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.
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>
- **Description:** Propagates config_factories when calling decoration
methods for RunnableBinding--e.g. bind, with_config, with_types,
with_retry, and with_listeners. This ensures that configs attached to
the original RunnableBinding are kept when creating the new
RunnableBinding and the configs are merged during invocation. Picks up
where #30551 left off.
- **Issue:** #30531
Co-authored-by: ccurme <chester.curme@gmail.com>
This pull request updates the `pyproject.toml` configuration file to
modify the linting rules and ignored warnings for the project. The most
important changes include switching to a more comprehensive selection of
linting rules and updating the list of ignored rules to better align
with the project's requirements.
Linting rules update:
* Changed the `select` option to include all available linting rules by
setting it to `["ALL"]`.
Ignored rules update:
* Updated the `ignore` option to include specific rules that interfere
with the formatter, are incompatible with Pydantic, or are temporarily
excluded due to project constraints.
Release notes: https://pydantic.dev/articles/pydantic-v2-11-release
Covered here:
- We no longer access `model_fields` on class instances (that is now
deprecated);
- Update schema normalization for Pydantic version testing to reflect
changes to generated JSON schema (addition of `"additionalProperties":
True` for dict types with value Any or object).
## Considerations:
### Changes to JSON schema generation
#### Tool-calling / structured outputs
This may impact tool-calling + structured outputs for some providers,
but schema generation only changes if you have parameters of the form
`dict`, `dict[str, Any]`, `dict[str, object]`, etc. If dict parameters
are typed my understanding is there are no changes.
For OpenAI for example, untyped dicts work for structured outputs with
default settings before and after updating Pydantic, and error both
before/after if `strict=True`.
### Use of `model_fields`
There is one spot where we previously accessed `super(cls,
self).model_fields`, where `cls` is an object in the MRO. This was done
for the purpose of tracking aliases in secrets. I've updated this to
always be `type(self).model_fields`-- see comment in-line for detail.
---------
Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>
**Description:**
This PR addresses the loss of partially initialised variables when
composing different prompts. I.e. it allows the following snippet to
run:
```python
from langchain_core.prompts import ChatPromptTemplate
prompt = ChatPromptTemplate.from_messages([('system', 'Prompt {x} {y}')]).partial(x='1')
appendix = ChatPromptTemplate.from_messages([('system', 'Appendix {z}')])
(prompt + appendix).invoke({'y': '2', 'z': '3'})
```
Previously, this would have raised a `KeyError`, stating that variable
`x` remains undefined.
**Issue**
References issue #30049
**Todo**
- [x] **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.
- [x] **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/
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Stripped-down version of
[OpenAICallbackHandler](https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/callbacks/openai_info.py)
that just tracks `AIMessage.usage_metadata`.
```python
from langchain_core.callbacks import get_usage_metadata_callback
from langgraph.prebuilt import create_react_agent
def get_weather(location: str) -> str:
"""Get the weather at a location."""
return "It's sunny."
tools = [get_weather]
agent = create_react_agent("openai:gpt-4o-mini", tools)
with get_usage_metadata_callback() as cb:
result = await agent.ainvoke({"messages": "What's the weather in Boston?"})
print(cb.usage_metadata)
```
- Test if models support forcing tool calls via `tool_choice`. If they
do, they should support
- `"any"` to specify any tool
- the tool name as a string to force calling a particular tool
- Add `tool_choice` to signature of `BaseChatModel.bind_tools` in core
- Deprecate `tool_choice_value` in standard tests in favor of a boolean
`has_tool_choice`
Will follow up with PRs in external repos (tested in AWS and Google
already).
- Support thinking blocks in core's `convert_to_openai_messages` (pass
through instead of error)
- Ignore thinking blocks in ChatOpenAI (instead of error)
- Support Anthropic-style image blocks in ChatOpenAI
---
Standard integration tests include a `supports_anthropic_inputs`
property which is currently enabled only for tests on `ChatAnthropic`.
This test enforces compatibility with message histories of the form:
```
- system message
- human message
- AI message with tool calls specified only through `tool_use` content blocks
- human message containing `tool_result` and an additional `text` block
```
It additionally checks support for Anthropic-style image inputs if
`supports_image_inputs` is enabled.
Here we change this test, such that if you enable
`supports_anthropic_inputs`:
- You support AI messages with text and `tool_use` content blocks
- You support Anthropic-style image inputs (if `supports_image_inputs`
is enabled)
- You support thinking content blocks.
That is, we add a test case for thinking content blocks, but we also
remove the requirement of handling tool results within HumanMessages
(motivated by existing agent abstractions, which should all return
ToolMessage). We move that requirement to a ChatAnthropic-specific test.
**Description:**
5 fix of example from function with_alisteners() in
libs/core/langchain_core/runnables/base.py
Replace incoherent example output with workable example's output.
1. SyntaxError: unterminated string literal
print(f"on start callback starts at {format_t(time.time())}
correct as
print(f"on start callback starts at {format_t(time.time())}")
2. SyntaxError: unterminated string literal
print(f"on end callback starts at {format_t(time.time())}
correct as
print(f"on end callback starts at {format_t(time.time())}")
3. NameError: name 'Runnable' is not defined
Fix as
from langchain_core.runnables import Runnable
4. NameError: name 'asyncio' is not defined
Fix as
import asyncio
5. NameError: name 'format_t' is not defined.
Implement format_t() as
from datetime import datetime, timezone
def format_t(timestamp: float) -> str:
return datetime.fromtimestamp(timestamp, tz=timezone.utc).isoformat()
- **Description:** Same changes as #26593 but for FileCallbackHandler
- **Issue:** Fixes#29941
- **Dependencies:** None
- **Twitter handle:** None
- [x] **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/
See https://docs.astral.sh/ruff/rules/#flake8-type-checking-tc
Some fixes done for TC001,TC002 and TC003 but these rules are excluded
since they don't play well with Pydantic.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Resolves https://github.com/langchain-ai/langchain/issues/29951
Was able to reproduce the issue with Anthropic installing from pydantic
`main` and correct it with the fix recommended in the issue.
Thanks very much @Viicos for finding the bug and the detailed writeup!
Resolves https://github.com/langchain-ai/langchain/issues/29003,
https://github.com/langchain-ai/langchain/issues/27264
Related: https://github.com/langchain-ai/langchain-redis/issues/52
```python
from langchain.chat_models import init_chat_model
from langchain.globals import set_llm_cache
from langchain_community.cache import SQLiteCache
from pydantic import BaseModel
cache = SQLiteCache()
set_llm_cache(cache)
class Temperature(BaseModel):
value: int
city: str
llm = init_chat_model("openai:gpt-4o-mini")
structured_llm = llm.with_structured_output(Temperature)
```
```python
# 681 ms
response = structured_llm.invoke("What is the average temperature of Rome in May?")
```
```python
# 6.98 ms
response = structured_llm.invoke("What is the average temperature of Rome in May?")
```
See https://docs.astral.sh/ruff/rules/#flake8-annotations-ann
The interest compared to only mypy is that ruff is very fast at
detecting missing annotations.
ANN101 and ANN102 are deprecated so we ignore them
ANN401 (no Any type) ignored to be in sync with mypy config
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
