as a title." }, "url_field": { "type": "string", "description": "The name of the index field to use as a URL." }, "filepath_field": { "type": "string", "description": "The name of the index field to use as a filepath." }, "content_fields": { "type": "array", "description": "The names of index fields that should be treated as content.", "items": { "type": "string" } }, "content_fields_separator": { "type": "string", "description": "The separator pattern that content fields should use." }, "vector_fields": { "type": "array", "description": "The names of fields that represent vector data.", "items": { "type": "string" } } }, "description": "Optional settings to control how fields are processed when using a configured Azure Cosmos DB resource." }, "onYourDataAuthenticationOptions": { "required": [ "type" ], "type": "object", "properties": { "type": { "$ref": "#/components/schemas/onYourDataAuthenticationType" } }, "description": "The authentication options for Azure OpenAI On Your Data.", "discriminator": { "propertyName": "type", "mapping": { "api_key": "#/components/schemas/onYourDataApiKeyAuthenticationOptions", "connection_string": "#/components/schemas/onYourDataConnectionStringAuthenticationOptions", "system_assigned_managed_identity": "#/components/schemas/onYourDataSystemAssignedManagedIdentityAuthenticationOptions", "user_assigned_managed_identity": "#/components/schemas/onYourDataUserAssignedManagedIdentityAuthenticationOptions" } } }, "onYourDataAuthenticationType": { "type": "string", "description": "The authentication types supported with Azure OpenAI On Your Data.", "enum": [ "api_key", "connection_string", "system_assigned_managed_identity", "user_assigned_managed_identity" ], "x-ms-enum": { "name": "OnYourDataAuthenticationType", "modelAsString": true, "values": [ { "name": "apiKey", "value": "api_key", "description": "Authentication via API key." }, { "name": "connectionString", "value": "connection_string", "description": "Authentication via connection string." }, { "name": "systemAssignedManagedIdentity", "value": "system_assigned_managed_identity", "description": "Authentication via system-assigned managed identity." }, { "name": "userAssignedManagedIdentity", "value": "user_assigned_managed_identity", "description": "Authentication via user-assigned managed identity." } ] } }, "onYourDataApiKeyAuthenticationOptions": { "required": [ "key" ], "description": "The authentication options for Azure OpenAI On Your Data when using an API key.", "allOf": [ { "$ref": "#/components/schemas/onYourDataAuthenticationOptions" }, { "properties": { "key": { "type": "string", "description": "The API key to use for authentication." } } } ], "x-ms-discriminator-value": "api_key" }, "onYourDataConnectionStringAuthenticationOptions": { "required": [ "connection_string" ], "description": "The authentication options for Azure OpenAI On Your Data when using a connection string.", "allOf": [ { "$ref": "#/components/schemas/onYourDataAuthenticationOptions" }, { "properties": { "connection_string": { "type": "string", "description": "The connection string to use for authentication." } } } ], "x-ms-discriminator-value": "connection_string" }, "onYourDataSystemAssignedManagedIdentityAuthenticationOptions": { "description": "The authentication options for Azure OpenAI On Your Data when using a system-assigned managed identity.", "allOf": [ { "$ref": "#/components/schemas/onYourDataAuthenticationOptions" } ], "x-ms-discriminator-value": "system_assigned_managed_identity" }, "onYourDataUserAssignedManagedIdentityAuthenticationOptions": { "required": [ "managed_identity_resource_id" ], "description": "The authentication options for Azure OpenAI On Your Data when using a user-assigned managed identity.", "allOf": [ { "$ref": "#/components/schemas/onYourDataAuthenticationOptions" }, { "properties": { "managed_identity_resource_id": { "type": "string", "description": "The resource ID of the user-assigned managed identity to use for authentication." } } } ], "x-ms-discriminator-value": "user_assigned_managed_identity" }, "onYourDataVectorizationSource": { "required": [ "type" ], "type": "object", "properties": { "type": { "$ref": "#/components/schemas/onYourDataVectorizationSourceType" } }, "description": "An abstract representation of a vectorization source for Azure OpenAI On Your Data with vector search.", "discriminator": { "propertyName": "type", "mapping": { "endpoint": "#/components/schemas/onYourDataEndpointVectorizationSource", "deployment_name": "#/components/schemas/onYourDataDeploymentNameVectorizationSource" } } }, "onYourDataVectorizationSourceType": { "type": "string", "description": "Represents the available sources Azure OpenAI On Your Data can use to configure vectorization of data for use with\nvector search.", "enum": [ "endpoint", "deployment_name" ], "x-ms-enum": { "name": "OnYourDataVectorizationSourceType", "modelAsString": true, "values": [ { "name": "endpoint", "value": "endpoint", "description": "Represents vectorization performed by public service calls to an Azure OpenAI embedding model." }, { "name": "deploymentName", "value": "deployment_name", "description": "Represents an Ada model deployment name to use. This model deployment must be in the same Azure OpenAI resource, but\nOn Your Data will use this model deployment via an internal call rather than a public one, which enables vector\nsearch even in private networks." } ] } }, "onYourDataDeploymentNameVectorizationSource": { "required": [ "deployment_name" ], "description": "The details of a a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based\non an internal embeddings model deployment name in the same Azure OpenAI resource.", "allOf": [ { "$ref": "#/components/schemas/onYourDataVectorizationSource" }, { "properties": { "deployment_name": { "type": "string", "description": "Specifies the name of the model deployment to use for vectorization. This model deployment must be in the same Azure OpenAI resource, but On Your Data will use this model deployment via an internal call rather than a public one, which enables vector search even in private networks." } } } ], "x-ms-discriminator-value": "deployment_name" }, "onYourDataEndpointVectorizationSource": { "required": [ "authentication", "endpoint" ], "description": "The details of a a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based\non a public Azure OpenAI endpoint call for embeddings.", "allOf": [ { "$ref": "#/components/schemas/onYourDataVectorizationSource" }, { "properties": { "authentication": { "$ref": "#/components/schemas/onYourDataApiKeyAuthenticationOptions" }, "endpoint": { "type": "string", "description": "Specifies the endpoint to use for vectorization. This endpoint must be in the same Azure OpenAI resource, but On Your Data will use this endpoint via an internal call rather than a public one, which enables vector search even in private networks.", "format": "uri" } } } ], "x-ms-discriminator-value": "endpoint" }, "azureChatExtensionsMessageContext": { "type": "object", "properties": { "citations": { "type": "array", "description": "The data source retrieval result, used to generate the assistant message in the response.", "items": { "$ref": "#/components/schemas/citation" }, "x-ms-identifiers": [] }, "intent": { "type": "string", "description": "The detected intent from the chat history, used to pass to the next turn to carry over the context." } }, "description": " A representation of the additional context information available when Azure OpenAI chat extensions are involved\n in the generation of a corresponding chat completions response. This context information is only populated when\n using an Azure OpenAI request configured to use a matching extension." }, "citation": { "required": [ "content" ], "type": "object", "properties": { "content": { "type": "string", "description": "The content of the citation." }, "title": { "type": "string", "description": "The title of the citation." }, "url": { "type": "string", "description": "The URL of the citation." }, "filepath": { "type": "string", "description": "The file path of the citation." }, "chunk_id": { "type": "string", "description": "The chunk ID of the citation." } }, "description": "citation information for a chat completions response message." }, "chatCompletionMessageToolCall": { "type": "object", "properties": { "id": { "type": "string", "description": "The ID of the tool call." }, "type": { "$ref": "#/components/schemas/toolCallType" }, "function": { "type": "object", "description": "The function that the model called.", "properties": { "name": { "type": "string", "description": "The name of the function to call." }, "arguments": { "type": "string", "description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function." } }, "required": [ "name", "arguments" ] } }, "required": [ "id", "type", "function" ] }, "toolCallType": { "type": "string", "enum": [ "function" ], "description": "The type of the tool call, in this case `function`.", "x-ms-enum": { "name": "ToolCallType", "modelAsString": true, "values": [ { "value": "function", "description": "The tool call type is function." } ] } }, "chatCompletionRequestMessageTool": { "allOf": [ { "$ref": "#/components/schemas/chatCompletionRequestMessage" }, { "type": "object", "nullable": true, "properties": { "tool_call_id": { "type": "string", "description": "Tool call that this message is responding to." }, "content": { "type": "string", "description": "The contents of the message.", "nullable": true } } } ], "required": [ "tool_call_id", "content" ] }, "chatCompletionRequestMessageFunction": { "allOf": [ { "$ref": "#/components/schemas/chatCompletionRequestMessage" }, { "type": "object", "description": "Deprecated. Message that represents a function.", "nullable": true, "properties": { "role": { "type": "string", "enum": [ "function" ], "description": "The role of the messages author, in this case `function`." }, "name": { "type": "string", "description": "The contents of the message." }, "content": { "type": "string", "description": "The contents of the message.", "nullable": true } } } ], "required": [ "function_call_id", "content" ] }, "createChatCompletionResponse": { "type": "object", "allOf": [ { "$ref": "#/components/schemas/chatCompletionsResponseCommon" }, { "properties": { "prompt_filter_results": { "$ref": "#/components/schemas/promptFilterResults" }, "choices": { "type": "array", "items": { "type": "object", "allOf": [ { "$ref": "#/components/schemas/chatCompletionChoiceCommon" }, { "properties": { "message": { "$ref": "#/components/schemas/chatCompletionResponseMessage" }, "content_filter_results": { "$ref": "#/components/schemas/contentFilterChoiceResults" } } } ] } } } } ], "required": [ "id", "object", "created", "model", "choices" ] }, "chatCompletionResponseMessage": { "type": "object", "description": "A chat completion message generated by the model.", "properties": { "role": { "$ref": "#/components/schemas/chatCompletionResponseMessageRole" }, "content": { "type": "string", "description": "The contents of the message.", "nullable": true }, "tool_calls": { "type": "array", "description": "The tool calls generated by the model, such as function calls.", "items": { "$ref": "#/components/schemas/chatCompletionMessageToolCall" } }, "function_call": { "$ref": "#/components/schemas/chatCompletionFunctionCall" }, "context": { "$ref": "#/components/schemas/azureChatExtensionsMessageContext" } } }, "chatCompletionResponseMessageRole": { "type": "string", "enum": [ "assistant" ], "description": "The role of the author of the response message." }, "chatCompletionToolChoiceOption": { "description": "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 `{\"type\": \"function\", \"function\": {\"name\": \"my_function\"}}` forces the model to call that function.", "oneOf": [ { "type": "string", "description": "`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.", "enum": [ "none", "auto" ] }, { "$ref": "#/components/schemas/chatCompletionNamedToolChoice" } ] }, "chatCompletionNamedToolChoice": { "type": "object", "description": "Specifies a tool the model should use. Use to force the model to call a specific function.", "properties": { "type": { "type": "string", "enum": [ "function" ], "description": "The type of the tool. Currently, only `function` is supported." }, "function": { "type": "object", "properties": { "name": { "type": "string", "description": "The name of the function to call." } }, "required": [ "name" ] } } }, "chatCompletionFunctionCall": { "type": "object", "description": "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model.", "properties": { "name": { "type": "string", "description": "The name of the function to call." }, "arguments": { "type": "string", "description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function." } }, "required": [ "name", "arguments" ] }, "chatCompletionsResponseCommon": { "type": "object", "properties": { "id": { "type": "string", "description": "A unique identifier for the chat completion." }, "object": { "$ref": "#/components/schemas/chatCompletionResponseObject" }, "created": { "type": "integer", "format": "unixtime", "description": "The Unix timestamp (in seconds) of when the chat completion was created." }, "model": { "type": "string", "description": "The model used for the chat completion." }, "usage": { "$ref": "#/components/schemas/completionUsage" }, "system_fingerprint": { "type": "string", "description": "Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism." } }, "required": [ "id", "object", "created", "model" ] }, "chatCompletionResponseObject": { "type": "string", "description": "The object type.", "enum": [ "chat.completion" ], "x-ms-enum": { "name": "ChatCompletionResponseObject", "modelAsString": true, "values": [ { "value": "chat.completion", "description": "The object type is chat completion." } ] } }, "completionUsage": { "type": "object", "description": "Usage statistics for the completion request.", "properties": { "prompt_tokens": { "type": "integer", "description": "Number of tokens in the prompt." }, "completion_tokens": { "type": "integer", "description": "Number of tokens in the generated completion." }, "total_tokens": { "type": "integer", "description": "Total number of tokens used in the request (prompt + completion)." } }, "required": [ "prompt_tokens", "completion_tokens", "total_tokens" ] }, "chatCompletionTool": { "type": "object", "properties": { "type": { "$ref": "#/components/schemas/chatCompletionToolType" }, "function": { "type": "object", "properties": { "description": { "type": "string", "description": "A description of what the function does, used by the model to choose when and how to call the function." }, "name": { "type": "string", "description": "The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64." }, "parameters": { "$ref": "#/components/schemas/chatCompletionFunctionParameters" } }, "required": [ "name", "parameters" ] } }, "required": [ "type", "function" ] }, "chatCompletionToolType": { "type": "string", "enum": [ "function" ], "description": "The type of the tool. Currently, only `function` is supported.", "x-ms-enum": { "name": "ChatCompletionToolType", "modelAsString": true, "values": [ { "value": "function", "description": "The tool type is function." } ] } }, "chatCompletionChoiceCommon": { "type": "object", "properties": { "index": { "type": "integer" }, "finish_reason": { "type": "string" } } }, "createTranslationRequest": { "type": "object", "description": "Translation request.", "properties": { "file": { "type": "string", "description": "The audio file to translate.", "format": "binary" }, "prompt": { "type": "string", "description": "An optional text to guide the model's style or continue a previous audio segment. The prompt should be in English." }, "response_format": { "$ref": "#/components/schemas/audioResponseFormat" }, "temperature": { "type": "number", "default": 0, "description": "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit." } }, "required": [ "file" ] }, "audioResponse": { "description": "Translation or transcription response when response_format was json", "type": "object", "properties": { "text": { "type": "string", "description": "Translated or transcribed text." } }, "required": [ "text" ] }, "audioVerboseResponse": { "description": "Translation or transcription response when response_format was verbose_json", "type": "object", "allOf": [ { "$ref": "#/components/schemas/audioResponse" }, { "properties": { "task": { "type": "string", "description": "Type of audio task.", "enum": [ "transcribe", "translate" ], "x-ms-enum": { "modelAsString": true } }, "language": { "type": "string", "description": "Language." }, "duration": { "type": "number", "description": "Duration." }, "segments": { "type": "array", "items": { "$ref": "#/components/schemas/audioSegment" } } } } ], "required": [ "text" ] }, "audioResponseFormat": { "title": "AudioResponseFormat", "description": "Defines the format of the output.", "enum": [ "json", "text", "srt", "verbose_json", "vtt" ], "type": "string", "x-ms-enum": { "modelAsString": true } }, "createTranscriptionRequest": { "type": "object", "description": "Transcription request.", "properties": { "file": { "type": "string", "description": "The audio file object to transcribe.", "format": "binary" }, "prompt": { "type": "string", "description": "An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language." }, "response_format": { "$ref": "#/components/schemas/audioResponseFormat" }, "temperature": { "type": "number", "default": 0, "description": "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit." }, "language": { "type": "string", "description": "The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency." } }, "required": [ "file" ] }, "audioSegment": { "type": "object", "description": "Transcription or translation segment.", "properties": { "id": { "type": "integer", "description": "Segment identifier." }, "seek": { "type": "number", "description": "Offset of the segment." }, "start": { "type": "number", "description": "Segment start offset." }, "end": { "type": "number", "description": "Segment end offset." }, "text": { "type": "string", "description": "Segment text." }, "tokens": { "type": "array", "items": { "type": "number", "nullable": false }, "description": "Tokens of the text." }, "temperature": { "type": "number", "description": "Temperature." }, "avg_logprob": { "type": "number", "description": "Average log probability." }, "compression_ratio": { "type": "number", "description": "Compression ratio." }, "no_speech_prob": { "type": "number", "description": "Probability of 'no speech'." } } }, "imageQuality": { "description": "The quality of the image that will be generated.", "type": "string", "enum": [ "standard", "hd" ], "default": "standard", "x-ms-enum": { "name": "Quality", "modelAsString": true, "values": [ { "value": "standard", "description": "Standard quality creates images with standard quality.", "name": "Standard" }, { "value": "hd", "description": "HD quality creates images with finer details and greater consistency across the image.", "name": "HD" } ] } }, "imagesResponseFormat": { "description": "The format in which the generated images are returned.", "type": "string", "enum": [ "url", "b64_json" ], "default": "url", "x-ms-enum": { "name": "ImagesResponseFormat", "modelAsString": true, "values": [ { "value": "url", "description": "The URL that provides temporary access to download the generated images.", "name": "Url" }, { "value": "b64_json", "description": "The generated images are returned as base64 encoded string.", "name": "Base64Json" } ] } }, "imageSize": { "description": "The size of the generated images.", "type": "string", "enum": [ "1792x1024", "1024x1792", "1024x1024" ], "default": "1024x1024", "x-ms-enum": { "name": "Size", "modelAsString": true, "values": [ { "value": "1792x1024", "description": "The desired size of the generated image is 1792x1024 pixels.", "name": "Size1792x1024" }, { "value": "1024x1792", "description": "The desired size of the generated image is 1024x1792 pixels.", "name": "Size1024x1792" }, { "value": "1024x1024", "description": "The desired size of the generated image is 1024x1024 pixels.", "name": "Size1024x1024" } ] } }, "imageStyle": { "description": "The style of the generated images.", "type": "string", "enum": [ "vivid", "natural" ], "default": "vivid", "x-ms-enum": { "name": "Style", "modelAsString": true, "values": [ { "value": "vivid", "description": "Vivid creates images that are hyper-realistic and dramatic.", "name": "Vivid" }, { "value": "natural", "description": "Natural creates images that are more natural and less hyper-realistic.", "name": "Natural" } ] } }, "imageGenerationsRequest": { "type": "object", "properties": { "prompt": { "description": "A text description of the desired image(s). The maximum length is 4000 characters.", "type": "string", "format": "string", "example": "a corgi in a field", "minLength": 1 }, "n": { "description": "The number of images to generate.", "type": "integer", "minimum": 1, "maximum": 1, "default": 1 }, "size": { "$ref": "#/components/schemas/imageSize" }, "response_format": { "$ref": "#/components/schemas/imagesResponseFormat" }, "user": { "description": "A unique identifier representing your end-user, which can help to monitor and detect abuse.", "type": "string", "format": "string", "example": "user123456" }, "quality": { "$ref": "#/components/schemas/imageQuality" }, "style": { "$ref": "#/components/schemas/imageStyle" } }, "required": [ "prompt" ] }, "generateImagesResponse": { "type": "object", "properties": { "created": { "type": "integer", "format": "unixtime", "description": "The unix timestamp when the operation was created.", "example": "1676540381" }, "data": { "type": "array", "description": "The result data of the operation, if successful", "items": { "$ref": "#/components/schemas/imageResult" } } }, "required": [ "created", "data" ] }, "imageResult": { "type": "object", "description": "The image url or encoded image if successful, and an error otherwise.", "properties": { "url": { "type": "string", "description": "The image url.", "example": "https://www.contoso.com" }, "b64_json": { "type": "string", "description": "The base64 encoded image" }, "content_filter_results": { "$ref": "#/components/schemas/dalleContentFilterResults" }, "revised_prompt": { "type": "string", "description": "The prompt that was used to generate the image, if there was any revision to the prompt." }, "prompt_filter_results": { "$ref": "#/components/schemas/dalleFilterResults" } } } }, "securitySchemes": { "bearer": { "type": "oauth2", "flows": { "implicit": { "authorizationUrl": "https://login.microsoftonline.com/common/oauth2/v2.0/authorize", "scopes": {} } }, "x-tokenInfoFunc": "api.middleware.auth.bearer_auth", "x-scopeValidateFunc": "api.middleware.auth.validate_scopes" }, "apiKey": { "type": "apiKey", "name": "api-key", "in": "header" } } } }