Ballerina library

azure.openai.chat

Module azure.openai.chat

OverviewSetup guideQuickstartExamples

API

Client

Definitions

ApiKeysConfig
AzureContentFilterBlocklistResult
AzureContentFilterBlocklistResultDetails
AzureContentFilterCompletionTextSpan
AzureContentFilterCompletionTextSpanDetectionResult
AzureContentFilterCustomTopicResult
AzureContentFilterCustomTopicResultDetails
AzureContentFilterDetectionResult
AzureContentFilterResultForChoice
AzureContentFilterResultForChoiceError
AzureContentFilterResultForChoiceProtectedMaterialCode
AzureContentFilterResultForChoiceProtectedMaterialCodeCitation
AzureContentFilterResultForPrompt
AzureContentFilterResultForPromptContentFilterResults
AzureContentFilterSeverityResult
AzureUserSecurityContext
ChatCompletionsBody
ConnectionConfig
CreateChatCompletionQueries
InlineResponse200PromptFilterResults
OpenAIChatCompletionAllowedTools
OpenAIChatCompletionAllowedToolsChoice
OpenAIChatCompletionFunctionCallOption
OpenAIChatCompletionFunctions
OpenAIChatCompletionMessageCustomToolCall
OpenAIChatCompletionMessageCustomToolCallCustom
OpenAIChatCompletionMessageToolCall
OpenAIChatCompletionMessageToolCallChunk
OpenAIChatCompletionMessageToolCallChunkFunction
OpenAIChatCompletionMessageToolCallFunction
OpenAIChatCompletionNamedToolChoice
OpenAIChatCompletionNamedToolChoiceCustom
OpenAIChatCompletionNamedToolChoiceCustomCustom
OpenAIChatCompletionNamedToolChoiceFunction
OpenAIChatCompletionRequestMessage
OpenAIChatCompletionRequestMessageContentPartText
OpenAIChatCompletionResponseMessage
OpenAIChatCompletionResponseMessageAnnotations
OpenAIChatCompletionResponseMessageAnnotationsUrlCitation
OpenAIChatCompletionResponseMessageAudio
OpenAIChatCompletionResponseMessageFunctionCall
OpenAIChatCompletionStreamOptions
OpenAIChatCompletionStreamResponseDelta
OpenAIChatCompletionStreamResponseDeltaFunctionCall
OpenAIChatCompletionTokenLogprob
OpenAIChatCompletionTokenLogprobTopLogprobs
OpenAIChatCompletionTool
OpenAICompletionUsage
OpenAICompletionUsageCompletionTokensDetails
OpenAICompletionUsagePromptTokensDetails
OpenAICreateChatCompletionRequestAudio
OpenAICreateChatCompletionRequestResponseFormat
OpenAICreateChatCompletionResponseChoices
OpenAICreateChatCompletionResponseChoicesLogprobs
OpenAICreateChatCompletionStreamResponseChoices
OpenAICreateChatCompletionStreamResponseChoicesLogprobs
OpenAICustomToolChatCompletions
OpenAICustomToolChatCompletionsCustom
OpenAICustomToolChatCompletionsCustomFormatGrammar
OpenAICustomToolChatCompletionsCustomFormatGrammarGrammar
OpenAICustomToolChatCompletionsCustomFormatText
OpenAIFunctionObject
OpenAIFunctionParameters
OpenAIMetadata
OpenAIPredictionContent

AzureAIFoundryModelsApiVersion
OpenAIStopConfiguration
OpenAIReasoningEffort
OpenAIVerbosity
OpenAIVoiceIdsOrCustomVoice
InlineResponse200
OpenAICreateChatCompletionRequestResponseFormatType
OpenAIChatCompletionToolChoiceOption
OpenAIVoiceIdsShared
OpenAIChatCompletionRequestMessageType

OpenAIResponseModalities
OpenAIChatCompletionMessageToolCallsItem

AzureContentFilterPersonallyIdentifiableInformationResult

ballerinax/azure.openai.chat Ballerina library

4.0.0
Ballerina Azure OpenAI Chat Completions connector

Build GitHub Last Commit GitHub Issues

Overview

Azure OpenAI provides access to OpenAI's powerful language models including GPT-4o, GPT-4, and o-series models through Microsoft Azure's enterprise-grade infrastructure. It combines OpenAI's advanced AI capabilities with Azure's security, compliance, and regional availability features.

The ballerinax/azure.openai.chat package offers functionality to connect and interact with the Chat Completions API of the Azure AI Foundry Models Service. The Chat Completions API enables you to build conversational AI applications with features like multi-turn conversations, function/tool calling, structured outputs, and vision capabilities.

Setup guide

To use the Azure OpenAI Chat Completions Connector, you must have access to an Azure OpenAI resource through a Microsoft Azure account. If you do not have an Azure account, you can sign up for one here.

Create an Azure OpenAI resource and obtain the API key

  1. Sign in to the Azure Portal.

  2. Search for "Azure OpenAI" in the top search bar and select Azure OpenAI from the results.

  3. Click Create to create a new Azure OpenAI resource. Fill in the required details such as subscription, resource group, region, and resource name, then click Review + create and finally Create.

  4. Once the resource is deployed, navigate to your Azure OpenAI resource.

  5. In the left-hand menu, go to Resource Management -> Keys and Endpoint.

  6. Copy one of the provided keys (Key 1 or Key 2) and the endpoint URL. Store them securely to use in your application.

  7. Append /openai/v1 to the endpoint URL. The portal shows the resource root (for example https://<resource-name>.openai.azure.com/), while this connector targets the v1 API surface, so the value to pass as serviceUrl is https://<resource-name>.openai.azure.com/openai/v1. Resources provisioned through Azure AI Foundry may instead show https://<resource-name>.services.ai.azure.com/, which becomes https://<resource-name>.services.ai.azure.com/openai/v1.

Quickstart

To use the Azure OpenAI Chat Completions connector in your Ballerina application, update the .bal file as follows:

Step 1: Import the module

Import the ballerinax/azure.openai.chat module.

Copy
import ballerinax/azure.openai.chat;

Step 2: Create a new connector instance

Create a chat:Client with your Azure OpenAI resource endpoint and one credential. Azure accepts either an API key or a Microsoft Entra ID access token, and the two are alternatives — provide whichever you have, not both.

serviceUrl must be the endpoint including the /openai/v1 base path, as described in step 7 of the setup guide — https://<resource-name>.openai.azure.com/openai/v1. Passing the bare resource root makes every request return 404.

Using the API key obtained in the setup guide:

Copy
configurable string apiKey = ?;
configurable string serviceUrl = ?;

final chat:Client azureOpenAIChat = check new ({
    auth: {
        api\-key: apiKey
    }
}, serviceUrl);

Alternatively, using a Microsoft Entra ID access token, which is sent as an Authorization: Bearer header:

Copy
configurable string token = ?;
configurable string serviceUrl = ?;

final chat:Client azureOpenAIChat = check new ({
    auth: {
        token
    }
}, serviceUrl);

Step 3: Invoke the connector operation

Now, you can utilize available connector operations.

Create a chat completion

Copy
public function main() returns error? {

    chat:ChatCompletionsBody request = {
        model: "gpt-4o-mini",
        messages: [
            {role: "user", "content": "What is the Ballerina programming language?"}
        ]
    };

    chat:InlineResponse200 response = check azureOpenAIChat->/chat/completions.post(request);
}

Step 4: Run the Ballerina application

Copy
bal run

Examples

The Azure OpenAI Chat Completions connector provides practical examples illustrating usage in various scenarios. Explore these examples, covering the following use cases:

  1. Chat completion - Create a basic chat completion using the Azure OpenAI Chat Completions API.
  2. Function calling - Use function/tool calling to extend the model's capabilities with custom functions.

Clients

azure.openai.chat: Client

Isolated

Constructor

Gets invoked to initialize the connector.

init (ConnectionConfig config, string serviceUrl)
  • config ConnectionConfig - The configurations to be used when initializing the connector
  • serviceUrl string - URL of the target service

post chat/completions

Isolated FunctionResource Function
function post chat/completions(ChatCompletionsBody payload, map<string|string[]> headers, *CreateChatCompletionQueries queries) returns InlineResponse200|error

Creates a chat completion.

Parameters
  • headers map<string|string[]> (default {}) - Headers to be sent with the request
Return Type

Records

azure.openai.chat: ApiKeysConfig

Closed record

Provides API key configurations needed when communicating with a remote HTTP endpoint.

Fields

azure.openai.chat: AzureContentFilterBlocklistResult

A collection of true/false filtering results for configured custom blocklists.

Fields
  • filtered boolean - A value indicating whether any of the detailed blocklists resulted in a filtering action.

azure.openai.chat: AzureContentFilterBlocklistResultDetails

Fields
  • filtered boolean - A value indicating whether the blocklist produced a filtering action.
  • id string - The ID of the custom blocklist evaluated.

azure.openai.chat: AzureContentFilterCompletionTextSpan

A representation of a span of completion text as used by Azure OpenAI content filter results.

Fields
  • completion_start_offset Signed32 - Offset of the UTF32 code point which begins the span.
  • completion_end_offset Signed32 - Offset of the first UTF32 code point which is excluded from the span. This field is always equal to completion_start_offset for empty spans. This field is always larger than completion_start_offset for non-empty spans.

azure.openai.chat: AzureContentFilterCompletionTextSpanDetectionResult

Fields
  • filtered boolean - Whether the content detection resulted in a content filtering action.
  • detected boolean - Whether the labeled content category was detected in the content.

azure.openai.chat: AzureContentFilterCustomTopicResult

A collection of true/false filtering results for configured custom topics.

Fields
  • filtered boolean - A value indicating whether any of the detailed topics resulted in a filtering action.

azure.openai.chat: AzureContentFilterCustomTopicResultDetails

Fields
  • detected boolean - A value indicating whether the topic is detected.
  • id string - The ID of the custom topic evaluated.

azure.openai.chat: AzureContentFilterDetectionResult

A labeled content filter result item that indicates whether the content was detected and whether the content was filtered.

Fields
  • filtered boolean - Whether the content detection resulted in a content filtering action.
  • detected boolean - Whether the labeled content category was detected in the content.

azure.openai.chat: AzureContentFilterResultForChoice

A content filter result for a single response item produced by a generative AI system.

Fields
  • sexual? AzureContentFilterSeverityResult - A content filter category for language related to anatomical organs and genitals, romantic relationships, acts portrayed in erotic or affectionate terms, pregnancy, physical sexual acts, including those portrayed as an assault or a forced sexual violent act against one's will, prostitution, pornography, and abuse.
  • hate? AzureContentFilterSeverityResult - A content filter category that can refer to any content that attacks or uses pejorative or discriminatory language with reference to a person or identity group based on certain differentiating attributes of these groups including but not limited to race, ethnicity, nationality, gender identity and expression, sexual orientation, religion, immigration status, ability status, personal appearance, and body size.
  • violence? AzureContentFilterSeverityResult - A content filter category for language related to physical actions intended to hurt, injure, damage, or kill someone or something; describes weapons, guns and related entities, such as manufactures, associations, legislation, and so on.
  • self_harm? AzureContentFilterSeverityResult - A content filter category that describes language related to physical actions intended to purposely hurt, injure, damage one's body or kill oneself.

azure.openai.chat: AzureContentFilterResultForChoiceError

If present, details about an error that prevented content filtering from completing its evaluation.

Fields
  • code Signed32 - A distinct, machine-readable code associated with the error.
  • message string - A human-readable message associated with the error.

azure.openai.chat: AzureContentFilterResultForChoiceProtectedMaterialCode

A detection result that describes a match against licensed code or other protected source material.

Fields
  • filtered boolean - Whether the content detection resulted in a content filtering action.
  • detected boolean - Whether the labeled content category was detected in the content.

azure.openai.chat: AzureContentFilterResultForChoiceProtectedMaterialCodeCitation

If available, the citation details describing the associated license and its location.

Fields
  • license? string - The name or identifier of the license associated with the detection.
  • URL? string - The URL associated with the license.

azure.openai.chat: AzureContentFilterResultForPrompt

A content filter result associated with a single input prompt item into a generative AI system.

Fields
  • prompt_index? Signed32 - The index of the input prompt associated with the accompanying content filter result categories.

azure.openai.chat: AzureContentFilterResultForPromptContentFilterResults

The content filter category details for the result.

Fields
  • sexual? AzureContentFilterSeverityResult - A content filter category for language related to anatomical organs and genitals, romantic relationships, acts portrayed in erotic or affectionate terms, pregnancy, physical sexual acts, including those portrayed as an assault or a forced sexual violent act against one's will, prostitution, pornography, and abuse.
  • hate? AzureContentFilterSeverityResult - A content filter category that can refer to any content that attacks or uses pejorative or discriminatory language with reference to a person or identity group based on certain differentiating attributes of these groups including but not limited to race, ethnicity, nationality, gender identity and expression, sexual orientation, religion, immigration status, ability status, personal appearance, and body size.
  • violence? AzureContentFilterSeverityResult - A content filter category for language related to physical actions intended to hurt, injure, damage, or kill someone or something; describes weapons, guns and related entities, such as manufactures, associations, legislation, and so on.
  • self_harm? AzureContentFilterSeverityResult - A content filter category that describes language related to physical actions intended to purposely hurt, injure, damage one's body or kill oneself.
  • jailbreak AzureContentFilterDetectionResult - A detection result that describes user prompt injection attacks, where malicious users deliberately exploit system vulnerabilities to elicit unauthorized behavior from the LLM. This could lead to inappropriate content generation or violations of system-imposed restrictions.
  • indirect_attack AzureContentFilterDetectionResult - A detection result that describes attacks on systems powered by Generative AI models that can happen every time an application processes information that wasn’t directly authored by either the developer of the application or the user.

azure.openai.chat: AzureContentFilterSeverityResult

A labeled content filter result item that indicates whether the content was filtered and what the qualitative severity level of the content was, as evaluated against content filter configuration for the category.

Fields
  • filtered boolean - Whether the content severity resulted in a content filtering action.
  • severity "safe"|"low"|"medium"|"high" - The labeled severity of the content.

azure.openai.chat: AzureUserSecurityContext

User security context contains several parameters that describe the application itself, and the end user that interacts with the application. These fields assist your security operations teams to investigate and mitigate security incidents by providing a comprehensive approach to protecting your AI applications. Learn more about protecting AI applications using Microsoft Defender for Cloud.

Fields
  • application_name? string - The name of the application. Sensitive personal information should not be included in this field.
  • end_user_id? string - This identifier is the Microsoft Entra ID (formerly Azure Active Directory) user object ID used to authenticate end-users within the generative AI application. Sensitive personal information should not be included in this field.
  • end_user_tenant_id? string - The Microsoft 365 tenant ID the end user belongs to. It's required when the generative AI application is multitenant.
  • source_ip? string - Captures the original client's IP address.

azure.openai.chat: ChatCompletionsBody

Fields
  • metadata? OpenAIMetadata - Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  • top_logprobs? int? -
  • user? string - A unique identifier representing your end-user, which can help to monitor and detect abuse.
  • safety_identifier? string - A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
  • prompt_cache_key? string - Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
  • prompt_cache_retention? "in_memory"|"24h"? -
  • messages OpenAIChatCompletionRequestMessage[] - A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.
  • model string - Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
  • modalities? OpenAIResponseModalities? - Output types that you would like the model to generate. Most models are capable of generating text, which is the default: ["text"] The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use: ["text", "audio"]
  • verbosity? OpenAIVerbosity? - Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.
  • reasoning_effort? OpenAIReasoningEffort? - Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
    • gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
    • All models before gpt-5.1 default to medium reasoning effort, and do not support none.
    • The gpt-5-pro model defaults to (and only supports) high reasoning effort.
    • xhigh is supported for all models after gpt-5.1-codex-max.
  • max_completion_tokens? int? - An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
  • frequency_penalty? decimal? - 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.
  • presence_penalty? decimal? - 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.
  • response_format? OpenAICreateChatCompletionRequestResponseFormat - An object specifying the format that the model must output. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Setting to { "type": "json_object" } enables JSON mode, which ensures 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.
  • store? boolean? - Whether or not to store the output of this chat completion request for use in model distillation or evals products.
  • 'stream? boolean? - If set to true, the model response data will be streamed to the client as it is generated using server-sent events.
  • stop? OpenAIStopConfiguration - Not supported with latest reasoning models o3 and o4-mini. Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
  • logit_bias? record {}? - 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.
  • logprobs? boolean? - 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.
  • max_tokens? int? - The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API. This value is now deprecated in favor of max_completion_tokens, and is not compatible with o1 series models.
  • n? int? - 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.
  • prediction? OpenAIPredictionContent - Static predicted output content, such as the content of a text file that is being regenerated.
  • seed? int? - 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.
  • tool_choice? OpenAIChatCompletionToolChoiceOption - Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.
  • function_call? "none"|"auto"|OpenAIChatCompletionFunctionCallOption - 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.
  • user_security_context? AzureUserSecurityContext - User security context contains several parameters that describe the application itself, and the end user that interacts with the application. These fields assist your security operations teams to investigate and mitigate security incidents by providing a comprehensive approach to protecting your AI applications. Learn more about protecting AI applications using Microsoft Defender for Cloud.

azure.openai.chat: ConnectionConfig

Closed record

Provides a set of configurations for controlling the behaviours when communicating with a remote HTTP endpoint.

Fields
  • httpVersion HttpVersion(default http:HTTP_2_0) - The HTTP version understood by the client
  • timeout decimal(default 30) - The maximum time to wait (in seconds) for a response before closing the connection
  • forwarded string(default "disable") - The choice of setting forwarded/x-forwarded header
  • followRedirects? FollowRedirects - Configurations associated with Redirection
  • cache CacheConfig(default {}) - HTTP caching related configurations
  • compression Compression(default http:COMPRESSION_AUTO) - Specifies the way of handling compression (accept-encoding) header
  • circuitBreaker? CircuitBreakerConfig - Configurations associated with the behaviour of the Circuit Breaker
  • retryConfig? RetryConfig - Configurations associated with retrying
  • cookieConfig? CookieConfig - Configurations associated with cookies
  • responseLimits ResponseLimitConfigs(default {}) - Configurations associated with inbound response size limits
  • socketConfig ClientSocketConfig(default {}) - Provides settings related to client socket configuration
  • validation boolean(default true) - Enables the inbound payload validation functionality which provided by the constraint package. Enabled by default
  • laxDataBinding boolean(default true) - Enables relaxed data binding on the client side. When enabled, nil values are treated as optional, and absent fields are handled as nilable types. Enabled by default.

azure.openai.chat: CreateChatCompletionQueries

Represents the Queries record for the operation: createChatCompletion

Fields
  • api\-version? AzureAIFoundryModelsApiVersion - The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

azure.openai.chat: InlineResponse200PromptFilterResults

Fields
  • prompt_index Signed32 - The index of the input prompt that this content filter result corresponds to.

azure.openai.chat: OpenAIChatCompletionAllowedTools

Constrains the tools available to the model to a pre-defined set.

Fields
  • mode "auto"|"required" - Constrains the tools available to the model to a pre-defined set. auto allows the model to pick from among the allowed tools and generate a message. required requires the model to call one or more of the allowed tools.
  • tools record {}[] - A list of tool definitions that the model should be allowed to call. For the Chat Completions API, the list of tool definitions might look like: 
      [
    { "type": "function", "function": { "name": "get_weather" } },
    { "type": "function", "function": { "name": "get_time" } }
  ]

azure.openai.chat: OpenAIChatCompletionAllowedToolsChoice

Constrains the tools available to the model to a pre-defined set.

Fields
  • 'type "allowed_tools" - Allowed tool configuration type. Always allowed_tools.

azure.openai.chat: OpenAIChatCompletionFunctionCallOption

Specifying a particular function via {"name": "my_function"} forces the model to call that function.

Fields
  • name string - The name of the function to call.

azure.openai.chat: OpenAIChatCompletionFunctions

Deprecated
Fields
  • description? string - A description of what the function does, used by the model to choose when and how to call the function.
  • name string - 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? OpenAIFunctionParameters - The parameters the functions accepts, described as a JSON Schema object. See the JSON Schema reference for documentation about the format. Omitting parameters defines a function with an empty parameter list.

azure.openai.chat: OpenAIChatCompletionMessageCustomToolCall

A call to a custom tool created by the model.

Fields
  • id string - The ID of the tool call.
  • 'type "custom" - The type of the tool. Always custom.

azure.openai.chat: OpenAIChatCompletionMessageCustomToolCallCustom

Fields

azure.openai.chat: OpenAIChatCompletionMessageToolCall

A call to a function tool created by the model.

Fields
  • id string - The ID of the tool call.
  • 'type "function" - The type of the tool. Currently, only function is supported.

azure.openai.chat: OpenAIChatCompletionMessageToolCallChunk

Fields
  • id? string - The ID of the tool call.
  • 'type? "function" - The type of the tool. Currently, only function is supported.

azure.openai.chat: OpenAIChatCompletionMessageToolCallChunkFunction

Fields

azure.openai.chat: OpenAIChatCompletionMessageToolCallFunction

Fields

azure.openai.chat: OpenAIChatCompletionNamedToolChoice

Specifies a tool the model should use. Use to force the model to call a specific function.

Fields
  • 'type "function" - For function calling, the type is always function.

azure.openai.chat: OpenAIChatCompletionNamedToolChoiceCustom

Specifies a tool the model should use. Use to force the model to call a specific custom tool.

Fields
  • 'type "custom" - For custom tool calling, the type is always custom.

azure.openai.chat: OpenAIChatCompletionNamedToolChoiceCustomCustom

Fields

azure.openai.chat: OpenAIChatCompletionNamedToolChoiceFunction

Fields

azure.openai.chat: OpenAIChatCompletionRequestMessage

Fields

azure.openai.chat: OpenAIChatCompletionRequestMessageContentPartText

Fields
  • 'type "text" - The type of the content part.
  • text string - The text content.

azure.openai.chat: OpenAIChatCompletionResponseMessage

If the audio output modality is requested, this object contains data about the audio response from the model.

Fields
  • role "assistant" - The role of the author of this message.
  • reasoning_content? string - An Azure-specific extension property containing generated reasoning content from supported models.

azure.openai.chat: OpenAIChatCompletionResponseMessageAnnotations

Fields
  • 'type "url_citation" -

azure.openai.chat: OpenAIChatCompletionResponseMessageAnnotationsUrlCitation

Fields
  • end_index int -
  • start_index int -

azure.openai.chat: OpenAIChatCompletionResponseMessageAudio

Fields
  • expires_at int -

azure.openai.chat: OpenAIChatCompletionResponseMessageFunctionCall

Fields

azure.openai.chat: OpenAIChatCompletionStreamOptions

Options for streaming response. Only set this when you set stream: true.

Fields
  • include_usage? boolean - If set, an additional chunk will be streamed before the data: [DONE] message. The usage field on this chunk shows the token usage statistics for the entire request, and the choices field will always be an empty array. All other chunks will also include a usage field, but with a null value. NOTE: If the stream is interrupted, you may not receive the final usage chunk which contains the total token usage for the request.
  • include_obfuscation? boolean - When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.

azure.openai.chat: OpenAIChatCompletionStreamResponseDelta

A chat completion delta generated by streamed model responses.

Fields
  • role? "developer"|"system"|"user"|"assistant"|"tool" - The role of the author of this message.
  • reasoning_content? string - An Azure-specific extension property containing generated reasoning content from supported models.

azure.openai.chat: OpenAIChatCompletionStreamResponseDeltaFunctionCall

Fields

azure.openai.chat: OpenAIChatCompletionTokenLogprob

Fields
  • logprob decimal - The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.
  • bytes int[]? -

azure.openai.chat: OpenAIChatCompletionTokenLogprobTopLogprobs

Fields
  • bytes int[]? -

azure.openai.chat: OpenAIChatCompletionTool

A function tool that can be used to generate a response.

Fields
  • 'type "function" - The type of the tool. Currently, only function is supported.

azure.openai.chat: OpenAICompletionUsage

Usage statistics for the completion request.

Fields
  • completion_tokens int - Number of tokens in the generated completion.
  • prompt_tokens int - Number of tokens in the prompt.
  • total_tokens int - Total number of tokens used in the request (prompt + completion).

azure.openai.chat: OpenAICompletionUsageCompletionTokensDetails

Fields
  • accepted_prediction_tokens? int -
  • audio_tokens? int -
  • reasoning_tokens? int -
  • rejected_prediction_tokens? int -

azure.openai.chat: OpenAICompletionUsagePromptTokensDetails

Fields
  • audio_tokens? int -
  • cached_tokens? int -

azure.openai.chat: OpenAICreateChatCompletionRequestAudio

Fields
  • format "wav"|"aac"|"mp3"|"flac"|"opus"|"pcm16" -

azure.openai.chat: OpenAICreateChatCompletionRequestResponseFormat

An object specifying the format that the model must output. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide. Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

Fields

azure.openai.chat: OpenAICreateChatCompletionResponseChoices

Fields
  • finish_reason "stop"|"length"|"tool_calls"|"content_filter"|"function_call" -

azure.openai.chat: OpenAICreateChatCompletionResponseChoicesLogprobs

Fields

azure.openai.chat: OpenAICreateChatCompletionStreamResponseChoices

Fields
  • finish_reason "stop"|"length"|"tool_calls"|"content_filter"|"function_call"? -

azure.openai.chat: OpenAICreateChatCompletionStreamResponseChoicesLogprobs

Fields

azure.openai.chat: OpenAICustomToolChatCompletions

A custom tool that processes input using a specified format.

Fields
  • 'type "custom" - The type of the custom tool. Always custom.

azure.openai.chat: OpenAICustomToolChatCompletionsCustom

Fields

azure.openai.chat: OpenAICustomToolChatCompletionsCustomFormatGrammar

Fields
  • 'type "grammar" -

azure.openai.chat: OpenAICustomToolChatCompletionsCustomFormatGrammarGrammar

Fields
  • syntax "lark"|"regex" -

azure.openai.chat: OpenAICustomToolChatCompletionsCustomFormatText

Fields
  • 'type "text" -

azure.openai.chat: OpenAIFunctionObject

Fields
  • description? string - A description of what the function does, used by the model to choose when and how to call the function.
  • name string - 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? OpenAIFunctionParameters - The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format. Omitting parameters defines a function with an empty parameter list.

azure.openai.chat: OpenAIFunctionParameters

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format. Omitting parameters defines a function with an empty parameter list.

azure.openai.chat: OpenAIMetadata

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

azure.openai.chat: OpenAIPredictionContent

Static predicted output content, such as the content of a text file that is being regenerated.

Fields
  • 'type "content" - The type of the predicted content you want to provide. This type is currently always content.

Union types

azure.openai.chat: AzureAIFoundryModelsApiVersion

"v1"|"preview"

AzureAIFoundryModelsApiVersion

azure.openai.chat: OpenAIStopConfiguration

string|string[]

OpenAIStopConfiguration

Not supported with latest reasoning models o3 and o4-mini. Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

azure.openai.chat: OpenAIReasoningEffort

"none"|"minimal"|"low"|"medium"|"high"|"xhigh"?

OpenAIReasoningEffort

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

  • gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
  • All models before gpt-5.1 default to medium reasoning effort, and do not support none.
  • The gpt-5-pro model defaults to (and only supports) high reasoning effort.
  • xhigh is supported for all models after gpt-5.1-codex-max.

azure.openai.chat: OpenAIVerbosity

"low"|"medium"|"high"?

OpenAIVerbosity

Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.

azure.openai.chat: OpenAIVoiceIdsOrCustomVoice

OpenAIVoiceIdsShared|record { id string }

OpenAIVoiceIdsOrCustomVoice

A built-in voice name or a custom voice reference.

azure.openai.chat: InlineResponse200

record { id string, choices OpenAICreateChatCompletionResponseChoices[], created int, model string, system_fingerprint string, 'object "chat.completion" , usage OpenAICompletionUsage, prompt_filter_results InlineResponse200PromptFilterResults[] }|record { id string, choices OpenAICreateChatCompletionStreamResponseChoices[], created int, model string, system_fingerprint string, 'object "chat.completion.chunk" , usage OpenAICompletionUsage, delta OpenAIChatCompletionStreamResponseDelta, content_filter_results AzureContentFilterResultForChoice }

InlineResponse200

azure.openai.chat: OpenAICreateChatCompletionRequestResponseFormatType

string|"text"|"json_schema"|"json_object"

OpenAICreateChatCompletionRequestResponseFormatType

azure.openai.chat: OpenAIChatCompletionToolChoiceOption

"none"|"auto"|"required"|OpenAIChatCompletionAllowedToolsChoice|OpenAIChatCompletionNamedToolChoice|OpenAIChatCompletionNamedToolChoiceCustom

OpenAIChatCompletionToolChoiceOption

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.

azure.openai.chat: OpenAIVoiceIdsShared

string|"alloy"|"ash"|"ballad"|"coral"|"echo"|"sage"|"shimmer"|"verse"|"marin"|"cedar"

OpenAIVoiceIdsShared

azure.openai.chat: OpenAIChatCompletionRequestMessageType

string|"developer"|"system"|"user"|"assistant"|"tool"|"function"

OpenAIChatCompletionRequestMessageType

Array types

azure.openai.chat: OpenAIResponseModalities

("text"|"audio")[]?

OpenAIResponseModalities

Output types that you would like the model to generate. Most models are capable of generating text, which is the default: ["text"] The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use: ["text", "audio"]

azure.openai.chat: OpenAIChatCompletionMessageToolCallsItem

(OpenAIChatCompletionMessageToolCall|OpenAIChatCompletionMessageCustomToolCall)[]

OpenAIChatCompletionMessageToolCallsItem

The tool calls generated by the model, such as function calls.

Simple name reference types

azure.openai.chat: AzureContentFilterPersonallyIdentifiableInformationResult

AzureContentFilterDetectionResult

AzureContentFilterPersonallyIdentifiableInformationResult

A content filter detection result for Personally Identifiable Information that includes harm extensions.

Import

import ballerinax/azure.openai.chat;Copy

Other versions

4.0.0

3.0.33.0.23.0.13.0.0
See more...

Metadata

Released date: about 13 hours ago

Version: 4.0.0

License: Apache-2.0

Compatibility

Platform: any

Ballerina version: 2201.12.0

GraalVM compatible: Yes

Pull count

Total: 25638

Current verison: 9

Weekly downloads

Source repository

Keywords

AI/Chat

Azure

Azure OpenAI

Chat Completions

Vendor/Microsoft

Contributors

Dependencies

ballerina/constraint/1.7.0ballerina/os/1.10.1ballerina/log/2.14.0
See more...

Terms of service

Privacy policy

Cookie policy

Delete policy

© 2026 WSO2 LLC