Commit graph

59 commits

Author SHA1 Message Date
Max Brunsfeld
b1c69c2178
Fix usage recording in llm service (#16044)
Release Notes:

- N/A

Co-authored-by: Marshall <marshall@zed.dev>
2024-08-09 11:48:18 -07:00
Max Brunsfeld
225726ba4a
Remove code paths that skip LLM db in prod (#16008)
Release Notes:

- N/A
2024-08-09 10:41:50 -04:00
Max Brunsfeld
06625bfe94
Apply rate limits in LLM service (#15997)
Release Notes:

- N/A

---------

Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
2024-08-08 15:46:33 -07:00
Bennet Bo Fenner
514b79e461
collab: Always use newest anthropic model version (#15978)
When Anthropic releases a new version of their models, Zed AI users
should always get access to the new version even when using an old
version of zed.

Co-Authored-By: Thorsten <thorsten@zed.dev>

Release Notes:

- N/A

Co-authored-by: Thorsten <thorsten@zed.dev>
2024-08-08 15:24:08 +02:00
Marshall Bowers
7f6d0919c9
collab: Setup database for LLM service (#15882)
This PR puts the initial infrastructure for the LLM service's database
in place.

The LLM service will be using a separate Postgres database, with its own
set of migrations.

Currently we only connect to the database in development, as we don't
yet have the database setup for the staging/production environments.

Release Notes:

- N/A
2024-08-06 17:18:08 -04:00
Marshall Bowers
cf5f4dddf5
Authorize access to language model providers based on country (#15859)
This PR updates the LLM service to authorize access to language model
providers based on the requester's country.

We detect the country using Cloudflare's
[`CF-IPCountry`](https://developers.cloudflare.com/fundamentals/reference/http-request-headers/#cf-ipcountry)
header.

The country code is then checked against the list of supported countries
for the given LLM provider. Countries that are not supported will
receive an `HTTP 451: Unavailable For Legal Reasons` response.

Release Notes:

- N/A
2024-08-06 11:49:04 -04:00
Marshall Bowers
ca9511393b
collab: Add support for more providers to the LLM service (#15832)
This PR adds support for additional providers to the LLM service:

- OpenAI
- Google
- Custom Zed models (through Hugging Face)

Release Notes:

- N/A
2024-08-05 21:16:18 -04:00
Max Brunsfeld
8e9c2b1125
Introduce a separate backend service for LLM calls (#15831)
This PR introduces a separate backend service for making LLM calls.

It exposes an HTTP interface that can be called by Zed clients. To call
these endpoints, the client must provide a `Bearer` token. These tokens
are issued/refreshed by the collab service over RPC.

We're adding this in a backwards-compatible way. Right now the access
tokens can only be minted for Zed staff, and calling this separate LLM
service is behind the `llm-service` feature flag (which is not
automatically enabled for Zed staff).

Release Notes:

- N/A

---------

Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
2024-08-05 20:26:21 -04:00
Max Brunsfeld
27779e33fb
Refactor: Restructure collab main function to prepare for new subcommand: serve llm (#15824)
This is just a refactor that we're landing ahead of any functional
changes to make sure we haven't broken anything.

Release Notes:

- N/A

Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Jason <jason@zed.dev>
2024-08-05 12:07:38 -07:00