class OpenAI::CreateTextCompletion
- OpenAI::CreateTextCompletion
- Reference
- Object
Overview
POST https://api.openai.com/v1/completions
Included Modules
- JSON::Serializable
Extended Modules
- JSON::Schema
Defined in:
open_ai/models/text_completion.crConstructors
Instance Method Summary
-
#best_of : Int32
Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token).
-
#best_of=(best_of : Int32)
Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token).
-
#echo : Bool
Echo back the prompt in addition to the completion
-
#echo=(echo : Bool)
Echo back the prompt in addition to the completion
-
#frequency_penalty : Float64
Number between -2.0 and 2.0.
-
#frequency_penalty=(frequency_penalty : Float64)
Number between -2.0 and 2.0.
-
#logit_bias : Hash(String, Float64) | Nil
Modify the likelihood of specified tokens appearing in the completion.
-
#logit_bias=(logit_bias : Hash(String, Float64) | Nil)
Modify the likelihood of specified tokens appearing in the completion.
-
#logprobs : Int32 | Nil
Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens.
-
#logprobs=(logprobs : Int32 | Nil)
Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens.
-
#max_tokens : Int32
The maximum number of tokens to generate in the completion.
-
#max_tokens=(max_tokens : Int32)
The maximum number of tokens to generate in the completion.
-
#model : String
the model id
-
#model=(model : String)
the model id
-
#num_completions : Int32
How many completions to generate for each prompt.
-
#num_completions=(num_completions : Int32)
How many completions to generate for each prompt.
-
#presence_penalty : Float64
Number between -2.0 and 2.0.
-
#presence_penalty=(presence_penalty : Float64)
Number between -2.0 and 2.0.
-
#prompt : String | Array(String) | Nil
The prompt(s) to generate completions for
-
#prompt=(prompt : String | Array(String) | Nil)
The prompt(s) to generate completions for
-
#stop : String | Array(String) | Nil
Up to 4 sequences where the API will stop generating further tokens.
-
#stop=(stop : String | Array(String) | Nil)
Up to 4 sequences where the API will stop generating further tokens.
-
#stream : Bool
Whether to stream back partial progress.
-
#stream=(stream : Bool)
Whether to stream back partial progress.
-
#suffix : String | Nil
The suffix that comes after a completion of inserted text.
-
#suffix=(suffix : String | Nil)
The suffix that comes after a completion of inserted text.
-
#temperature : Float64
What sampling temperature to use, between 0 and 2.
-
#temperature=(temperature : Float64)
What sampling temperature to use, between 0 and 2.
-
#top_p : Float64
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
-
#top_p=(top_p : Float64)
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
-
#user : String | Nil
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
-
#user=(user : String | Nil)
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
Constructor Detail
Instance Method Detail
Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. best_of must be greater than num_completions
Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. best_of must be greater than num_completions
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.
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.
Modify the likelihood of specified tokens appearing in the completion. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs
Modify the likelihood of specified tokens appearing in the completion. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs
Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens.
Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens.
The maximum number of tokens to generate in the completion. Most models have a context length of 2048 tokens (except for the newest models, which support 4096). The token count of your prompt plus max_tokens cannot exceed the model's context length.
The maximum number of tokens to generate in the completion. Most models have a context length of 2048 tokens (except for the newest models, which support 4096). The token count of your prompt plus max_tokens cannot exceed the model's context length.
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.
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.
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
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.
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.
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. Alter this or temperature but not both.
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. Alter this or temperature but not both.
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.