feat(providers): add Sarvam preset to the provider wizard - #205
Merged
plombeer31 merged 1 commit intoAug 21, 2026
Conversation
- Adds a Sarvam entry to PROVIDER_PRESETS between SambaNova and Together AI, resolving to the existing openai-compatible kind - Verified live: https://api.sarvam.ai/v1/models answers 200 with a data array keyless (sarvam-105b, sarvam-105b-conversations), and a bogus sibling path answers 404 — the preset admission bar
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Follow-up to the closed #129, per the maintainer's guidance: this is a preset-only addition — no new provider kind.
Change: one
PROVIDER_PRESETSentry between SambaNova and Together AI, resolving to the existingopenai-compatiblekind like every other preset./v1/modelsconfirmation (probed live 2026-08-20, per the file's admission bar):GET https://api.sarvam.ai/v1/models→ 200 with adataarray, keyless:sarvam-105b,sarvam-105b-conversationsGET https://api.sarvam.ai/v1/definitely-not-a-route→ 404 (the host actually routes/v1/models)Because the list answers keyless (same as SambaNova / Ollama Cloud / Novita / Nous), the entry sets
listsModelsWithoutKey: true, so the wizard skips the key screen. TheSARVAM_API_KEYenv var is still wired for chat requests that need it.Verified:
tsc --noEmitclean, preset tests (sort order, keyless marking) pass.