Expand description
OpenAI endpoint collection
§OpenAI
§Introduction
This module provides functionalities accessable from OpenAI’s RESTful API endpoints.
You should have a valid API Key first. Put the key in config.yml, see
README.md for instance.
These types are re-exported from submodules:
Audio: audio transcriptions and translations;ChatCompletion: ChatGPT like capabilities for text/code completion;Completion: GPT-3 based text/code completion;Edit: text content manipulation;Embedding: Ada based embedding extraction;Moderation: content violation detection;Model: an enum represents all available OpenAI public models.
§Support List
| Category | Variant | Tested Models | Stream |
|---|---|---|---|
| Chat completions | - | gpt-4-turbo-preview, gpt-4-0125-preview, gpt-4-1106-vision-preview, gpt-4-1106-preview, gpt-4-vision-preview, gpt-4, gpt-4-0314, gpt-4-0613, gpt-3.5-turbo-0125, gpt-3.5-turbo-1106, gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-3.5-turbo-16k-0613, gpt-3.5-turbo-0613, gpt-3.5-turbo-0301, text-davinci-003, text-davinci-002, code-davinci-0021 | yes |
| Completions | - | gpt-4-turbo-preview, gpt-4-0125-preview, gpt-4-1106-vision-preview, gpt-4-1106-preview, gpt-4-vision-preview, gpt-4, gpt-4-0314, gpt-4-0613, gpt-3.5-turbo-0125, gpt-3.5-turbo-1106, gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-3.5-turbo-16k-0613, gpt-3.5-turbo-0613, gpt-3.5-turbo-0301, text-davinci-003 | yes |
| Edits | - | text-davinci-edit-001, code-davinci-edit-001 | - |
| Images | Generations | dall-e-2, dall-e-3 | - |
| Images | Edits | dall-e-2 | - |
| Images | Variations | dall-e-2 | - |
| Embeddings | - | text-embedding-ada-0022 | - |
| Audios | Transcriptions | whisper-1 | - |
| Audios | Translation | whisper-1 | - |
| Moderation | - | text-moderation-latest3, text-moderation-stable | - |
Note:
- Updated on Feburary 22nd, 2024.
- OpenAI’s Fine Tunes endpoints are currently not supported.
- OpenAI’s Assistants endpoints are currently not supported.
GPT-4/GPT-4-0314/GPT-4-0613 tested, GPT-4-32K/GPT-4-32K-0314 not tested because developer currently only has access to 8K token ones (May 6th, 2023). ↩
You may notice the actual model behind Embedding API to be
text-embedding-ada-002-v2(March 23rd, 2023). ↩OpenAI’s responses for moderation indicate usage of
text-moderation-004model (March 23rd, 2023). But developers cannot use its API endpoints to specify variants other thantext-moderation-latestandtext-moderation-stable. ↩
Re-exports§
pub use apis::chat_completion::ChatCompletion;pub use apis::completion::Completion;pub use apis::edit::Edit;pub use apis::image::Image;pub use apis::embedding::Embedding;pub use apis::audio::Audio;pub use apis::moderation::Moderation;pub use types::model::Model;