or13/Open AI

Access GPT-3 completions from openai.com

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
Runtime
Deprecated runtime
namedescriptionrequireddefault
api-keyOpen AI api key.
engineEngines describe and provide access to these models. You can also customize our base models for your specific use case with fine-tuning. See: https://beta.openai.com/docs/engines/overview yes
promptThe prompt you would like a completion for. See: https://beta.openai.com/examples. yes
temperatureWhat 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. Learn more: https://beta.openai.com/docs/api-reference/completions/create#completions/temperature yes
max_tokensThe 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. Most models have a context length of 2048 tokens (except for the newest models, which support 4096). Learn more: https://beta.openai.com/docs/api-reference/completions/create#completions/create-max_tokens yes
top_pAn 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. Learn more: https://beta.openai.com/docs/api-reference/completions/create#completions/create-top_p yes
frequency_penaltyNumber 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. Learn more: https://beta.openai.com/docs/api-reference/completions/create#completions/create-frequency_penalty yes
presence_penaltyNumber 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. Learn more: https://beta.openai.com/docs/api-reference/completions/create#completions/create-presence_penalty yes
namedescription
jsonThe output in as json.
textThe output in as text.