I ended up making a native Mac playground as I was finding myself spending hours on end playing with the API in the OpenAI playground—only I wasn’t satisfied with the lack of ChatML in the export and the interface for browsing and restoring history was too clunky for fast iteration and retrieval. The playground is also currently limiting the parameters and some of the ranges.
The app is immutable by design with both immediate time travel and automatic versioning. It’s written in Swift and a bit of Rust for the tokenizer extracted from tiktoken. It is faster than you expect it to be.
- It has support for variants, which is the
nparameter in the chat completion API.
- It shows model- and ChatML-aware tokens and cost, and it dynamically adjusts response length in function of prompt length and context length.
- It supports hiding runs that are not useful, marking the ones that are notable, and going through the ancestry of the current run.
- It also has support for examples, as specified in ChatML, conversation names and personal and local-only notes.
- The full-text search works across all stored text and it has support for
phrasematching; the results are time-ordered rather than ranked for the time being.
- There are several shortcuts and more are coming so that the app can be used entirely by keyboard.
- You can export to JSON and all data is exported.
- It is sandboxed and notarized. The API keys are stored securely in the Keychain.
Next I plan to implement combinatorial runs (mixing multiple values of the same parameter and multiple models as well) and full Markdown support.
All of OpenAI’s conversational models are supported (GPT 3.5, GPT 4 8K, GPT 4 32K), more to come.
Give it a try. Any and all feedback welcome! Thoughts and questions as well!