feat(sarvam): add Sarvam provider support - #2423
Open
EshwarCVS wants to merge 1 commit into
Open
Conversation
…ovider
Add first-class Sarvam AI integration for the OpenAI-compatible Indic chat API (sarvam-30b, sarvam-105b) through from_sarvam() and from_provider("sarvam/...").
- Register Sarvam in v2 provider specs, modes, and auto-client routing
- Reuse OpenAI-compatible handlers for TOOLS, JSON_SCHEMA, and MD_JSON
- Default mode to MD_JSON for structured extraction
- Add integration docs, smoke tests, and v2 client/handler coverage
Author
|
@jxnl Please review whenever you can. Open for suggestions. Thanks. |
Author
|
Does this act as a bridge between both |
This was referenced Jul 29, 2026
jxnl
added a commit
that referenced
this pull request
Aug 3, 2026
## Summary - accumulate declared, nested, and unknown numeric OpenAI/Anthropic usage fields across retries while preserving non-numeric metadata - add corrective feedback when a Responses API retry receives no tool call - preserve raw iterable type hints through sync and async v2 parallel-tool wrappers - strengthen API-key-free coverage for current and future SDK usage counters ## Consolidated and superseded items - closes #2493 - consolidates contributor work from #2498, #2500, and #2501 with original commit authorship preserved - supersedes #2497 because it drops unknown `model_extra` counters - supersedes #2499 because its hand-maintained provider field lists would drift as SDKs evolve ## Validation - focused changed-surface suite: `110 passed` - broad offline v2/coverage suite: `2368 passed, 91 skipped, 73 deselected` - Ruff check and format check: passed - scoped `ty check`: passed - `uv lock --check`: passed - pre-commit hooks and `git diff --check`: passed The 73 deselected tests require live provider credentials. An unfiltered local run confirmed its 22 failures were provider network connections in the restricted environment; GitHub provider jobs remain the authoritative validation for those paths. ## Intentionally skipped - provider additions or expansions: #2436, #2435, #2423, #2409, #2384, #2322, #2306, #2298, #2283, #2168, #2086; issues #2408, #2383, #2365, #2260, #2084, #2076 - broad architecture, product, security, or streaming decisions: #2394, #2392, #2357, #2356, #2355, #2351, #2321, #2307, #2287, #2263; issues #2479, #2403, #2393, #2391, #2316, #2272, #2056 - dependency batch: #2433 - nontrivial examples and editorial/resource additions: #2468, #2405, #2401, #2354, #2346, #2311, #2305; issue #2404 These remain open because they need dedicated product, architecture, provider, security, dependency, or editorial review and are not required for the `1.15.5` patch release. <!-- CURSOR_SUMMARY --> --- > [!NOTE] > **Medium Risk** > Changes retry usage totals and reask message content on failure paths; scope is limited and heavily covered by tests, with no auth or data-store changes. > > **Overview** > Bundles three v2 retry and wrapper fixes for a patch release. > > **Retry usage accounting** replaces hand-maintained token field sums with generic `_accumulate_models` on Pydantic usage objects. Numeric fields (including nested models and `model_extra` counters) add across retries; booleans and other non-numeric metadata are not treated as billable. OpenAI and Anthropic paths share this logic. > > **OpenAI Responses reask** appends a user correction when `RESPONSES_TOOLS` validation fails but the output has no tool calls (e.g. reasoning-only), so retries include feedback instead of repeating the same request. > > **Parallel tools** in `patch_v2` skips `prepare_response_model` and does not replace `response_model` with the handler’s prepared wrapper for parallel modes, keeping raw `Iterable[...]` hints so schemas and parsed results include every member type. > > <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit bbddca1. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup> <!-- /CURSOR_SUMMARY -->
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.
Description
Adds Sarvam AI as a first-class Instructor provider for structured outputs on
Indic chat models (
sarvam-30b,sarvam-105b) via Sarvam's OpenAI-compatiblechat completions API.
Users can initialize clients with
from_sarvam()orfrom_provider("sarvam/...").The integration supports
Mode.TOOLS,Mode.JSON_SCHEMA, andMode.MD_JSON,with
Mode.MD_JSONas the default.Changes
Provider.SARVAMin v2 provider specs, modes, andauto_clientfrom_sarvam()factory and_build_sarvam()routingsarvam-30bandsarvam-105bto supported model listsdocs/integrations/sarvam.mdTesting
uv run ruff check instructor tests/llm/test_sarvam tests/v2/test_sarvam_client.py uv run ruff format instructor tests/llm/test_sarvam tests/v2/test_sarvam_client.py uv run pytest tests/v2/test_sarvam_client.py tests/v2/test_client_unified.py -k SARVAM -q uv run pytest tests/llm/test_sarvam/test_simple.py tests/llm/test_sarvam/test_stream.py tests/llm/test_sarvam/test_retries.py -q Live smoke tests require `SARVAM_API_KEY`.