Note: this feature uses @dqbd/tiktoken which in turns uses WebAssembly
to perform re-tokenization for every single character typed (there's
no reusing/smart caching of blocks). This may be super heavy while being
super useful - we'll see what people say.
Note the usage of Async webAssembly is enabled in the 'webpack' config
within next.config.js.
Chats are exported to paste.gg, are unlisted by default, and expire
in 30 days by default. The user is also provided with the deletion
key which will be only shown at the time of creation, and it's needed
to take down the paste.
Rendering looks quite great, including code and turns.
Closes#32. Enable Users / Deployments to change the host where
OpenAI API calls are directed to. This enables project like
[Helicone](https://www.helicone.ai/) (Observability of LLM ops)
for tracking prompt/responses quality in real-time.
Configuration:
- User: App > Settings > Advanced > API host (e.g. "oai.hconeai.com")
- Deployment: set the 'API_API_HOST=...' environment variable
User takes precedence over deployment over api.openai.com. Realtime
switching in chat apps works well.
Note: the Helicone team is fixing dashboard reporting for 'streaming'
over the /v1/chat/completions endpoint.
The package makes the App slower to load, and I am not
aware of people using the Code
Execution feature
If someone still wants it, we can quickly revert
this commit and add it back (or you can use an older
official/preview build on Vercel)
Note: some older chats will lost the name of the model
but they'll regain it fast. And now the system purpose
that originated the message is captured, as well as
the typing indication
Enrico Ros