chore: update constraints-dev.txt (2026-02-09)

[courtneypacheco]

This PR updates the constraints-dev.txt file using tox -e constraints.

Summary by CodeRabbit

• Chores
  • Updated development dependencies across multiple packages to latest compatible versions
  • Added new dependencies to the project
  • Removed and replaced outdated dependency declarations

[sourcery-ai]

Reviewer's Guide

Regenerated the development constraints file by running tox -e constraints, updating pinned versions for all development dependencies.

File-Level Changes

Change	Details	Files
Regenerate constraints-dev.txt with updated dependency pins	Executed tox -e constraints to refresh all dev dependency versions	constraints-dev.txt

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey @courtneypacheco - I've reviewed your changes and they look great!

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[coderabbitai]

Actionable comments posted: 2

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 6d4dc18 and 1ac4c17.

📒 Files selected for processing (1)

• constraints-dev.txt (2 hunks)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)

• GitHub Check: Sourcery review
• GitHub Check: mypy
• GitHub Check: pylint
• GitHub Check: test: 3.11 on ubuntu-latest

🔇 Additional comments (1)

constraints-dev.txt (1)

134-134: Review premise is incorrect; the cited concern does not apply to this codebase.

The codebase contains direct openai imports, contradicting the review's claim that it imports exclusively via langchain-openai:

• from openai import Client as OpenAIClient (ragas.py)
• from openai.types.chat import ChatCompletionMessageParam (ragas.py)
• import openai (mt_bench_common.py)

The review specifically cites "ResponseFunctionToolCallOutputItem.output" changing from string to string|Array as a potential breaking change. This object type does not appear anywhere in the codebase.

The actual patterns used—client.chat.completions.create() and accessing response.choices[0].message.content—are standard APIs stable across openai 2.x versions. Exception handling uses standard openai exception types present in 2.8.1. The openai==2.8.1 pin satisfies the openai>=1.13.3 requirement.

Likely an incorrect or invalid review comment.

[coderabbitai]

⚠️ Potential issue | 🟠 Major

🧩 Analysis chain

Verify numpy 2.2.6 compatibility across the dependency tree.

Pandas 2.2.2 is the first version generally compatible with numpy 2.0, and the constraints file pins pandas 2.3.3, which should work with numpy 2.2.6. However, numpy 2.2.6 is a significant jump from 1.26.4 with potential breaking changes for compiled extensions (e.g., cupy-cuda12x, scipy, scikit-learn, torch). Modules compiled using NumPy 1.x cannot run in NumPy 2.0.0 and may crash; modules must be recompiled with NumPy 2.0 to support both versions.

Verify that all scientific packages in this constraint file (especially torch 2.6.0, scipy 1.16.3, scikit-learn 1.7.2, cupy-cuda12x 13.6.0, and torchvision 0.21.0) are wheels built with numpy 2.x compatibility.

---

I'll verify the numpy 2.2.6 compatibility concerns in the review comment by checking the constraints file and investigating the compatibility claims.

---

🏁 Script executed:

```shell
#!/bin/bash
# Find and display constraints-dev.txt to verify versions and context
fd -t f 'constraints-dev.txt' --exec cat {} \;

Length of output: 15934

---

🌐 Web query:

numpy 2.2.6 compatibility torch scipy scikit-learn cupy 2024 2025

💡 Result:

Short answer — NumPy 2.2.6 (released May 17, 2025) can break many scientific wheels that were built against NumPy 1.x. Practical compatibility notes:

• NumPy 2.2.6 release date and notes. [1]
• PyTorch: older torch wheels built against NumPy 1.x will error on NumPy 2.x (ABI break); PyTorch added NumPy‑2.0 support in the PyTorch 2.3 development line and CI was updated to support NumPy 2.x — upgrade to a torch wheel built against NumPy 2.x or rebuild from source. If you see “A module that was compiled using NumPy 1.x cannot be run in NumPy 2.x…” the workaround is to upgrade torch to a NumPy‑2‑compatible release or downgrade NumPy to <2.0. [2][3][4]
• SciPy: SciPy releases document explicit NumPy version ranges — many SciPy versions expect NumPy <2.x (or specific upper bounds) so older SciPy wheels will warn/fail with NumPy 2.2.6. Use a SciPy release whose toolchain lists compatibility with NumPy 2.x or downgrade NumPy. Check the SciPy toolchain table for the SciPy version you use. [5][6]
• scikit‑learn: follows NumPy ABI expectations of compiled C extensions; older scikit‑learn wheels built against NumPy 1.x can fail with NumPy 2.x — upgrade scikit‑learn to a wheel built against NumPy 2.x or use numpy<2 if stuck. (scikit‑learn doesn’t yet pin a single universal range; treat it like other compiled packages.) [see PyTorch/vision discussion re: ecosystem transition]. [4]
• CuPy: many CuPy releases historically required NumPy 1.x (older install docs list NumPy 1.*). If you use CuPy, confirm the CuPy release notes/wheels for NumPy‑2 support; otherwise expect to need a CuPy build matched to your NumPy or to keep numpy<2. [7][8]

Actionable guidance

• If you get the “compiled using NumPy 1.x” error: either downgrade NumPy (pip install "numpy<2") or upgrade the affected libraries to versions/wheels built against NumPy 2.x (or rebuild them from source against NumPy ≥2.0). [3][4][7]
• Before changing anything, check the package’s release/CI notes or wheel metadata to confirm which NumPy ABI it was built against.

Sources

1. NumPy releases (includes 2.2.6 entry). [numpy.org news]. [1]
2. PyTorch issues and guidance about NumPy‑2 ABI and required rebuilds / CI updates. [pytorch/pytorch issue threads]. [2][4]
3. Community reports / StackOverflow on the “module compiled using NumPy 1.x” error and practical workarounds (downgrade numpy or upgrade libs). [StackOverflow]. [3]
4. PyTorch/vision discussion noting PyTorch’s NumPy‑2.0 support as part of the 2.3 effort. [pytorch/vision issue]. [4]
5. SciPy toolchain/version tables showing supported NumPy version ranges per SciPy release. [scipy docs]. [5][6]
6. CuPy installation docs (shows many CuPy releases target NumPy 1.x historically — verify current CuPy release notes for NumPy‑2 support). [cupy docs]. [7][8]

If you want, tell me the exact versions of torch, scipy, scikit‑learn or cupy you use and I’ll check whether those specific wheels are known to support NumPy 2.2.6 (or recommend exact versions to upgrade/downgrade).

---

🌐 Web query:

pandas 2.3.3 numpy 2.2 compatibility requirements

💡 Result:

Short answer: pandas 2.3.3 is compatible with NumPy 2.x (including NumPy 2.2). Pandas added general NumPy 2.0 compatibility in the 2.2.x series and later 2.3.x releases continue to support NumPy 2.x. [1][2]

Notes/recommendation:

• If you hit import/runtime errors after upgrading (some third‑party C extensions or optional dependencies have had issues historically), check for patches or pins on those packages (see pandas issue/bug reports). If you need maximum stability, use the wheel provided by your package manager (conda) or pin to the known-working NumPy/pandas pair used in your environment. [3]

Sources:

• pandas "What's new" (2.2.2) — pandas 2.2.2 added general compatibility with NumPy 2.0. [1]
• pandas 2.3.x release notes / what's new (2.3.3). [2]
• Example pandas GitHub issue reporting compatibility/import problems after mixing pandas and NumPy 2.0 (illustrates potential 3rd-party/extension issues). [3]

---

I need to verify the specific package versions flagged in the review. Let me search for their NumPy 2.x compatibility.

Verify numpy 2.2.6 compatibility—critical torch/torchvision version mismatch found.

The verification reveals a more urgent issue than the original concern: torchvision 0.21.0's wheel metadata declares a requirement for torch >=2.8.0, yet constraints pin torch 2.6.0, creating a direct installation conflict. This must be resolved before testing numpy compatibility.

Regarding the numpy 2.2.6 compatibility concern itself:

• SciPy 1.13.0 (April 2024) is the first stable release supporting NumPy 2.x, and scipy 1.16.3 (October 2025) is well within the supported range.
• torch 2.6.0 is post-PyTorch 2.3, which added NumPy 2.x support.
• scikit-learn 1.4.2 includes support for numpy 2, and scikit-learn 1.7.2 is newer.
• CuPy v13 is tested against NumPy 1.22–1.25 only; there is no documented support for numpy 2.x in CuPy 13.6.0. CuPy NumPy 2.0 compatibility work is targeted for CuPy v14, meaning 13.6.0 is not validated for numpy 2.x.

Actions required:

1. Fix the torch/torchvision version mismatch: upgrade torchvision to 0.23+ or downgrade torch to 2.8+.
2. Verify or downgrade cupy-cuda12x compatibility: numpy 2.2.6 wheels built for cupy 13.6.0 have not been tested and may fail at runtime.

🤖 Prompt for AI Agents

In constraints-dev.txt line 120, numpy is pinned to 2.2.6 but the constraints
reveal a critical torch/torchvision mismatch: torchvision 0.21.0 requires torch
>=2.8.0 while constraints pin torch to 2.6.0; update the constraints so torch
and torchvision are compatible (preferably bump torch to >=2.8.0 to match
torchvision, or else pin torchvision to a release that supports torch 2.6), and
separately verify CuPy compatibility with NumPy 2.x (either pin cupy-cuda12x to
a CuPy version that explicitly supports NumPy 2.x or downgrade NumPy to a 1.x
line until CuPy v14+ is available); update the constraints file accordingly and
run a pip dependency resolution check to confirm no further conflicts.

[coderabbitai]

Actionable comments posted: 1

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 06f01e0 and eeb7f5b.

📒 Files selected for processing (1)

• constraints-dev.txt (2 hunks)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)

• GitHub Check: mypy
• GitHub Check: pylint
• GitHub Check: test: 3.11 on ubuntu-latest
• GitHub Check: test: 3.11 on macos-latest
• GitHub Check: Sourcery review

🔇 Additional comments (2)

constraints-dev.txt (2)

78-82: Verify ragas 0.4.0 resolves past LangChain 1.1.x incompatibility.

The past critical issue flagged ragas 0.3.2 incompatibility with LangChain 1.0.7+. Line 193 now pins ragas 0.4.0, which should be compatible with langchain 1.1.2 (line 78), langchain-core 1.1.1 (line 81), and langchain-openai 1.1.0 (line 82). This version bump appears to resolve the prior blocking issue, but verification is recommended to confirm ragas 0.4.0 officially supports LangChain 1.1.x.

Also applies to: 193-193

---

121-121: CuPy 13.6.0 has qualified NumPy 2.x support—monitor for runtime issues.

CuPy v13 is tested against NumPy versions including v2.0, 2.1, v2.2, and v2.3, so the constraint of cupy-cuda12x 13.6.0 with numpy 2.2.6 should work. However, NumPy 2.x support in CuPy v13 was added late in the release cycle and is qualified. Monitor for runtime failures if CuPy calls deprecated NumPy APIs or if wheel builds were not updated for NumPy 2.x compatibility.

Also applies to: 26-26

[coderabbitai]

Actionable comments posted: 2

📜 Review details

Configuration used: defaults

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 29ea0ba and ee54b7c.

📒 Files selected for processing (1)

• constraints-dev.txt

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

• GitHub Check: Sourcery review

🔇 Additional comments (1)

constraints-dev.txt (1)

193-193: Positive: ragas upgrade resolves LangChain compatibility.

The upgrade from ragas==0.3.2 to 0.4.2 appears to address the critical LangChain 1.x incompatibility flagged in past reviews. Verify that ragas 0.4.2 is tested and compatible with the pinned LangChain packages (lines 78–89).

[coderabbitai]

Actionable comments posted: 3

🤖 Fix all issues with AI agents

In `@constraints-dev.txt`:
- Line 26: The CuPy/Numpy ABI mismatch must be resolved: either upgrade
cupy-cuda12x (reference: cupy-cuda12x==13.6.0) to a 14.x release that supports
NumPy 2.x, or downgrade numpy (reference: numpy==2.2.6) to a 1.x (<2.0) pin;
apply the chosen change consistently in constraints-dev.txt (both the cupy and
numpy lines) and run a quick dependency check to ensure downstream packages
(ray, torch, scipy, etc.) remain compatible with the selected NumPy/CuPy
combination before committing.
- Line 230: The constraints file pins incompatible versions: torchvision==0.21.0
requires torch>=2.8.0 but torch is pinned to torch==2.6.0; fix by either
updating the torch pin to a compatible release (e.g., change torch==2.6.0 to
torch==2.8.0) or downgrading torchvision (e.g., change torchvision==0.21.0 to a
0.20.x release) and ensure the chosen change is applied consistently in
constraints-dev.txt and validated against other dependents like accelerate,
torchaudio, xformers, etc.
- Around line 78-89: The constraints list has a version conflict: ragas 0.4.3
requires langchain-core in the 0.2–0.3 range but the file pins
langchain-core==1.2.7; update the constraints to resolve this by either (A)
downgrading langchain-core to a compatible version range (e.g., set
langchain-core to a 0.2.x or 0.3.x pin) to match ragas, or (B) replace ragas
with a LangChain 1.x-compatible fork such as bisheng-ragas-lc1 so
langchain-core==1.2.7 remains valid; adjust the single line(s) containing
langchain-core and ragas accordingly and run dependency resolution to confirm no
further conflicts.

[coderabbitai]

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

🌐 Web query:

ragas 0.4.3 langchain-core 1.2.7 compatibility requirements

💡 Result:

Short answer: ragas 0.4.3 is not guaranteed compatible with langchain‑core 1.2.7.

Why: the official Ragas installation docs (for current stable/v0.x series) require LangChain v0.2–v0.3 style packages and explicitly recommend installing langchain‑core in the 0.2–0.3 range to avoid mismatches. The Ragas PyPI release for 0.4.3 exists (Jan 13, 2026) but the docs still instruct using "langchain-core>=0.2,<0.3". See Ragas install docs. [1][2]

If you need to use LangChain langchain‑core 1.x (e.g., 1.2.7) you have two options:

• Pin langchain‑core to a supported 0.2.x–0.3.x range when using ragas 0.4.3. [1][2]
• Use a LangChain‑compat fork/adapter that targets LangChain v0.3+/1.x (examples exist such as bisheng‑ragas‑lc1) or check the Ragas GitHub for an updated branch that explicitly supports LangChain 1.x. [3][4]

Sources:

• Ragas installation / LangChain dependency recommendation. [1]
• Ragas PyPI (ragas 0.4.3 release). [2]
• Bisheng/compat fork note for LangChain v0.3+/1.x. [3]
• Ragas GitHub (repo and install instructions). [4]

References:
[1] Ragas docs — Installation (recommendation to install "langchain-core>=0.2,<0.3").
[2] PyPI — ragas 0.4.3 release (uploaded Jan 13, 2026).
[3] bisheng-ragas-lc1 PyPI (fork updated for LangChain v0.3+/core 1.x compatibility).
[4] Ragas GitHub repository and installation notes.

---

🌐 Web query:

ragas 0.4.3 release notes langchain dependencies

💡 Result:

Summary — Ragas 0.4.3 + LangChain dependency guidance

• Ragas 0.4.3 (released Jan 13, 2026): adds advanced prompt optimization via DSPyOptimizer, system-prompt support for several LLM wrappers, and multiple bugfixes (caching, CI, etc.). [1]

• Where to get the release: ragas 0.4.3 wheel and sdist are on PyPI (uploaded Jan 13, 2026). [2]

• LangChain-related dependency guidance for Ragas: when using LangChain-backed LLMs (e.g., langchain_openai / ChatOpenAI), explicitly install langchain-core and langchain-openai to avoid version conflicts; example bounds shown in Ragas docs: pip install -U "langchain-core>=0.2,<0.3" "langchain-openai>=0.1,<0.2" openai. (Ragas also exposes integrations under ragas.integrations.langchain.) [3][4]

Sources

1. RAGAS changelog (v0.4.3 release notes). [1]
2. PyPI — ragas 0.4.3 release files. [2]
3. Ragas installation docs (LangChain dependency guidance). [3]

Would you like the exact pip commands or the full changelog text?

---

Incompatible dependency versions: ragas 0.4.3 requires langchain-core 0.2–0.3, not 1.2.7.

Ragas 0.4.3 explicitly pins langchain-core to the 0.2–0.3 range. The constraints file specifies langchain-core==1.2.7 (line 81), which is outside the supported range and will cause import or API mismatches at runtime. Either downgrade langchain-core to the 0.2–0.3 range to match ragas 0.4.3, or switch to a LangChain 1.x-compatible fork such as bisheng-ragas-lc1. This blocks successful CI runs.

🤖 Prompt for AI Agents

In `@constraints-dev.txt` around lines 78 - 89, The constraints list has a version
conflict: ragas 0.4.3 requires langchain-core in the 0.2–0.3 range but the file
pins langchain-core==1.2.7; update the constraints to resolve this by either (A)
downgrading langchain-core to a compatible version range (e.g., set
langchain-core to a 0.2.x or 0.3.x pin) to match ragas, or (B) replace ragas
with a LangChain 1.x-compatible fork such as bisheng-ragas-lc1 so
langchain-core==1.2.7 remains valid; adjust the single line(s) containing
langchain-core and ragas accordingly and run dependency resolution to confirm no
further conflicts.

[coderabbitai]

Actionable comments posted: 3

🤖 Fix all issues with AI agents

In `@constraints-dev.txt`:
- Line 26: CI is broken because cupy-cuda12x==13.6.0 is built against NumPy 1.x
and incompatible with numpy==2.2.6; fix by either upgrading CuPy to a NumPy‑2.x
compatible release (bump cupy-cuda12x to v14.x or later) or pinning NumPy to a
1.x release (e.g., change numpy to 1.26.4), and update the constraint lines for
cupy-cuda12x and/or numpy accordingly; after changing the constraint, run
dependency checks against ray, torch, scipy, scikit-learn, pandas, and
transformers to ensure the chosen combination is compatible and adjust versions
if any conflicts appear.
- Line 230: The pinned torch version "torch==2.6.0" conflicts with the
torchvision requirement (torchvision==0.21.0 requires torch>=2.8.0); update the
constraint by either upgrading torch to a compatible release (e.g., change the
"torch==2.6.0" pin to "torch==2.8.0" or later) or downgrading the torchvision
pin to a 0.20.x that supports torch 2.6 (e.g., "torchvision==0.20.x"); after
making the change, verify compatibility with other torch-dependent packages
referenced in the file (torchaudio, accelerate, peft, xformers, vllm) and ensure
no other constraints (e.g., the other occurrence around the torchvision line)
conflict before committing.
- Line 81: The constraints file pins langchain-core==1.2.7 which conflicts with
ragas 0.4.3 (ragas requires langchain-core>=0.2,<0.3), so update the constraints
to resolve the dependency: either bump ragas to a release compatible with
langchain-core 1.x (e.g., ragas >=0.5.x) or revert langchain-core to a
0.2.x/0.3.x series that satisfies ragas 0.4.3; after changing the version, run a
dependency resolution (pip/pip-compile) to ensure langchain,
langchain-community, langchain-openai, langchain-text-splitters and langgraph
packages remain compatible and adjust their pins if needed until the install
succeeds.

[coderabbitai]

⚠️ Potential issue | 🔴 Critical

CRITICAL: CuPy 13.6.0 incompatible with NumPy 2.2.6 — blocking CI.

Based on past review verification, cupy-cuda12x==13.6.0 was built against the NumPy 1.x ABI and is incompatible with numpy==2.2.6. NumPy 2.x introduced breaking ABI changes; CuPy wheels compiled using NumPy 1.x cannot run with NumPy 2.x and will crash at import time. This is directly causing the CI failures indicated by the ci-failure label.

Required fix: Either:

• Upgrade CuPy to v14.x or later (with NumPy 2.x support), or
• Downgrade NumPy to <2.0 (e.g., numpy==1.26.4)

Verify the chosen solution is compatible with other NumPy-dependent packages (ray, torch, scipy, scikit-learn, pandas, transformers).

🤖 Suggested fix

Option A (upgrade CuPy):

-cupy-cuda12x==13.6.0
+cupy-cuda12x==14.0.0  # (verify latest 14.x release on PyPI)

Option B (downgrade NumPy):

-numpy==2.2.6
+numpy==1.26.4

Also applies to: 121-121

🤖 Prompt for AI Agents

In `@constraints-dev.txt` at line 26, CI is broken because cupy-cuda12x==13.6.0 is
built against NumPy 1.x and incompatible with numpy==2.2.6; fix by either
upgrading CuPy to a NumPy‑2.x compatible release (bump cupy-cuda12x to v14.x or
later) or pinning NumPy to a 1.x release (e.g., change numpy to 1.26.4), and
update the constraint lines for cupy-cuda12x and/or numpy accordingly; after
changing the constraint, run dependency checks against ray, torch, scipy,
scikit-learn, pandas, and transformers to ensure the chosen combination is
compatible and adjust versions if any conflicts appear.

[coderabbitai]

⚠️ Potential issue | 🔴 Critical

CRITICAL: ragas 0.4.3 incompatible with langchain-core 1.2.7 — blocking CI.

Based on past review verification, ragas 0.4.3 explicitly requires langchain-core>=0.2,<0.3, but line 81 pins langchain-core==1.2.7, which is outside the supported range. This creates an unresolvable dependency conflict that prevents pip installation, directly causing the CI failures indicated by the ci-failure label.

Required fix: Either:

• Upgrade ragas to a version compatible with langchain-core 1.x (check for ragas ≥0.5.x releases), or
• Downgrade langchain-core to a 0.2.x or 0.3.x version compatible with ragas 0.4.3

Verify the chosen solution resolves without conflicting with other langchain packages (langchain, langchain-community, langchain-openai, langchain-text-splitters, langgraph components).

🤖 Suggested fix

-langchain-core==1.2.7
+langchain-core==0.3.26

or upgrade ragas:

-ragas==0.4.3
+ragas==0.5.x  # (check PyPI for latest 0.5.x with langchain 1.x support)

Also applies to: 193-193

🤖 Prompt for AI Agents

In `@constraints-dev.txt` at line 81, The constraints file pins
langchain-core==1.2.7 which conflicts with ragas 0.4.3 (ragas requires
langchain-core>=0.2,<0.3), so update the constraints to resolve the dependency:
either bump ragas to a release compatible with langchain-core 1.x (e.g., ragas
>=0.5.x) or revert langchain-core to a 0.2.x/0.3.x series that satisfies ragas
0.4.3; after changing the version, run a dependency resolution (pip/pip-compile)
to ensure langchain, langchain-community, langchain-openai,
langchain-text-splitters and langgraph packages remain compatible and adjust
their pins if needed until the install succeeds.

[coderabbitai]

⚠️ Potential issue | 🔴 Critical

CRITICAL: torch/torchvision version conflict — blocking CI.

Based on past review verification, torchvision==0.21.0 requires torch>=2.8.0, but line 230 pins torch==2.6.0. This creates an unresolvable dependency conflict that prevents pip installation, directly causing the CI failures indicated by the ci-failure label.

Required fix: Either:

• Upgrade torch to >=2.8.0 (e.g., torch==2.8.0), or
• Downgrade torchvision to a version compatible with torch 2.6.0 (e.g., torchvision==0.20.x)

Verify the chosen solution is compatible with other torch-dependent packages (torchaudio, accelerate, peft, xformers, vllm).

🤖 Suggested fix

Option A (upgrade torch — recommended if other deps support it):

-torch==2.6.0
+torch==2.8.0

Option B (downgrade torchvision):

-torchvision==0.21.0
+torchvision==0.20.1  # (verify exact version compatible with torch 2.6.0 on PyPI)

Also applies to: 232-232

🤖 Prompt for AI Agents

In `@constraints-dev.txt` at line 230, The pinned torch version "torch==2.6.0"
conflicts with the torchvision requirement (torchvision==0.21.0 requires
torch>=2.8.0); update the constraint by either upgrading torch to a compatible
release (e.g., change the "torch==2.6.0" pin to "torch==2.8.0" or later) or
downgrading the torchvision pin to a 0.20.x that supports torch 2.6 (e.g.,
"torchvision==0.20.x"); after making the change, verify compatibility with other
torch-dependent packages referenced in the file (torchaudio, accelerate, peft,
xformers, vllm) and ensure no other constraints (e.g., the other occurrence
around the torchvision line) conflict before committing.