gloq
Types
pub type GroqRequestBuilder {
GroqRequestBuilder(
key: String,
user: String,
context: String,
model: String,
frequency_penalty: Option(Float),
logprobs: Option(Bool),
max_tokens: Option(Int),
n: Option(Int),
parallel_tool_calls: Option(Bool),
presence_penalty: Option(Float),
seed: Option(Int),
stop: Option(String),
stream: Option(Bool),
temperature: Option(Float),
top_p: Option(Float),
)
}
Constructors
-
GroqRequestBuilder( key: String, user: String, context: String, model: String, frequency_penalty: Option(Float), logprobs: Option(Bool), max_tokens: Option(Int), n: Option(Int), parallel_tool_calls: Option(Bool), presence_penalty: Option(Float), seed: Option(Int), stop: Option(String), stream: Option(Bool), temperature: Option(Float), top_p: Option(Float), )
Functions
pub fn build(builder: GroqRequestBuilder) -> Request(String)
Builds the request body for the GroqCloud API that can be sent using the appropriate HTTP client.
pub fn default_groq_request() -> GroqRequestBuilder
Creates a new GroqRequestBuilder with default model and user values.
Uses the default model llama3-8b-8192
and user role user
.
pub fn new_groq_request() -> GroqRequestBuilder
Create a new GroqRequestBuilder with no default values.
pub fn send(builder: GroqRequestBuilder) -> String
Sends the request to the GroqCloud API for chat completions.
Function is deprecated, send logic is left to consumer To create a request, use the
build
function and send the request using the appropriate HTTP client of your choice. Uses thehackney
HTTP client to send the request, this command is no longer supported.
pub fn view_models(api_key: String) -> Request(String)
Builds the request body for the GroqCloud API that can be sent using the appropriate HTTP client.
pub fn with_context(
builder: GroqRequestBuilder,
context: String,
) -> GroqRequestBuilder
Sets the context/prompt for the GroqRequestBuilder.
pub fn with_frequency_penalty(
builder: GroqRequestBuilder,
frequency_penalty: Float,
) -> GroqRequestBuilder
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.
pub fn with_key(
builder: GroqRequestBuilder,
key: String,
) -> GroqRequestBuilder
Sets the API key for the GroqRequestBuilder.
pub fn with_logprobs(
builder: GroqRequestBuilder,
logprobs: Bool,
) -> GroqRequestBuilder
This is not yet supported by any of our models. 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
.
pub fn with_max_tokens(
builder: GroqRequestBuilder,
max_tokens: Int,
) -> GroqRequestBuilder
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.
pub fn with_model(
builder: GroqRequestBuilder,
model: String,
) -> GroqRequestBuilder
Sets the model for the GroqRequestBuilder.
pub fn with_n(
builder: GroqRequestBuilder,
n: Int,
) -> GroqRequestBuilder
How many chat completion choices to generate for each input message. Note that the current moment, only n=1 is supported. Other values will result in a 400 response.
pub fn with_parallel_tool_calls(
builder: GroqRequestBuilder,
parallel_tool_calls: Bool,
) -> GroqRequestBuilder
Whether to enable parallel function calling during tool use.
pub fn with_presence_penalty(
builder: GroqRequestBuilder,
presence_penalty: Float,
) -> GroqRequestBuilder
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.
pub fn with_seed(
builder: GroqRequestBuilder,
seed: Int,
) -> GroqRequestBuilder
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.
pub fn with_stop(
builder: GroqRequestBuilder,
stop: String,
) -> GroqRequestBuilder
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
pub fn with_stream(
builder: GroqRequestBuilder,
stream: Bool,
) -> GroqRequestBuilder
If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
pub fn with_temperature(
builder: GroqRequestBuilder,
temperature: Float,
) -> GroqRequestBuilder
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
pub fn with_top_p(
builder: GroqRequestBuilder,
top_p: Float,
) -> GroqRequestBuilder
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.