langchain - 💡(How to fix) Fix Add langchain-nebius as a partner package under libs/partners/ [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
langchain-ai/langchain#37169Fetched 2026-05-05 05:43:50
View on GitHub
Comments
1
Participants
2
Timeline
5
Reactions
0
Author
Timeline (top)
closed ×1commented ×1labeled ×1mentioned ×1
RAW_BUFFERClick to expand / collapse

Submission checklist

  • This is a feature request, not a bug report or usage question.
  • I added a clear and descriptive title that summarizes the feature request.
  • I used the GitHub search to find a similar feature request and didn't find it.
  • I checked the LangChain documentation and API reference to see if this feature already exists.
  • This is not related to the langchain-community package.

Package

langchain (specifically: a new libs/partners/nebius/ directory)

Feature Description

Add langchain-nebius as a first-party partner integration under libs/partners/, matching the pattern recently used for openrouter (#35211) and perplexity (#30618).

Use Case

Nebius runs Token Factory (formerly Nebius AI Studio), a hosted inference platform for 60+ open-weight models including Llama, DeepSeek, Qwen, Mistral, and Kimi families. It's increasingly used as a cost-competitive alternative to other inference providers in the same tier (Fireworks, Groq, Together) for LangChain and LangGraph workloads.

A standalone langchain-nebius package already exists at https://github.com/nebius/langchain-nebius (PyPI: https://pypi.org/project/langchain-nebius/, currently v0.1.3). It exposes:

  • ChatNebius — chat model (extends BaseChatOpenAI; supports tool calling, structured output, JSON mode, streaming)
  • NebiusEmbeddings
  • NebiusRetriever
  • NebiusRetrievalTool and nebius_search

Nebius is also already listed in the LangChain provider docs at https://docs.langchain.com/oss/python/integrations/providers/nebius. The remaining gap is being colocated in the langchain monorepo so the package benefits from:

  • The shared CI / lint / standard-tests infrastructure that other partner packages use
  • langchain-profiles-managed model capability profiles (see libs/partners/fireworks/langchain_fireworks/data/_profiles.py)
  • The release / model-profile-refresh automation
  • Higher discoverability for users browsing libs/partners/

Proposed Solution

  1. Onboarding conversation between LangChain maintainers and the langchain-nebius maintainer (@aktsvigun) on whether to (a) transfer the package into the monorepo, (b) dual-publish, or (c) take a different approach.
  2. If approved, a PR mirroring #35211 (OpenRouter) that ports the existing source under libs/partners/nebius/, adds pyproject.toml/Makefile/CI hooks matching other partners, and wires up the standard ChatModelUnitTests / ChatModelIntegrationTests suites.

Additional Context

  • Maintainer of the existing standalone package: @aktsvigun (Nebius)
  • I've recently sent a series of small PRs and an audit issue against the standalone package: https://github.com/nebius/langchain-nebius/issues/4
  • Happy to coordinate the port / take ownership of the partner-package PR work once a maintainer signals direction, per the template's "do not begin work on a PR unless explicitly assigned" guidance.

extent analysis

TL;DR

The proposed solution involves onboarding the langchain-nebius package into the LangChain monorepo through an onboarding conversation between maintainers.

Guidance

  • Discuss the onboarding approach with LangChain maintainers and the langchain-nebius maintainer to decide on transferring, dual-publishing, or taking a different approach.
  • If approved, create a PR to port the existing source under libs/partners/nebius/ and add necessary configuration files and tests.
  • Ensure the ported package benefits from shared CI, lint, and standard-tests infrastructure, as well as langchain-profiles-managed model capability profiles.
  • Coordinate with the maintainer to take ownership of the partner-package PR work once direction is signaled.

Notes

The success of this proposal depends on the outcome of the onboarding conversation and the approval of LangChain maintainers.

Recommendation

Apply workaround: Coordinate with maintainers to discuss the onboarding approach, as this will determine the next steps for integrating langchain-nebius into the LangChain monorepo.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

langchain - 💡(How to fix) Fix Add langchain-nebius as a partner package under libs/partners/ [1 comments, 2 participants]