Allow AI interactions to be proxied through Zed's server so you don't need an API key (#7367)

Co-authored-by: Antonio <antonio@zed.dev>

Resurrected this from some assistant work I did in Spring of 2023.
- [x] Resurrect streaming responses
- [x] Use streaming responses to enable AI via Zed's servers by default
(but preserve API key option for now)
- [x] Simplify protobuf
- [x] Proxy to OpenAI on zed.dev
- [x] Proxy to Gemini on zed.dev
- [x] Improve UX for switching between openAI and google models
- We current disallow cycling when setting a custom model, but we need a
better solution to keep OpenAI models available while testing the google
ones
- [x] Show remaining tokens correctly for Google models
- [x] Remove semantic index
- [x] Delete `ai` crate
- [x] Cloud front so we can ban abuse
- [x] Rate-limiting
- [x] Fix panic when using inline assistant
- [x] Double check the upgraded `AssistantSettings` are
backwards-compatible
- [x] Add hosted LLM interaction behind a `language-models` feature
flag.

Release Notes:

- We are temporarily removing the semantic index in order to redesign it
from scratch.

---------

Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Thorsten <thorsten@zed.dev>
Co-authored-by: Max <max@zed.dev>
This commit is contained in:
Nathan Sobo 2024-03-19 12:22:26 -06:00 committed by GitHub
parent 905a24079a
commit 8ae5a3b61a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
87 changed files with 3647 additions and 8937 deletions

View file

@ -149,7 +149,10 @@ messages!(
(CallCanceled, Foreground),
(CancelCall, Foreground),
(ChannelMessageSent, Foreground),
(CompleteWithLanguageModel, Background),
(CopyProjectEntry, Foreground),
(CountTokensWithLanguageModel, Background),
(CountTokensResponse, Background),
(CreateBufferForPeer, Foreground),
(CreateChannel, Foreground),
(CreateChannelResponse, Foreground),
@ -160,6 +163,7 @@ messages!(
(DeleteChannel, Foreground),
(DeleteNotification, Foreground),
(DeleteProjectEntry, Foreground),
(EndStream, Foreground),
(Error, Foreground),
(ExpandProjectEntry, Foreground),
(ExpandProjectEntryResponse, Foreground),
@ -211,6 +215,7 @@ messages!(
(JoinProjectResponse, Foreground),
(JoinRoom, Foreground),
(JoinRoomResponse, Foreground),
(LanguageModelResponse, Background),
(LeaveChannelBuffer, Background),
(LeaveChannelChat, Foreground),
(LeaveProject, Foreground),
@ -300,6 +305,8 @@ request_messages!(
(Call, Ack),
(CancelCall, Ack),
(CopyProjectEntry, ProjectEntryResponse),
(CompleteWithLanguageModel, LanguageModelResponse),
(CountTokensWithLanguageModel, CountTokensResponse),
(CreateChannel, CreateChannelResponse),
(CreateProjectEntry, ProjectEntryResponse),
(CreateRoom, CreateRoomResponse),