| chat_request {oaii} | R Documentation |
API chat: send create (chat) request
Description
Creates a model response for the given chat conversation. To get more details, visit https://platform.openai.com/docs/api-reference/chat/create https://platform.openai.com/docs/guides/text-generation
Usage
chat_request(
messages,
model,
frequency_penalty = NULL,
logit_bias = NULL,
logprobs = NULL,
top_logprobs = NULL,
max_tokens = NULL,
n = NULL,
presence_penalty = NULL,
response_format = NULL,
seed = NULL,
stop = NULL,
stream = NULL,
temperature = NULL,
top_p = NULL,
tools = NULL,
tool_choice = NULL,
user = NULL,
api_key = api_get_key()
)
Arguments
messages |
data.frame, data.frame with messages comprising the conversation so far |
model |
string, ID of the model to use. See the model endpoint compatibility table https://platform.openai.com/docs/models/model-endpoint-compatibility for details on which models work with the Chat API. |
frequency_penalty |
NULL/double, 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. More at https://platform.openai.com/docs/guides/text-generation/parameter-details |
logit_bias |
NULL/list, modify the likelihood of specified tokens appearing in the completion. Accepts a list 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. See https://platform.openai.com/tokenizer |
logprobs |
NULL/flag, 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. This option is currently not available on the gpt-4-vision-preview model. Defaults to false. |
top_logprobs |
NULL/int, an integer between 0 and 5 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. |
max_tokens |
NULL/int, the maximum number of tokens to generate in the chat completion |
n |
NULL/int, how many chat completion choices to generate for each input message. |
presence_penalty |
NULL/double, 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 https://platform.openai.com/docs/guides/text-generation/parameter-details |
response_format |
NULL/list, an object specifying the format that the model must output. Compatible with gpt-4-1106-preview and gpt-3.5-turbo-1106. Setting to list(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. Text is default response format. |
seed |
NULL/int, 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. |
stop |
NULL/character vector, up to 4 sequences where the API will stop generating further tokens. |
stream |
NULL/flag, 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. Defaults to false |
temperature |
NULL/double, 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. |
top_p |
NULL/double, 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. Defaults to 1 |
tools |
NULL/list, 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. Example value:
list(
# string (required), the type of the tool. Currently, only
# 'function' is supported
type = "function",
# list (required)
function = list(
# string (optional)
description = "some description",
# string (required), the name of the function to be called.
# Must be a-z, A-Z, 0-9, or contain underscores and dashes,
# with a maximum length of 64
name = "functionname",
# list (optional), the parameters the functions accepts,
# described as a JSON Schema object. Omitting parameters
# defines a function with an empty parameter list.
parameters = list()
)
)
|
tool_choice |
NULL/string/list, 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 list 'list(type = "function", function": list(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. |
user |
NULL/string, a unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. See https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids |
api_key |
string, OpenAI API key (see https://platform.openai.com/account/api-keys) |
Value
content of the httr response object or SimpleError (conditions) enhanced with two additional fields: 'status_code' (response$status_code) and 'message_long' (built on response content)
Examples
## Not run:
question <- dialog_df("hi")
res_content <- chat_request(
messages = question,
model = "gpt-3.5-turbo"
)
if (!is_error(res_content)) {
answer <- chat_fetch_messages(res_content)
conversation <- merge_dialog_df(question, answer)
print(conversation)
}
## End(Not run)