Chat
Pass in a list of messages and Maitai will return a response.
Create chat completion
Creates a model response for the given chat conversation. Passing parameters in through the SDK overrides the Portal configuration.
Maitai Specific Parameters
A unique identifier you set for the session.
Specifies the type the intention of the request.
Examples: CONVERSATION
The reference to the application the request is created from.
Optional metadata used to reference the request/session later.
Optional. A reference identifier for identifying the request in your session.
Optional. A callback function that may be used to handle the resulting Maitai evaluation asynchronously.
Indicates whether or not to evaluate model output.
Indicates whether or not to apply corrections if a fault is found during evaluation. This is also referred to as “autocorrect”.
Safe Mode ensures that corrections all LLM outputs are evaluated and corrected, with no consideration for latency.
Whether to run as an Assistant. See Assistants for more info
Optional. Unique identifier for a user, used for long term memory.
Indicates whether or not to retrieve and inject applicable context parts.
Optional. A query used for retrieving applicable context. If not provided
while context_retrieval_enabled
is true, a query will be inferred.
Optional. Configuration for fallback model.
Indicates whether the inference should be performed server-side. Only OpenAI models can be run client-side.
The unique identifier for the end-user. If this is supplied, we’ll create, store, and search core memories to provide inter-session context.
Model Provider Parameters
A list of messages comprising the conversation so far.
ID of the model to use. Providing in parameters overwrites portal config.
Defaults to 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.
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 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.
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.
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.
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.
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, 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.
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.
Optional. Defaults to null. Options for streaming response. Only set this when you set stream: true
.
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.
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.
Specifies a tool the model should use. Use to force the model to call a specific function.
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
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.
Deprecated in favor of tools
.
A list of functions the model may generate JSON inputs for.
Returns
Returns a chat completion object, or a streamed sequence of chat completion chunk objects if the request is streamed.
The chat completion object
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.
If cache
this means that the result came out of the semantic cache.
The object type, which is always chat.completion
.
The chat completion chunk object
Represents a streamed chunk of a chat completion response returned by model, based on the provided input.
A unique identifier for the chat completion. Each chunk has the same ID.
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. Each chunk has the same timestamp.
The model used to generate the 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.
If cache
this means that the result came out of the semantic cache.
The object type, which is always chat.completion.chunk.
An optional field that will only be present when you set stream_options: {'"include_usage": true}
in your request. When present, it contains a null value except for the last chunk which contains the token usage statistics for the entire request.