Chat models currently implement support for:
- images in OpenAI Chat Completions format
- other multimodal types (e.g., PDF and audio) in a cross-provider
[standard
format](https://python.langchain.com/docs/how_to/multimodal_inputs/)
Here we update core to extend support to PDF and audio input in Chat
Completions format. **If an OAI-format PDF or audio content block is
passed into any chat model, it will be transformed to the LangChain
standard format**. We assume that any chat model supporting OAI-format
PDF or audio has implemented support for the standard format.
Thank you for contributing to LangChain!
- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core, etc. is
being modified. Use "docs: ..." for purely docs changes, "infra: ..."
for CI changes.
- Example: "community: add foobar LLM"
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
Addresses #30158
When using the output parser—either in a chain or standalone—hitting
max_tokens triggers a misleading “missing variable” error instead of
indicating the output was truncated. This subtle bug often surfaces with
Anthropic models.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
We only need to rebuild model schemas if type annotation information
isn't available during declaration - that shouldn't be the case for
these types corrected here.
Need to do more thorough testing to make sure these structures have
complete schemas, but hopefully this boosts startup / import time.
TL;DR: you can't optimize imports with a lazy `__getattr__` if there is
a namespace conflict with a module name and an attribute name. We should
avoid introducing conflicts like this in the future.
This PR fixes a bug introduced by my lazy imports PR:
https://github.com/langchain-ai/langchain/pull/30769.
In `langchain_core`, we have utilities for loading and dumping data.
Unfortunately, one of those utilities is a `load` function, located in
`langchain_core/load/load.py`. To make this function more visible, we
make it accessible at the top level `langchain_core.load` module via
importing the function in `langchain_core/load/__init__.py`.
So, either of these imports should work:
```py
from langchain_core.load import load
from langchain_core.load.load import load
```
As you can tell, this is already a bit confusing. You'd think that the
first import would produce the module `load`, but because of the
`__init__.py` shortcut, both produce the function `load`.
<details> More on why the lazy imports PR broke this support...
All was well, except when the absolute import was run first, see the
last snippet:
```
>>> from langchain_core.load import load
>>> load
<function load at 0x101c320c0>
```
```
>>> from langchain_core.load.load import load
>>> load
<function load at 0x1069360c0>
```
```
>>> from langchain_core.load import load
>>> load
<function load at 0x10692e0c0>
>>> from langchain_core.load.load import load
>>> load
<function load at 0x10692e0c0>
```
```
>>> from langchain_core.load.load import load
>>> load
<function load at 0x101e2e0c0>
>>> from langchain_core.load import load
>>> load
<module 'langchain_core.load.load' from '/Users/sydney_runkle/oss/langchain/libs/core/langchain_core/load/load.py'>
```
In this case, the function `load` wasn't stored in the globals cache for
the `langchain_core.load` module (by the lazy import logic), so Python
defers to a module import.
</details>
New `langchain` tongue twister 😜: we've created a problem for ourselves
because you have to load the load function from the load file in the
load module 😨.
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.
Most easily reviewed with the "hide whitespace" option toggled.
Seeing 10-50% speed ups in import time for common structures 🚀
The general purpose of this PR is to lazily import structures within
`langchain_core.XXX_module.__init__.py` so that we're not eagerly
importing expensive dependencies (`pydantic`, `requests`, etc).
Analysis of flamegraphs generated with `importtime` motivated these
changes. For example, the one below demonstrates that importing
`HumanMessage` accidentally triggered imports for `importlib.metadata`,
`requests`, etc.
There's still much more to do on this front, and we can start digging
into our own internal code for optimizations now that we're less
concerned about external imports.
<img width="1210" alt="Screenshot 2025-04-11 at 1 10 54 PM"
src="https://github.com/user-attachments/assets/112a3fe7-24a9-4294-92c1-d5ae64df839e"
/>
I've tracked the improvements with some local benchmarks:
## `pytest-benchmark` results
| Name | Before (s) | After (s) | Delta (s) | % Change |
|-----------------------------|------------|-----------|-----------|----------|
| Document | 2.8683 | 1.2775 | -1.5908 | -55.46% |
| HumanMessage | 2.2358 | 1.1673 | -1.0685 | -47.79% |
| ChatPromptTemplate | 5.5235 | 2.9709 | -2.5526 | -46.22% |
| Runnable | 2.9423 | 1.7793 | -1.163 | -39.53% |
| InMemoryVectorStore | 3.1180 | 1.8417 | -1.2763 | -40.93% |
| RunnableLambda | 2.7385 | 1.8745 | -0.864 | -31.55% |
| tool | 5.1231 | 4.0771 | -1.046 | -20.42% |
| CallbackManager | 4.2263 | 3.4099 | -0.8164 | -19.32% |
| LangChainTracer | 3.8394 | 3.3101 | -0.5293 | -13.79% |
| BaseChatModel | 4.3317 | 3.8806 | -0.4511 | -10.41% |
| PydanticOutputParser | 3.2036 | 3.2995 | 0.0959 | 2.99% |
| InMemoryRateLimiter | 0.5311 | 0.5995 | 0.0684 | 12.88% |
Note the lack of change for `InMemoryRateLimiter` and
`PydanticOutputParser` is just random noise, I'm getting comparable
numbers locally.
## Local CodSpeed results
We're still working on configuring CodSpeed on CI. The local usage
produced similar results.
Looks like `pyupgrade` was already used here but missed some docs and
tests.
This helps to keep our docs looking professional and up to date.
Eventually, we should lint / format our inline docs.
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"
/>
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.
Generally, this PR is CI performance focused + aims to clean up some
dependencies at the same time.
1. Unpins upper bounds for `numpy` in all `pyproject.toml` files where
`numpy` is specified
2. Requires `numpy >= 2.1.0` for Python 3.13 and `numpy > v1.26.0` for
Python 3.12, plus a `numpy` min version bump for `chroma`
3. Speeds up CI by minutes - linting on Python 3.13, installing `numpy <
2.1.0` was taking [~3
minutes](https://github.com/langchain-ai/langchain/actions/runs/14316342925/job/40123305868?pr=30713),
now the entire env setup takes a few seconds
4. Deleted the `numpy` test dependency from partners where that was not
used, specifically `huggingface`, `voyageai`, `xai`, and `nomic`.
It's a bit unfortunate that `langchain-community` depends on `numpy`, we
might want to try to fix that in the future...
Closes https://github.com/langchain-ai/langchain/issues/26026
Fixes https://github.com/langchain-ai/langchain/issues/30555
Add ruff rules PGH: https://docs.astral.sh/ruff/rules/#pygrep-hooks-pgh
Except PGH003 which will be dealt in a dedicated PR.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
**Description:**
Fixed a bug in `BaseCallbackManager.remove_handler()` that caused a
`ValueError` when removing a handler added via the constructor's
`handlers` parameter. The issue occurred because handlers passed to the
constructor were added only to the `handlers` list and not automatically
to `inheritable_handlers` unless explicitly specified. However,
`remove_handler()` attempted to remove the handler from both lists
unconditionally, triggering a `ValueError` when it wasn't in
`inheritable_handlers`.
The fix ensures the method checks for the handler’s presence in each
list before attempting removal, making it more robust while preserving
its original behavior.
**Issue:** Fixes#30640
**Dependencies:** None
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
This pull request includes various changes to the `langchain_core`
library, focusing on improving compatibility with different versions of
Pydantic. The primary change involves replacing checks for Pydantic
major versions with boolean flags, which simplifies the code and
improves readability.
This also solves ruff rule checks for
[RUF048](https://docs.astral.sh/ruff/rules/map-int-version-parsing/) and
[PLR2004](https://docs.astral.sh/ruff/rules/magic-value-comparison/).
Key changes include:
### Compatibility Improvements:
*
[`libs/core/langchain_core/output_parsers/json.py`](diffhunk://#diff-5add0cf7134636ae4198a1e0df49ee332ae0c9123c3a2395101e02687c717646L22-R24):
Replaced `PYDANTIC_MAJOR_VERSION` with `IS_PYDANTIC_V1` to check for
Pydantic version 1.
*
[`libs/core/langchain_core/output_parsers/pydantic.py`](diffhunk://#diff-2364b5b4aee01c462aa5dbda5dc3a877dcd20f29df173ad540dc8adf8b192361L14-R14):
Updated version checks from `PYDANTIC_MAJOR_VERSION` to `IS_PYDANTIC_V2`
in the `PydanticOutputParser` class.
[[1]](diffhunk://#diff-2364b5b4aee01c462aa5dbda5dc3a877dcd20f29df173ad540dc8adf8b192361L14-R14)
[[2]](diffhunk://#diff-2364b5b4aee01c462aa5dbda5dc3a877dcd20f29df173ad540dc8adf8b192361L27-R27)
### Utility Enhancements:
*
[`libs/core/langchain_core/utils/pydantic.py`](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896R23):
Introduced `IS_PYDANTIC_V1` and `IS_PYDANTIC_V2` flags and deprecated
the `get_pydantic_major_version` function. Updated various functions to
use these flags instead of version numbers.
[[1]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896R23)
[[2]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896R42-R78)
[[3]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L90-R89)
[[4]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L104-R101)
[[5]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L120-R122)
[[6]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L135-R132)
[[7]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L149-R151)
[[8]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L164-R161)
[[9]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L248-R250)
[[10]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L330-R335)
[[11]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L356-R357)
[[12]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L393-R390)
[[13]](diffhunk://#diff-ff28020c5f1073a8b63bcd9d8b756a187fd682cb81935295120c63b207071896L403-R400)
### Test Updates:
*
[`libs/core/tests/unit_tests/output_parsers/test_openai_tools.py`](diffhunk://#diff-694cc0318edbd6bbca34f53304934062ad59ba9f5a788252ce6c5f5452489d67L19-R22):
Updated tests to use `IS_PYDANTIC_V1` and `IS_PYDANTIC_V2` for version
checks.
[[1]](diffhunk://#diff-694cc0318edbd6bbca34f53304934062ad59ba9f5a788252ce6c5f5452489d67L19-R22)
[[2]](diffhunk://#diff-694cc0318edbd6bbca34f53304934062ad59ba9f5a788252ce6c5f5452489d67L532-R535)
[[3]](diffhunk://#diff-694cc0318edbd6bbca34f53304934062ad59ba9f5a788252ce6c5f5452489d67L567-R570)
[[4]](diffhunk://#diff-694cc0318edbd6bbca34f53304934062ad59ba9f5a788252ce6c5f5452489d67L602-R605)
*
[`libs/core/tests/unit_tests/prompts/test_chat.py`](diffhunk://#diff-3e60e744842086a4f3c4b21bc83e819c3435720eab210078e77e2430fb8c7e84R7):
Replaced version tuple checks with `PYDANTIC_VERSION` comparisons.
[[1]](diffhunk://#diff-3e60e744842086a4f3c4b21bc83e819c3435720eab210078e77e2430fb8c7e84R7)
[[2]](diffhunk://#diff-3e60e744842086a4f3c4b21bc83e819c3435720eab210078e77e2430fb8c7e84L35-R38)
[[3]](diffhunk://#diff-3e60e744842086a4f3c4b21bc83e819c3435720eab210078e77e2430fb8c7e84L924-R927)
[[4]](diffhunk://#diff-3e60e744842086a4f3c4b21bc83e819c3435720eab210078e77e2430fb8c7e84L935-R938)
*
[`libs/core/tests/unit_tests/runnables/test_graph.py`](diffhunk://#diff-99a290330ef40103d0ce02e52e21310d6fadea142bfdea13c94d23fc81c0bb5dR3):
Simplified version checks using `PYDANTIC_VERSION`.
[[1]](diffhunk://#diff-99a290330ef40103d0ce02e52e21310d6fadea142bfdea13c94d23fc81c0bb5dR3)
[[2]](diffhunk://#diff-99a290330ef40103d0ce02e52e21310d6fadea142bfdea13c94d23fc81c0bb5dL15-R18)
[[3]](diffhunk://#diff-99a290330ef40103d0ce02e52e21310d6fadea142bfdea13c94d23fc81c0bb5dL234-L239)
*
[`libs/core/tests/unit_tests/runnables/test_runnable.py`](diffhunk://#diff-06bed920c0dad0cfd41d57a8d9e47a7b56832409649c10151061a791860d5bb5L18-R20):
Introduced `PYDANTIC_VERSION_AT_LEAST_29` and
`PYDANTIC_VERSION_AT_LEAST_210` for more readable version checks.
[[1]](diffhunk://#diff-06bed920c0dad0cfd41d57a8d9e47a7b56832409649c10151061a791860d5bb5L18-R20)
[[2]](diffhunk://#diff-06bed920c0dad0cfd41d57a8d9e47a7b56832409649c10151061a791860d5bb5L92-R99)
[[3]](diffhunk://#diff-06bed920c0dad0cfd41d57a8d9e47a7b56832409649c10151061a791860d5bb5L230-R233)
[[4]](diffhunk://#diff-06bed920c0dad0cfd41d57a8d9e47a7b56832409649c10151061a791860d5bb5L652-R655)
Add ruff rules:
* FIX: https://docs.astral.sh/ruff/rules/#flake8-fixme-fix
* TD: https://docs.astral.sh/ruff/rules/#flake8-todos-td
Code cleanup:
*
[`libs/core/langchain_core/outputs/chat_generation.py`](diffhunk://#diff-a1017ee46f58fa4005b110ffd4f8e1fb08f6a2a11d6ca4c78ff8be641cbb89e5L56-R56):
Removed the "HACK" prefix from a comment in the `set_text` method.
Configuration adjustments:
*
[`libs/core/pyproject.toml`](diffhunk://#diff-06baaee12b22a370fef9f170c9ed13e2727e377d3b32f5018430f4f0a39d3537R85-R93):
Added new rules `FIX002`, `TD002`, and `TD003` to the ignore list.
*
[`libs/core/pyproject.toml`](diffhunk://#diff-06baaee12b22a370fef9f170c9ed13e2727e377d3b32f5018430f4f0a39d3537L102-L108):
Removed the `FIX` and `TD` rules from the ignore list.
Test refinement:
*
[`libs/core/tests/unit_tests/runnables/test_runnable.py`](diffhunk://#diff-06bed920c0dad0cfd41d57a8d9e47a7b56832409649c10151061a791860d5bb5L3231-R3232):
Updated a TODO comment to improve clarity in the `test_map_stream`
function.
