On core releases, we check out the latest published package for
langchain-openai and langchain-anthropic and run their tests against the
candidate version of langchain-core.
Because these packages have a local install of langchain-tests, we also
need to check out the previous version of langchain-tests.
Fix CI to trigger benchmarks on `run-codspeed-benchmarks` label addition
Reduce scope of async benchmark to save time on CI
Waiting to merge this PR until we figure out how to use walltime on
local runners.
This PR aims to reduce import time of `langchain-core` tools by removing
the `importlib.metadata` import previously used in `__init__.py`. This
is the first in a sequence of PRs to reduce import time delays for
`langchain-core` features and structures 🚀.
Because we're now hard coding the version, we need to make sure
`version.py` and `pyproject.toml` stay in sync, so I've added a new CI
job that runs whenever either of those files are modified. [This
run](https://github.com/langchain-ai/langchain/actions/runs/14358012706/job/40251952044?pr=30744)
demonstrates the failure that occurs whenever the version gets out of
sync (thus blocking a PR).
Before, note the ~15% of time spent on the `importlib.metadata` /related
imports
<img width="1081" alt="Screenshot 2025-04-09 at 9 06 15 AM"
src="https://github.com/user-attachments/assets/59f405ec-ee8d-4473-89ff-45dea5befa31"
/>
After (note, lack of `importlib.metadata` time sink):
<img width="1245" alt="Screenshot 2025-04-09 at 9 01 23 AM"
src="https://github.com/user-attachments/assets/9c32e77c-27ce-485e-9b88-e365193ed58d"
/>
* Only run codspeed logic when `libs/core` is changed (for now, we'll
want to add other benchmarks later
* Also run on `master` so that we can get a reference :)
The first in a sequence of PRs focusing on improving performance in
core. We're starting with reducing import times for common structures,
hence the benchmarks here.
The benchmark looks a little bit complicated - we have to use a process
so that we don't suffer from Python's import caching system. I tried
doing manual modification of `sys.modules` between runs, but that's
pretty tricky / hacky to get right, hence the subprocess approach.
Motivated by extremely slow baseline for common imports (we're talking
2-5 seconds):
<img width="633" alt="Screenshot 2025-04-09 at 12 48 12 PM"
src="https://github.com/user-attachments/assets/994616fe-1798-404d-bcbe-48ad0eb8a9a0"
/>
Also added a `make benchmark` command to make local runs easy :).
Currently using walltimes so that we can track total time despite using
a manual proces.
Perplexity's importance in the space has been growing, so we think it's
time to add an official integration!
Note: following the release of `langchain-perplexity` to `pypi`, we
should be able to add `perplexity` as an extra in
`libs/langchain/pyproject.toml`, but we're blocked by a circular import
for now.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Here we add a job to the release workflow that, when releasing
`langchain-core`, tests prior published versions of select packages
against the new version of core. We limit the testing to the most recent
published versions of langchain-anthropic and langchain-openai.
This is designed to catch backward-incompatible updates to core. We
sometimes update core and downstream packages simultaneously, so there
may not be any commit in the history at which tests would fail. So
although core and latest downstream packages could be consistent, we can
benefit from testing prior versions of downstream packages against core.
I tested the workflow by simulating a [breaking
change](d7287248cf)
in core and running it with publishing steps disabled:
https://github.com/langchain-ai/langchain/actions/runs/13741876345. The
workflow correctly caught the issue.
Follows on from #27991, updates the langchain-community package to
support numpy 2 versions
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
