sparknlp.annotator.openai.openai_completion#
Contains classes for OpenAICompletion.
Module Contents#
Classes#
Transformer that makes a request for OpenAI Completion API for each executor. |
- class OpenAICompletion(classname='com.johnsnowlabs.ml.ai.OpenAICompletion', java_model=None)[source]#
Transformer that makes a request for OpenAI Completion API for each executor.
See OpenAI API Doc: https://platform.openai.com/docs/api-reference/completions/create for reference
Input Annotation types
Output Annotation type
DOCUMENTDOCUMENT- Parameters:
- model
ID of the OpenAI model to use
- suffix
The suffix that comes after a completion of inserted text
- maxTokens
The maximum number of tokens to generate in the completion.
- temperature
What sampling temperature to use, between 0 and 2
- topP
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass
- numberOfCompletions
How many completions to generate for each prompt.
- logprobs
Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens.
- echo
Echo back the prompt in addition to the completion
- stop
Up to 4 sequences where the API will stop generating further tokens.
- presencePenalty
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.
- frequencyPenalty
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.
- bestOf
Generates best_of completions server-side and returns the best (the one with the highest log probability per token).
- logitBias
Modify the likelihood of specified tokens appearing in the completion.
- user
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
- I had the pleasure of dining at La Fiorita recently, and it was a truly delightful experience! The menu boasted a wonderful selection of classic Italian dishes, all exquisitely prepared and presented. The service staff was friendly and attentive and really, {}, []}]|
|[{document, 0, 227,
- I recently visited Barbecue Joe’s for dinner and it was amazing! The menu had so many items to choose from including pulled pork, smoked turkey, brisket, pork ribs, and sandwiches. I opted for the pulled pork sandwich and let, {}, []}] |
|[{document, 0, 172,
- {
- “review”: {
“overallRating”: 4, “reviewBody”: “I enjoyed my meal at this restaurant. The food was flavourful, well-prepared and beautifully presented., {}, []}] |
- setModel(value)[source]#
Sets model ID of the OpenAI model to use
- Parameters:
- valuestr
ID of the OpenAI model to use
- setSuffix(value)[source]#
Sets the suffix that comes after a completion of inserted text.
- Parameters:
- valuestr
The suffix that comes after a completion of inserted text.
- setMaxTokens(value)[source]#
- Sets the maximum number of tokens to generate in the completion.
The token count of your prompt plus max_tokens cannot exceed the model’s context length.
- Parameters:
- valueint
The maximum number of tokens to generate in the completion.
- setTemperature(value)[source]#
Sets 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.
- Parameters:
- valuefloat
What sampling temperature to use, between 0 and 2
- setTopP(value)[source]#
Sets 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.
- Parameters:
- valuefloat
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass
- setNumberOfCompletions(value)[source]#
Sets how many completions to generate for each prompt.
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.
- Parameters:
- valueint
How many completions to generate for each prompt.
- setLogprobs(value)[source]#
Sets 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. The maximum value for logprobs is 5.
- Parameters:
- valueint
How many completions to generate for each prompt.
- setEcho(value)[source]#
Sets echo back the prompt in addition to the completion
- Parameters:
- valuestr
Echo back the prompt in addition to the completion
- setStop(value)[source]#
Sets Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
- Parameters:
- valueList[str]
Up to 4 sequences where the API will stop generating further tokens.
- setPresencePenalty(value)[source]#
Sets values to penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.
- Parameters:
- valueint
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.
- setFrequencyPenalty(value)[source]#
- Sets values to penalize new tokens based on their existing frequency in the text so far,
decreasing the model’s likelihood to repeat the same line verbatim.
- Parameters:
- valueint
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.
- setBestOf(value)[source]#
Sets best_of completions server-side and returns the “best” (the one with the highest log probability per token)
- Parameters:
- valueint
Generates best_of completions server-side and returns the “best” (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.
- setLogitBias(value)[source]#
Sets the likelihood of specified tokens appearing in the completion
- Parameters:
- valuedict
- 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 {“50256”: -100} to prevent the <|endoftext|> token from being generated.