Skip to content

Latest commit

 

History

History
52 lines (46 loc) · 5.17 KB

CompletionsCreateRequest.md

File metadata and controls

52 lines (46 loc) · 5.17 KB
Raw

AzureOpenaiClient::CompletionsCreateRequest

Properties

Name Type Description Notes
prompt CompletionsCreateRequestPrompt [optional]
max_tokens Integer The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096). Has minimum of 0. [optional][default to 16]
temperature Float What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend altering this or top_p but not both. [optional][default to 1]
top_p Float 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. [optional][default to 1]
logit_bias Object 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 GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs. 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. As an example, you can pass {&quot;50256&quot; &#58; -100} to prevent the < endoftext
user String A unique identifier representing your end-user, which can help monitoring and detecting abuse [optional]
n Integer How many completions to generate for each prompt. Minimum of 1 and maximum of 128 allowed. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop. [optional][default to 1]
stream Boolean Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. [optional][default to false]
logprobs Integer Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. Minimum of 0 and maximum of 5 allowed. [optional]
model String ID of the model to use. You can use the Models_List operation to see all of your available models, or see our Models_Get overview for descriptions of them. [optional]
suffix String The suffix that comes after a completion of inserted text. [optional]
echo Boolean Echo back the prompt in addition to the completion [optional][default to false]
stop CompletionsCreateRequestStop [optional]
completion_config String [optional]
cache_level Integer can be used to disable any server-side caching, 0=no cache, 1=prompt prefix enabled, 2=full cache [optional]
presence_penalty Float 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. [optional][default to 0]
frequency_penalty Float 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. [optional][default to 0]
best_of Integer Generates best_of completions server-side and returns the &quot;best&quot; (the one with the highest log probability per token). Results cannot be streamed. When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop. Has maximum value of 128. [optional]

Example

require 'azure_openai_client'

instance = AzureOpenaiClient::CompletionsCreateRequest.new(
  prompt: null,
  max_tokens: 16,
  temperature: 1,
  top_p: 1,
  logit_bias: null,
  user: null,
  n: 1,
  stream: null,
  logprobs: null,
  model: davinci,
  suffix: null,
  echo: null,
  stop: null,
  completion_config: null,
  cache_level: null,
  presence_penalty: null,
  frequency_penalty: null,
  best_of: null
)