OpenAI
OpenAI copied to clipboard
Swift community driven package for OpenAI public API
I'd like a way to retrieve a log of previous chats. Anyway thanks for this great api!
The `host` that you supply to `OpenAI.Configuration` is converted into a URL by `buildURL`, which has the scheme hard-coded to `https`. With projects like GPT4All allowing users to run a...
The OpenAI API seems to allow both strings and arrays of strings in order to [batch requests](https://platform.openai.com/docs/guides/rate-limits/batching-requests): Here’s the canonical example from the docs using Python: ``` import openai #...
**Is your feature request related to a problem? Please describe.** Right, it's pretty nice we can init a OpenAI with custom host, like ``` let openAI = OpenAI(configuration: OpenAI.Configuration( token:...
**Is your feature request related to a problem? Please describe.** The Demo App is very Apple-like and I think it would not only be nice to give it some character,...
**Is your feature request related to a problem? Please describe.** The demo app includes a chat example; audio and image generation remains TBD. **Describe the solution you'd like** Using the...
Extend the library by adding fine-tuning capabilities. Add `files` and `fine-tunes` API calls so the library supports model tuning and file retrieval. Documentation * [Files](https://platform.openai.com/docs/api-reference/files) * [Fine-Tunes](https://platform.openai.com/docs/api-reference/fine-tunes)
## What Added a feature to retrieve token usage in stream chat mode. ## Why This functionality is available in the original API and could be useful for some users....
## What This PR adds fully customizable endpoint support. Instead of "just" adding `basePath` you can now pass a fully configured endpoint URL. ## Why Internal/hosted OpenAI Instances sometimes use...
When I want to connect to an OpenAI compatible proxy server (i.e. litellm), it does not accept requests including `/v1` in the URL. - This works `http://localhost:8000/chat/completion` - This does...