openai.chat
Module openai.chat
Definitions
ballerinax/openai.chat Ballerina library
Overview
This is a generated connector for the OpenAI Chat API OpenAPI Specification. OpenAI is an American artificial intelligence research laboratory consisting of a non-profit corporation and a for-profit subsidiary. OpenAI conducts AI research with the declared intention of promoting and developing friendly AI. The OpenAI Chat API provides a way to access the state-of-the-art ChatGPT models developed by OpenAI for a variety of tasks.
Prerequisites
Before using this connector in your Ballerina application, complete the following:
- Create an OpenAI account.
- Obtain an API key by following these instructions.
Quick start
To use the OpenAI Chat connector in your Ballerina application, update the .bal
file as follows:
Step 1: Import the connector
First, import the ballerinax/openai.chat
module into the Ballerina project.
import ballerinax/openai.chat;
Step 2: Create a new connector instance
Create and initialize a chat:Client
with the obtained apiKey
.
chat:Client chatClient = check new ({ auth: { token: "sk-XXXXXXXXX" } });
Step 3: Invoke the connector operation
- Now you can use the operations available within the connector.
Following is an example on creating a conversation with the GPT-3.5 model.
ballerina public function main() returns error? { chat:CreateChatCompletionRequest req = { model: "gpt-3.5-turbo", messages: [{"role": "user", "content": "What is Ballerina?"}] }; chat:CreateChatCompletionResponse res = check chatClient->/chat/completions.post(req); }
Following is an example of using OpenAI vision capabilities when chatting.
```ballerina public function main() returns error? { chat:CreateChatCompletionResponse response = check chatClient->/chat/completions.post( { model: "gpt-4-vision-preview", messages: [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": [ { "type": "text", "text": "Describe the image." }, { "type": "image_url", "image_url": { "url": "<image_url>" } } ] } ] } ); chat:CreateChatCompletionResponse_choices[] choices = response.choices; io:println(choices[0].message?.content); } ```
2. Use bal run
command to compile and run the Ballerina program.
Clients
openai.chat: Client
This is a generated connector for the [OpenAI API] (https://platform.openai.com/docs/api-reference/introduction) specification. Use the OpenAI API to access the state-of-the-art language models that can complete sentences, transcribe audio, and generate images. The API also supports natural language processing tasks such as text classification, entity recognition, and sentiment analysis. By using the OpenAI API, you can incorporate advanced AI capabilities into your own applications and services.
Constructor
Gets invoked to initialize the connector
.
To use the OpenAI API, you will need an API key. You can sign up for an API key by creating an account on the OpenAI website and following the provided instructions.
init (ConnectionConfig config, string serviceUrl)
- config ConnectionConfig - The configurations to be used when initializing the
connector
- serviceUrl string "https://api.openai.com/v1" - URL of the target service
post chat/completions
function post chat/completions(CreateChatCompletionRequest payload) returns CreateChatCompletionResponse|error
Creates a model response for the given chat conversation.
Parameters
- payload CreateChatCompletionRequest -
Return Type
Records
openai.chat: ChatCompletionFunctionCallOption
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.
openai.chat: ChatCompletionFunctions
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 FunctionParameters? - 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.
openai.chat: ChatCompletionMessageToolCall
Fields
- id string - The ID of the tool call.
- 'type "function" - The type of the tool. Currently, only
function
is supported.
- 'function ChatCompletionMessageToolCall_function - The function that the model called.
openai.chat: ChatCompletionMessageToolCall_function
The function that the model called.
Fields
- name string - The name of the function to call.
- arguments string - 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.
openai.chat: ChatCompletionNamedToolChoice
Specifies a tool the model should use. Use to force the model to call a specific function.
Fields
- 'type "function" - The type of the tool. Currently, only
function
is supported.
- 'function ChatCompletionNamedToolChoice_function - The function that should be called.
openai.chat: ChatCompletionNamedToolChoice_function
The function that should be called.
Fields
- name string - The name of the function to call.
openai.chat: ChatCompletionRequestAssistantMessage
Fields
- content string? - The contents of the assistant message. Required unless
tool_calls
orfunction_call
is specified.
- role "assistant" - The role of the messages author, in this case
assistant
.
- name string? - An optional name for the participant. Provides the model information to differentiate between participants of the same role.
- tool_calls ChatCompletionMessageToolCalls? - The tool calls generated by the model, such as function calls.
- function_call ChatCompletionRequestAssistantMessage_function_call? - Deprecated and replaced by
tool_calls
. The name and arguments of a function that should be called, as generated by the model.
openai.chat: ChatCompletionRequestAssistantMessage_function_call
Deprecated and replaced by tool_calls
. The name and arguments of a function that should be called, as generated by the model.
Fields
- arguments string - 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.
- name string - The name of the function to call.
openai.chat: ChatCompletionRequestFunctionMessage
Fields
- role "function" - The role of the messages author, in this case
function
.
- content string - The contents of the function message.
- name string - The name of the function to call.
openai.chat: ChatCompletionRequestMessageContentPartImage
Fields
- 'type "image_url" - The type of the content part.
openai.chat: ChatCompletionRequestMessageContentPartImage_image_url
Fields
- url string - Either a URL of the image or the base64 encoded image data.
- detail "auto"|"low"|"high" (default "auto") - Specifies the detail level of the image. Learn more in the Vision guide.
openai.chat: ChatCompletionRequestMessageContentPartText
Fields
- 'type "text" - The type of the content part.
- text string - The text content.
openai.chat: ChatCompletionRequestSystemMessage
Fields
- content string - The contents of the system message.
- role "system" - The role of the messages author, in this case
system
.
- name string? - An optional name for the participant. Provides the model information to differentiate between participants of the same role.
openai.chat: ChatCompletionRequestToolMessage
Fields
- role "tool" - The role of the messages author, in this case
tool
.
- content string - The contents of the tool message.
- tool_call_id string - Tool call that this message is responding to.
openai.chat: ChatCompletionRequestUserMessage
Fields
- content string|ChatCompletionRequestMessageContentPart[] - The contents of the user message.
- role "user" - The role of the messages author, in this case
user
.
- name string? - An optional name for the participant. Provides the model information to differentiate between participants of the same role.
openai.chat: ChatCompletionResponseMessage
A chat completion message generated by the model.
Fields
- content string - The contents of the message.
- tool_calls ChatCompletionMessageToolCalls? - The tool calls generated by the model, such as function calls.
- role "assistant" - The role of the author of this message.
- function_call ChatCompletionRequestAssistantMessage_function_call? - Deprecated and replaced by
tool_calls
. The name and arguments of a function that should be called, as generated by the model.
openai.chat: ChatCompletionTokenLogprob
Fields
- token string - The token.
- logprob decimal - The log probability of this token.
- bytes int[] - A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be
null
if there is no bytes representation for the token.
- top_logprobs ChatCompletionTokenLogprob_top_logprobs[] - List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested
top_logprobs
returned.
openai.chat: ChatCompletionTokenLogprob_top_logprobs
Fields
- token string - The token.
- logprob decimal - The log probability of this token.
- bytes int[] - A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be
null
if there is no bytes representation for the token.
openai.chat: ChatCompletionTool
Fields
- 'type "function" - The type of the tool. Currently, only
function
is supported.
- 'function FunctionObject -
openai.chat: ClientHttp1Settings
Provides settings related to HTTP/1.x protocol.
Fields
- keepAlive KeepAlive(default http:KEEPALIVE_AUTO) - Specifies whether to reuse a connection for multiple requests
- chunking Chunking(default http:CHUNKING_AUTO) - The chunking behaviour of the request
- proxy ProxyConfig? - Proxy server related options
openai.chat: CompletionUsage
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).
openai.chat: ConnectionConfig
Provides a set of configurations for controlling the behaviours when communicating with a remote HTTP endpoint.
Fields
- auth BearerTokenConfig - Configurations related to client authentication
- httpVersion HttpVersion(default http:HTTP_2_0) - The HTTP version understood by the client
- http1Settings ClientHttp1Settings? - Configurations related to HTTP/1.x protocol
- http2Settings ClientHttp2Settings? - Configurations related to HTTP/2 protocol
- timeout decimal(default 60) - 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
- poolConfig PoolConfiguration? - Configurations associated with request pooling
- cache CacheConfig? - 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
- responseLimits ResponseLimitConfigs? - Configurations associated with inbound response size limits
- secureSocket ClientSecureSocket? - SSL/TLS-related options
- proxy ProxyConfig? - Proxy server related options
- validation boolean(default true) - Enables the inbound payload validation functionality which provided by the constraint package. Enabled by default
openai.chat: CreateChatCompletionRequest
Fields
- messages ChatCompletionRequestMessage[] - A list of messages comprising the conversation so far. Example Python code.
- model string|"gpt-4-0125-preview"|"gpt-4-turbo-preview"|"gpt-4-1106-preview"|"gpt-4-vision-preview"|"gpt-4"|"gpt-4-0314"|"gpt-4-0613"|"gpt-4-32k"|"gpt-4-32k-0314"|"gpt-4-32k-0613"|"gpt-3.5-turbo"|"gpt-3.5-turbo-16k"|"gpt-3.5-turbo-0301"|"gpt-3.5-turbo-0613"|"gpt-3.5-turbo-1106"|"gpt-3.5-turbo-16k-0613" - ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
- frequency_penalty decimal?(default 0) - 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. See more information about frequency and presence penalties.
- logit_bias record { int... }? - 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
ofmessage
. This option is currently not available on thegpt-4-vision-preview
model.
- top_logprobs int? - An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
logprobs
must be set totrue
if this parameter is used.
- max_tokens int? - The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. Example Python code for counting tokens.
- n int?(default 1) - 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
as1
to minimize costs.
- presence_penalty decimal?(default 0) - 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. See more information about frequency and presence penalties.
- response_format CreateChatCompletionRequest_response_format? - An object specifying the format that the model must output. Compatible with GPT-4 Turbo and
gpt-3.5-turbo-1106
. Setting to{ "type": "json_object" }
enables JSON mode, which guarantees the message the model generates is valid JSON. Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off iffinish_reason="length"
, which indicates the generation exceededmax_tokens
or the conversation exceeded the max context length.
- 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 thesystem_fingerprint
response parameter to monitor changes in the backend.
- 'stream boolean?(default false) - 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. Example Python code.
- temperature decimal?(default 1) - What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or
top_p
but not both.
- top_p decimal?(default 1) - An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperature
but not both.
- tools ChatCompletionTool[]? - 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.
- tool_choice ChatCompletionToolChoiceOption? - 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.none
is the default when no functions are present.auto
is the default if functions are present.
- user string? - A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
- function_call "none"|"auto"|ChatCompletionFunctionCallOption? - 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.
- functions ChatCompletionFunctions[]? - Deprecated in favor of
tools
. A list of functions the model may generate JSON inputs for.
openai.chat: CreateChatCompletionRequest_response_format
An object specifying the format that the model must output. Compatible with GPT-4 Turbo and gpt-3.5-turbo-1106
.
Setting to { "type": "json_object" }
enables JSON mode, which guarantees the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length"
, which indicates the generation exceeded max_tokens
or the conversation exceeded the max context length.
Fields
- 'type "text"|"json_object" ? - Must be one of
text
orjson_object
.
openai.chat: CreateChatCompletionResponse
Represents a chat completion response returned by model, based on the provided input.
Fields
- id string - A unique identifier for the chat completion.
- choices CreateChatCompletionResponse_choices[] - A list of chat completion choices. Can be more than one if
n
is greater than 1.
- created int - The Unix timestamp (in seconds) of when the chat completion was created.
- model string - The model used for the chat completion.
- system_fingerprint string? - This fingerprint represents the backend configuration that the model runs with.
Can be used in conjunction with the
seed
request parameter to understand when backend changes have been made that might impact determinism.
- 'object "chat.completion" - The object type, which is always
chat.completion
.
- usage CompletionUsage? - Usage statistics for the completion request.
openai.chat: CreateChatCompletionResponse_choices
Fields
- finish_reason "stop"|"length"|"tool_calls"|"content_filter"|"function_call" - The reason the model stopped generating tokens. This will be
stop
if the model hit a natural stop point or a provided stop sequence,length
if the maximum number of tokens specified in the request was reached,content_filter
if content was omitted due to a flag from our content filters,tool_calls
if the model called a tool, orfunction_call
(deprecated) if the model called a function.
- index int - The index of the choice in the list of choices.
- message ChatCompletionResponseMessage - A chat completion message generated by the model.
- logprobs CreateChatCompletionResponse_logprobs? - Log probability information for the choice.
openai.chat: CreateChatCompletionResponse_logprobs
Log probability information for the choice.
Fields
- content ChatCompletionTokenLogprob[] - A list of message content tokens with log probability information.
openai.chat: FunctionObject
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 FunctionParameters? - 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.
openai.chat: FunctionParameters
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.
openai.chat: ProxyConfig
Proxy server configurations to be used with the HTTP client endpoint.
Fields
- host string(default "") - Host name of the proxy server
- port int(default 0) - Proxy server port
- userName string(default "") - Proxy server username
- password string(default "") - Proxy server password
Union types
openai.chat: ChatCompletionRequestMessage
ChatCompletionRequestMessage
openai.chat: ChatCompletionRequestMessageContentPart
ChatCompletionRequestMessageContentPart
openai.chat: ChatCompletionToolChoiceOption
ChatCompletionToolChoiceOption
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.
none
is the default when no functions are present. auto
is the default if functions are present.
openai.chat: ChatCompletionRole
ChatCompletionRole
The role of the author of a message
Array types
openai.chat: ChatCompletionMessageToolCalls
ChatCompletionMessageToolCalls
The tool calls generated by the model, such as function calls.
Import
import ballerinax/openai.chat;
Metadata
Released date: 8 months ago
Version: 2.0.1
License: Apache-2.0
Compatibility
Platform: any
Ballerina version: 2201.8.0
GraalVM compatible: Yes
Pull count
Total: 4510
Current verison: 1369
Weekly downloads
Keywords
AI/Chat
OpenAI
Cost/Paid
GPT-3.5
ChatGPT
Vendor/OpenAI
Contributors