You're seeing just the function create_answer, go back to ExOpenAI.Answers module for more information.
Link to this function

create_answer(examples, examples_context, model, question, opts \\ [])

View Source
This function is deprecated. Deprecated by OpenAI.


create_answer([[String.t()]], String.t(), String.t(), String.t(),
  user: String.t(),
  temperature: float(),
  stop: any(),
  search_model: String.t(),
  return_prompt: boolean(),
  return_metadata: boolean(),
  n: integer(),
  max_tokens: integer(),
  max_rerank: integer(),
  logprobs: integer(),
  logit_bias: map(),
  file: String.t(),
  expand: [map()],
  documents: [String.t()]
) :: {:ok, ExOpenAI.Components.CreateAnswerResponse.t()} | {:error, any()}

Answers the specified question using the provided documents and examples.

The endpoint first searches over provided documents or files to find relevant context. The relevant context is combined with the provided examples and question to create the prompt for completion.

Endpoint: https://api.openai.com/v1/answers

Method: POST

Docs: https://platform.openai.com/docs/api-reference/answers

Required Arguments:

  • examples: List of (question, answer) pairs that will help steer the model towards the tone and answer format you'd like. We recommend adding 2 to 3 examples.

Example: [['What is the capital of Canada?', 'Ottawa'], ['Which province is Ottawa in?', 'Ontario']]

  • examples_context: A text snippet containing the contextual information used to generate the answers for the examples you provide.

Example: Ottawa, Canada's capital, is located in the east of southern Ontario, near the city of Montréal and the U.S. border.

  • model: ID of the model to use for completion. You can select one of ada, babbage, curie, or davinci.

  • question: Question to get answered.

Example: What is the capital of Japan?

Optional Arguments:

  • documents: List of documents from which the answer for the input question should be derived. If this is an empty list, the question will be answered based on the question-answer examples.

You should specify either documents or a file, but not both.

Example: "['Japan is an island country in East Asia, located in the northwest Pacific Ocean.', 'Tokyo is the capital and most populous prefecture of Japan.']"

  • expand: If an object name is in the list, we provide the full information of the object; otherwise, we only provide the object ID. Currently we support completion and file objects for expansion.

  • file: The ID of an uploaded file that contains documents to search over. See upload file for how to upload a file of the desired format and purpose.

You should specify either documents or a file, but not both.

  • logit_bias: 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.

  • logprobs: 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.

The maximum value for logprobs is 5. If you need more than this, please contact us through our Help center and describe your use case.

When logprobs is set, completion will be automatically added into expand to get the logprobs.

  • max_rerank: The maximum number of documents to be ranked by Search when using file. Setting it to a higher value leads to improved accuracy but with increased latency and cost.

  • max_tokens: The maximum number of tokens allowed for the generated answer

  • n: How many answers to generate for each question.

  • return_metadata: A special boolean flag for showing metadata. If set to true, each document entry in the returned JSON will contain a "metadata" field.

This flag only takes effect when file is set.

  • return_prompt: If set to true, the returned JSON will include a "prompt" field containing the final prompt that was used to request a completion. This is mainly useful for debugging purposes.

  • search_model: ID of the model to use for Search. You can select one of ada, babbage, curie, or davinci.

  • stop: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

  • temperature: 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.

  • user: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Example: "user-1234"