OpenAI Chat completion
Creates a model response for the given chat conversation using an OpenAI model.
Creates a model response for the given chat conversation. This endpoint follows the OpenAI API specification and the requests are sent to the Azure OpenAI endpoint.
To use the API you need an API key. To request access, please contact us at support@langdock.com
All parameters from the OpenAI Chat Completion endpoint are supported according to the OpenAI specifications, with the following exceptions:
model
: Currently only thegpt-4o
,gpt-4o-mini
,gpt-4
andgpt-3.5-turbo
models are supported.n
: Not supported.service_tier
: Not supported.parallel_tool_calls
: Not supported.stream_options
: Not supported.
Rate limits
The rate limit for the Chat Completion endpoint is 500 RPM (requests per minute) and 60.000 TPM (tokens per minute). Rate limits are defined at the workspace level - and not at an API key level. Each model has its own rate limit. If you exceed your rate limit, you will receive a 429 Too Many Requests
response.
Please note that the rate limits are subject to change, refer to this documentation for the most up-to-date information. In case you need a higher rate limit, please contact us at support@langdock.com.
Using OpenAI-compatible libraries
As the request and response format is the same as the OpenAI API, you can use popular libraries like the OpenAI Python library or the Vercel AI SDK to use the Langdock API.
Example using the OpenAI Python library
Example using the Vercel AI SDK in Node.js
Path Parameters
The region of the API to use.
eu
, us
Body
A list of messages comprising the conversation so far. Example Python code.
ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
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.
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.
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
.
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.
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.
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.
An object specifying the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than 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.
This feature is in Beta.
If specified, OpenAI's 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.
Up to 4 sequences where the API will stop generating further tokens.
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.
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.
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.
A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.
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.
none
, auto
, required
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
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.
none
, auto
Deprecated in favor of tools
.
A list of functions the model may generate JSON inputs for.
Response
Represents a chat completion response returned by model, based on the provided input.
A unique identifier for the chat completion.
A list of chat completion choices. Can be more than one if n
is greater than 1.
The Unix timestamp (in seconds) of when the chat completion was created.
The model used for the chat completion.
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.
The object type, which is always chat.completion
.
chat.completion
Usage statistics for the completion request.
Was this page helpful?