class

OpenAI::CreateChatCompletionRequest

Inherits JSON::Serializable < Reference < Object

Extension methods for CreateChatCompletionRequest

Constructors

new(messages : Array(ChatCompletionRequestMessage) = [] of ChatCompletionRequestMessage, model : ModelIdsShared = String.new, modalities : ResponseModalities | Nil = nil, verbosity : Verbosity | Nil = nil, reasoning_effort : ReasoningEffort | Nil = nil, max_completion_tokens : Int64 | Nil = nil, frequency_penalty : Float64 | Nil = nil, presence_penalty : Float64 | Nil = nil, web_search_options : CreateChatCompletionRequestWebSearchOptions | Nil = nil, top_logprobs : Int64 | Nil = nil, response_format : CreateChatCompletionRequestResponseFormat | Nil = nil, audio : CreateChatCompletionRequestAudio | Nil = nil, store : Bool | Nil = nil, stream : Bool | Nil = nil, stop : StopConfiguration | Nil = nil, logit_bias : Hash(String, Int64) | Nil = nil, logprobs : Bool | Nil = nil, max_tokens : Int64 | Nil = nil, n : Int64 | Nil = nil, prediction : CreateChatCompletionRequestPrediction | Nil = nil, seed : Int64 | Nil = nil, stream_options : ChatCompletionStreamOptions | Nil = nil, tools : Array(CreateChatCompletionRequestToolsItem) | Nil = nil, tool_choice : ChatCompletionToolChoiceOption | Nil = nil, parallel_tool_calls : ParallelToolCalls | Nil = nil, function_call : CreateChatCompletionRequestFunctionCall | Nil = nil, functions : Array(ChatCompletionFunctions) | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

add_assistant_message(content : String | Nil, name : String | Nil = nil, refusal : String | Nil = nil) : self

Add an assistant message

Source
add_developer_message(content : String, name : String | Nil = nil) : self

Add a developer message

Source
add_messages_from_json(json : String) : self

Add messages from JSON

Source
add_system_message(content : String, name : String | Nil = nil) : self

Add a system message

Source
add_tool_message(content : String, tool_call_id : String) : self

Add a tool message

Source
add_user_message(content : String, name : String | Nil = nil) : self

Add a user message

Source
audio

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

Source
audio=(audio : CreateChatCompletionRequestAudio | Nil)

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

Source
frequency_penalty

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.

Source
frequency_penalty=(frequency_penalty : Float64 | Nil)

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.

Source
function_call

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.

Source
function_call=(function_call : CreateChatCompletionRequestFunctionCall | Nil)

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.

Source
functions

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

Source
functions=(functions : Array(ChatCompletionFunctions) | Nil)

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

Source
logit_bias

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.

Source
logit_bias=(logit_bias : Hash(String, Int64) | Nil)

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.

Source
logprobs

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.

Source
logprobs=(logprobs : Bool | Nil)

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.

Source
max_completion_tokens

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

Source
max_completion_tokens=(max_completion_tokens : Int64 | Nil)

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

Source
max_tokens

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 o-series models.

Source
max_tokens=(max_tokens : Int64 | Nil)

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 o-series models.

Source
messages

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.

Source
messages=(messages : Array(ChatCompletionRequestMessage))

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.

Source
modalities
Source
modalities=(modalities : ResponseModalities | Nil)
Source
model

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.

Source
model=(model : ModelIdsShared)

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.

Source
n

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.

Source
n=(n : Int64 | Nil)

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.

Source
parallel_tool_calls
Source
parallel_tool_calls=(parallel_tool_calls : ParallelToolCalls | Nil)
Source
prediction

Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.

Source
prediction=(prediction : CreateChatCompletionRequestPrediction | Nil)

Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.

Source
presence_penalty

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.

Source
presence_penalty=(presence_penalty : Float64 | Nil)

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.

Source
reasoning_effort
Source
reasoning_effort=(reasoning_effort : ReasoningEffort | Nil)
Source
response_format

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.

Source
response_format=(response_format : CreateChatCompletionRequestResponseFormat | Nil)

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.

Source
seed

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.

Source
seed=(seed : Int64 | Nil)

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.

Source
stop
Source
stop=(stop : StopConfiguration | Nil)
Source
store

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

Supports text and image inputs. Note: image inputs over 8MB will be dropped.

Source
store=(store : Bool | Nil)

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

Supports text and image inputs. Note: image inputs over 8MB will be dropped.

Source
stream

If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information, along with the streaming responses guide for more information on how to handle the streaming events.

Source
stream=(stream : Bool | Nil)

If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information, along with the streaming responses guide for more information on how to handle the streaming events.

Source
stream_options
Source
stream_options=(stream_options : ChatCompletionStreamOptions | Nil)
Source
tool_choice
Source
tool_choice=(tool_choice : ChatCompletionToolChoiceOption | Nil)
Source
tools

A list of tools the model may call. You can provide either custom tools or function tools.

Source
tools=(tools : Array(CreateChatCompletionRequestToolsItem) | Nil)

A list of tools the model may call. You can provide either custom tools or function tools.

Source
top_logprobs

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

Source
top_logprobs=(top_logprobs : Int64 | Nil)

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

Source
validate!
Source
verbosity
Source
verbosity=(verbosity : Verbosity | Nil)
Source
web_search_options

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

Source
web_search_options=(web_search_options : CreateChatCompletionRequestWebSearchOptions | Nil)

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

Source