This function creates and submits a batch of messages to the Azure OpenAI Batch API for asynchronous processing.
send_azure_openai_batch(
.llms,
.deployment = "gpt-4o-mini",
.endpoint_url = Sys.getenv("AZURE_ENDPOINT_URL"),
.api_version = "2024-10-01-preview",
.max_completion_tokens = NULL,
.frequency_penalty = NULL,
.logit_bias = NULL,
.logprobs = FALSE,
.top_logprobs = NULL,
.presence_penalty = NULL,
.seed = NULL,
.stop = NULL,
.temperature = NULL,
.top_p = NULL,
.dry_run = FALSE,
.overwrite = FALSE,
.max_tries = 3,
.timeout = 60,
.verbose = FALSE,
.json_schema = NULL,
.id_prefix = "tidyllm_azure_openai_req_"
)An updated and named list of .llms with identifiers that align with batch responses, including a batch_id attribute.
An LLMMessage object containing the conversation history.
The identifier of the model that is deployed (default: "gpt-4o-mini").
Base URL for the API (default: Sys.getenv("AZURE_ENDPOINT_URL")).
Which version of the API is deployed (default: "2024-10-01-preview")
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.
A named list modifying the likelihood of specified tokens appearing in the completion.
Whether to return log probabilities of the output tokens (default: FALSE).
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position.
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.
If specified, the system will make a best effort to sample deterministically.
Up to 4 sequences where the API will stop generating further tokens.
What sampling temperature to use, between 0 and 2. Higher values make the output more random.
An alternative to sampling with temperature, called nucleus sampling.
If TRUE, perform a dry run and return the request object (default: FALSE).
Logical; if TRUE, allows overwriting an existing batch ID (default: FALSE).
Maximum number of retries to perform the request (default: 3).
Request timeout in seconds (default: 60).
Logical; if TRUE, additional info about the requests is printed (default: FALSE).
A JSON schema object as R list to enforce the output structure (default: NULL).
Character string to specify a prefix for generating custom IDs when names in .llms are missing (default: "tidyllm_openai_req_").