# Allow AI interactions to be proxied through Zed's server so you don't need an API key \(\#7367\) ยท gitcafe/zed [View on GitCafe](https://git.cafe/gitcafe/zed/commit/8ae5a3b61a5e1d5b2483154ac9248fd1818a216b) Repository: [gitcafe/zed](https://git.cafe/gitcafe/zed) Visibility: public Requested revision: 8ae5a3b61a5e1d5b2483154ac9248fd1818a216b Requested commit: 8ae5a3b61a5e1d5b2483154ac9248fd1818a216b Commit: 8ae5a3b61a5e1d5b2483154ac9248fd1818a216b Tree: 1cda8a4d4b8dd2ad13598122b999844238148d76 Author: Nathan Sobo Committer: GitHub ## Message ``` Allow AI interactions to be proxied through Zed's server so you don't need an API key (#7367) Co-authored-by: Antonio 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 Co-authored-by: Antonio Scandurra Co-authored-by: Thorsten Co-authored-by: Max ``` ## Parents - [905a24079a4d2086130d60bd6722bf4ccf85f8bf](https://git.cafe/gitcafe/zed/commit/905a24079a4d2086130d60bd6722bf4ccf85f8bf?format=markdown) [Source at this commit](https://git.cafe/gitcafe/zed/tree/8ae5a3b61a5e1d5b2483154ac9248fd1818a216b?format=markdown)