This val exports a function pplx that provides an interface to the Perplexity AI chat completions API.

You'll need a Perplexity AI API key, see their documentation for how to get started with getting a key. By default, the function will use PERPLEXITY_API_KEY in your val town env variables unless overridden by setting apiKey in the function.

Generates a model's response for the given chat conversation. Required parameters in options are the following (for other parameters, see the Types section below):

• model (string): the name of the model that will complete your prompt. See below for possible values: pplx- 7b-chat, pplx-70b-chat, pplx-7b-online, pplx-70b-online, llama-2-70b-chat, codellama-34b -instruct, mistral-7b-instruct, and mixtral-8x7b-instruct.

• messages(Message[]): A list of messages comprising the conversation so far. A message object must contain role (system, user, or assistant) and content (a string).

You can also specify an apiKey to override the default Deno.env.get("PERPLEXITY_API_KEY").

The function returns an object of types PplxResponse, see below.

Request object sent to Perplexity models.

Property	Type	Description
model	Model	The name of the model that will complete your prompt. Possible values: pplx- 7b-chat, pplx-70b-chat, pplx-7b-online, pplx-70b-online, llama-2-70b-chat, codellama-34b -instruct, mistral-7b-instruct, and mixtral-8x7b-instruct.
messages	Message[]	A list of messages comprising the conversation so far.
max_tokens	number	(Optional) The maximum number of completion tokens returned by the API. The total number of tokens requested in max_tokens plus the number of prompt tokens sent in messages must not exceed the context window token limit of model requested. If left unspecified, then the model will generate tokens until either it reaches its stop token or the end of its context window.
temperature	number	(Optional) The amount of randomness in the response, valued between 0 inclusive and 2 exclusive. Higher values are more random, and lower values are more deterministic. You should either set temperature or top_p, but not both.
top_p	number	(Optional) The nucleus sampling threshold, valued between 0 and 1 inclusive. For each subsequent token, the model considers the results of the tokens with top_p probability mass. You should either alter temperature or top_p, but not both.
top_k	number	(Optional) The number of tokens to keep for highest top-k filtering, specified as an integer between 0 and 2048 inclusive. If set to 0, top-k filtering is disabled.
stream	boolean	(Optional) Flag indicating whether to stream the response.
presence_penalty	number	(Optional) A value 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. Incompatible with frequency_penalty.
frequency_penalty	number	(Optional) A multiplicative penalty greater than 0. Values greater than 1.0 penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. A value of 1.0 means no penalty. Incompatible with presence_penalty.

Response object for pplx models.

Property	Type	Description
id	string	The ID of the response.
model	Model	The model used for generating the response.
object	"chat.completion"	The type of object (always "chat.completion").
created	number	The timestamp indicating when the response was created.
choices	CompletionChoices[]	An array of completion choices.

Please refer to the code for more details and usage examples of these types.

Represents a message in a conversation.

Property	Type	Description
role	"system" | "user" | "assistant"	The role of the speaker in this turn of conversation. After the (optional) system message, user and assistant roles should alternate with user then assistant, ending in user.
content	string	The contents of the message in this turn of conversation.

The list of completion choices the model generated for the input prompt.

Property	Type	Description
index	number	The index of the choice.
finish_reason	"stop" | "length"	The reason the model stopped generating tokens. Possible values are stop if the model hit a natural stopping point, or length if the maximum number of tokens specified in the request was reached.
message	Message	The message generated by the model.
delta	Message	The incrementally streamed next tokens. Only meaningful when stream = true.

Migrated from folder: projects/pplxAI/perplexityAPI