Issue Station
Sign In
Tools hereToolbox

langchain - ✅(Solved) Fix langchain-together breaks with v1 versions of langchain-openai and so on [1 pull requests, 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#36104•Fetched 2026-04-08 01:01:56
View on GitHub
Comments
1
Participants
2
Timeline
10
Reactions
0
Author
smartinezbragadosmartinezbragado
Participants
keenborder786keenborder786smartinezbragadosmartinezbragado
Timeline (top)
labeled ×4commented ×1cross-referenced ×1issue_type_added ×1

When i try to use together ai latest version it has deps issues with the existing v1 of other providers: "uv sync --all-packages × No solution found when resolving dependencies for split (python_full_version >= '3.14' and sys_platform == 'win32'): ╰─▶ Because only langchain-together<=0.3.1 is available and traza-ai-core depends on langchain-together>=1.0, we can conclude that traza-ai-core's requirements are unsatisfiable. And because your workspace requires traza-ai-core, we can conclude that your workspace's requirements are unsatisfiable. make: *** [install] Error 1"

Error Message

make: *** [install] Error 1

Error Message and Stack Trace (if applicable)

make: *** [install] Error 1" make: *** [install] Error 1

Root Cause

uv sync --all-packages
  × No solution found when resolving dependencies for split (python_full_version >= '3.14' and sys_platform == 'win32'):
  ╰─▶ Because only langchain-together<=0.3.1 is available and traza-ai-core depends on langchain-together>=1.0, we can conclude that traza-ai-core's requirements are unsatisfiable.
      And because your workspace requires traza-ai-core, we can conclude that your workspace's requirements are unsatisfiable.
make: *** [install] Error 1

Fix Action

Fix / Workaround

  • This is a bug, not a usage question.
  • I added a clear and descriptive title that summarizes this issue.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangChain rather than my code.
  • The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
  • This is not related to the langchain-community package.
  • I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

PR fix notes

PR #36138: fix(together): relax langchain-openai constraint to support v1.x

Description (problem / solution / changelog)

Fixes #36104

Problem

langchain-together pins langchain-openai to ^0.3 (>=0.3,<0.4), which blocks it from being used alongside langchain-openai v1.x+ in the same environment. This causes dependency resolution failures.

Changes

  • pyproject.toml (monorepo root): Add [tool.uv.override-dependencies] to relax the langchain-openai bound to >=0.1,<3 so uv sync resolves without conflicts when langchain-together is a transitive dependency.
  • libs/langchain/pyproject.toml: Tighten the together optional-dep specifier to langchain-together>=0.3 (explicit lower bound) for clarity.

The root cause also lives in langchain-ai/langchain-together where the Poetry constraint should be updated from ^0.3 to >=0.3,<3. This PR addresses what can be fixed on the monorepo side in the meantime.

Changed files

  • docs/docs/integrations/chat/gigachat.ipynb (added, +141/-0)
  • libs/langchain/langchain/chat_models/base.py (modified, +10/-0)
  • libs/langchain/pyproject.toml (modified, +2/-1)
  • pyproject.toml (modified, +6/-0)

Code Example

uv sync --all-packages
  × No solution found when resolving dependencies for split (python_full_version >= '3.14' and sys_platform == 'win32'):
  ╰─▶ Because only langchain-together<=0.3.1 is available and traza-ai-core depends on langchain-together>=1.0, we can conclude that traza-ai-core's requirements are unsatisfiable.
      And because your workspace requires traza-ai-core, we can conclude that your workspace's requirements are unsatisfiable.
make: *** [install] Error 1

---
RAW_BUFFERClick to expand / collapse

Checked other resources

  • This is a bug, not a usage question.
  • I added a clear and descriptive title that summarizes this issue.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangChain rather than my code.
  • The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
  • This is not related to the langchain-community package.
  • I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Package (Required)

  • langchain
  • langchain-openai
  • langchain-anthropic
  • langchain-classic
  • langchain-core
  • langchain-model-profiles
  • langchain-tests
  • langchain-text-splitters
  • langchain-chroma
  • langchain-deepseek
  • langchain-exa
  • langchain-fireworks
  • langchain-groq
  • langchain-huggingface
  • langchain-mistralai
  • langchain-nomic
  • langchain-ollama
  • langchain-openrouter
  • langchain-perplexity
  • langchain-qdrant
  • langchain-xai
  • Other / not sure / general

Related Issues / PRs

No response

Reproduction Steps / Example Code (Python)

uv sync --all-packages
  × No solution found when resolving dependencies for split (python_full_version >= '3.14' and sys_platform == 'win32'):
  ╰─▶ Because only langchain-together<=0.3.1 is available and traza-ai-core depends on langchain-together>=1.0, we can conclude that traza-ai-core's requirements are unsatisfiable.
      And because your workspace requires traza-ai-core, we can conclude that your workspace's requirements are unsatisfiable.
make: *** [install] Error 1

Error Message and Stack Trace (if applicable)

Description

When i try to use together ai latest version it has deps issues with the existing v1 of other providers: "uv sync --all-packages × No solution found when resolving dependencies for split (python_full_version >= '3.14' and sys_platform == 'win32'): ╰─▶ Because only langchain-together<=0.3.1 is available and traza-ai-core depends on langchain-together>=1.0, we can conclude that traza-ai-core's requirements are unsatisfiable. And because your workspace requires traza-ai-core, we can conclude that your workspace's requirements are unsatisfiable. make: *** [install] Error 1"

System Info

uv sync --all-packages × No solution found when resolving dependencies for split (python_full_version >= '3.14' and sys_platform == 'win32'): ╰─▶ Because only langchain-together<=0.3.1 is available and traza-ai-core depends on langchain-together>=1.0, we can conclude that traza-ai-core's requirements are unsatisfiable. And because your workspace requires traza-ai-core, we can conclude that your workspace's requirements are unsatisfiable. make: *** [install] Error 1

extent analysis

Fix Plan

The fix involves resolving the dependency conflict between langchain-together and traza-ai-core.

  • Downgrade traza-ai-core to a version that depends on langchain-together<=0.3.1.
  • Alternatively, upgrade langchain-together to a version that is compatible with traza-ai-core>=1.0, if available.
  • If neither of the above options is feasible, consider using a different version of Python that is compatible with the required dependencies.

Example code to downgrade traza-ai-core:

pip install traza-ai-core==<compatible-version>

Replace <compatible-version> with the actual version number that is compatible with langchain-together<=0.3.1.

Verification

To verify that the fix worked, run the following command:

uv sync --all-packages

If the dependencies are resolved successfully, the command should complete without errors.

Extra Tips

  • Ensure that the versions of langchain-together and traza-ai-core are compatible with each other and with the Python version being used.
  • Consider using a virtual environment to manage dependencies and avoid conflicts with other projects.
  • If using a requirements.txt file, make sure to update it with the compatible versions of the dependencies.

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…
#api#ssr#installation#tensor shape#autograd error

Still need to ship something?

×6

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

Back to top recommendations

TRENDING