Closes https://github.com/langchain-ai/langchain/issues/33956
* Making `ModelRequest` generic on `ContextT` and `ResponseT` so that we
can thread type information through to `wrap_model_call`
* Making builtin middlewares generic on `ContextT` and `ResponseT` so
their context and response types can be inferred from the `create_agent`
signature
See new tests that verify backwards compatibility (for cases where folks
use custom middleware that wasn't parametrized).
This fixes:
1. Lack of access to context and response types in `wrap_model_call`
2. Lack of cohesion between middleware context + response types with
those specified in `create_agent`
See examples below:
### Type-safe context and response access
```python
class MyMiddleware(AgentMiddleware[AgentState[AnalysisResult], UserContext, AnalysisResult]):
def wrap_model_call(
self,
request: ModelRequest[UserContext],
handler: Callable[[ModelRequest[UserContext]], ModelResponse[AnalysisResult]],
) -> ModelResponse[AnalysisResult]:
# ✅ Now type-safe: IDE knows user_id exists and is str
user_id: str = request.runtime.context["user_id"]
# ❌ mypy error: "session_id" doesn't exist on UserContext
request.runtime.context["session_id"]
response = handler(request)
if response.structured_response is not None:
# ✅ Now type-safe: IDE knows sentiment exists and is str
sentiment: str = response.structured_response.sentiment
# ❌ mypy error: "summary" doesn't exist on AnalysisResult
response.structured_response.summary
return response
```
### Mismatched middleware/schema caught at `create_agent`
```python
class SessionMiddleware(AgentMiddleware[AgentState[Any], SessionContext, Any]):
...
# ❌ mypy error: SessionMiddleware expects SessionContext, not UserContext
create_agent(
model=model,
middleware=[SessionMiddleware()],
context_schema=UserContext, # mismatch!
)
class AnalysisMiddleware(AgentMiddleware[AgentState[AnalysisResult], ContextT, AnalysisResult]):
...
# ❌ mypy error: AnalysisMiddleware expects AnalysisResult, not SummaryResult
create_agent(
model=model,
middleware=[AnalysisMiddleware()],
response_format=SummaryResult, # mismatch!
)
```
Implementations using yield return generators, which are of type
`Iterator`.
This is technically a breaking change for implementers, however, known
existing implementations (in `langchain-community`) use `yield`, so they
already return `Iterator`s. For callers, it is not breaking.
Closes#25718
it looks scary but i promise it is not
improving documentation consistency across core. primarily update
docstrings and comments for better formatting, readability, and
accuracy, as well as add minor clarifications and formatting
improvements to user-facing documentation.
it looks scary but i promise it is not
improving documentation consistency across langchain. primarily update
docstrings and comments for better formatting, readability, and
accuracy, as well as add minor clarifications and formatting
improvements to user-facing documentation.
Update broken contributing links in AGENTS.md and CLAUDE.md
Description:
Update internal references from .github/CONTRIBUTING.md to [Contributing
Guide] to fix navigation issues for local contributors.
Proposed Changes
AGENTS.md: Change [.github/CONTRIBUTING.md] link text to [Contributing
Guide] since the file path is not present in the local root.
CLAUDE.md: Change [.github/CONTRIBUTING.md] link text to [Contributing
Guide] for consistency.
Reasoning:
Users following these docs locally often find the specific file path
.github/CONTRIBUTING.md confusing or "broken" in markdown previews that
don't resolve the .github hidden directory correctly. Using the
descriptive label "Contributing Guide" is more user-friendly and
standard across the repo.
Checklist:
[x] Run make format, make lint and make test (N/A for these doc-only
changes).
[x] PR title follows the format: TYPE(SCOPE): DESCRIPTION.
[x] I have read the [Contributing
Guide](https://www.google.com/search?q=https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md).
(Replace this entire block of text)
Read the full contributing guidelines:
https://docs.langchain.com/oss/python/contributing/overview
Thank you for contributing to LangChain! Follow these steps to have your
pull request considered as ready for review.
1. PR title: Should follow the format: TYPE(SCOPE): DESCRIPTION
- Examples:
- fix(anthropic): resolve flag parsing error
- feat(core): add multi-tenant support
- test(openai): update API usage tests
- Allowed TYPE and SCOPE values:
https://github.com/langchain-ai/langchain/blob/master/.github/workflows/pr_lint.yml#L15-L33
2. PR description:
- Write 1-2 sentences summarizing the change.
- If this PR addresses a specific issue, please include "Fixes
#ISSUE_NUMBER" in the description to automatically close the issue when
the PR is merged.
- If there are any breaking changes, please clearly describe them.
- If this PR depends on another PR being merged first, please include
"Depends on #PR_NUMBER" in the description.
3. Run `make format`, `make lint` and `make test` from the root of the
package(s) you've modified.
- We will not consider a PR unless these three are passing in CI.
Additional guidelines:
- We ask that if you use generative AI for your contribution, you
include a disclaimer.
- PRs should not touch more than one package unless absolutely
necessary.
- Do not update the `uv.lock` files or add dependencies to
`pyproject.toml` files (even optional ones) unless you have explicit
permission to do so by a maintainer.
…tring
(Replace this entire block of text)
Read the full contributing guidelines:
https://docs.langchain.com/oss/python/contributing/overview
Thank you for contributing to LangChain! Follow these steps to have your
pull request considered as ready for review.
1. PR title: Should follow the format: TYPE(SCOPE): DESCRIPTION
- Examples:
- fix(anthropic): resolve flag parsing error
- feat(core): add multi-tenant support
- test(openai): update API usage tests
- Allowed TYPE and SCOPE values:
https://github.com/langchain-ai/langchain/blob/master/.github/workflows/pr_lint.yml#L15-L33
2. PR description:
- Write 1-2 sentences summarizing the change.
- If this PR addresses a specific issue, please include "Fixes
#ISSUE_NUMBER" in the description to automatically close the issue when
the PR is merged.
- If there are any breaking changes, please clearly describe them.
- If this PR depends on another PR being merged first, please include
"Depends on #PR_NUMBER" in the description.
3. Run `make format`, `make lint` and `make test` from the root of the
package(s) you've modified.
- We will not consider a PR unless these three are passing in CI.
Additional guidelines:
- We ask that if you use generative AI for your contribution, you
include a disclaimer.
- PRs should not touch more than one package unless absolutely
necessary.
- Do not update the `uv.lock` files or add dependencies to
`pyproject.toml` files (even optional ones) unless you have explicit
permission to do so by a maintainer.
dependent upon https://github.com/langchain-ai/langgraph/pull/6711
1. relax constraint in `factory.py` to allow for tools not
pre-registered in the `ModelRequest.tools` list
2. always add tool node if `wrap_tool_call` or `awrap_tool_call` is
implemented
3. add tests confirming you can register new tools at runtime in
`wrap_model_call` and execute them via `wrap_tool_call`
allows for the following pattern
```py
from langchain_core.messages import HumanMessage, ToolMessage
from langchain_core.tools import tool
from libs.langchain_v1.langchain.agents.factory import create_agent
from libs.langchain_v1.langchain.agents.middleware.types import (
AgentMiddleware,
ModelRequest,
ToolCallRequest,
)
@tool
def get_weather(location: str) -> str:
"""Get the current weather for a location."""
return f"The weather in {location} is sunny and 72°F."
@tool
def calculate_tip(bill_amount: float, tip_percentage: float = 20.0) -> str:
"""Calculate the tip amount for a bill."""
tip = bill_amount * (tip_percentage / 100)
return f"Tip: ${tip:.2f}, Total: ${bill_amount + tip:.2f}"
class DynamicToolMiddleware(AgentMiddleware):
"""Middleware that adds and handles a dynamic tool."""
def wrap_model_call(self, request: ModelRequest, handler):
updated = request.override(tools=[*request.tools, calculate_tip])
return handler(updated)
def wrap_tool_call(self, request: ToolCallRequest, handler):
if request.tool_call["name"] == "calculate_tip":
return handler(request.override(tool=calculate_tip))
return handler(request)
agent = create_agent(model="openai:gpt-4o-mini", tools=[get_weather], middleware=[DynamicToolMiddleware()])
result = agent.invoke({
"messages": [HumanMessage("What's the weather in NYC? Also calculate a 20% tip on a $85 bill")]
})
for msg in result["messages"]:
msg.pretty_print()
```
## Summary
Add XML format option for `get_buffer_string()` to provide unambiguous
message serialization. This fixes role prefix ambiguity when message
content contains strings like "Human:" or "AI:".
Fixes#34786
## Changes
- Add `format="xml"` parameter with proper XML escaping using
`quoteattr()` for attributes
- Add explicit validation for format parameter (raises `ValueError` for
invalid values)
- Add comprehensive tests for XML format edge cases
<img width="1952" height="706" alt="image"
src="https://github.com/user-attachments/assets/1cd6f887-9365-43cf-a532-72d7addd8bad"
/>
<img width="2786" height="776" alt="image"
src="https://github.com/user-attachments/assets/a07b0db0-519c-46d7-b34b-b404237d812b"
/>
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
- Fix 'inthe' -> 'in the' on line 20
- Fix grammar error 'unless or add' -> 'or add' on line 30
(Replace this entire block of text)
Read the full contributing guidelines:
https://docs.langchain.com/oss/python/contributing/overview
Thank you for contributing to LangChain! Follow these steps to have your
pull request considered as ready for review.
1. PR title: Should follow the format: TYPE(SCOPE): DESCRIPTION
- Examples:
- fix(anthropic): resolve flag parsing error
- feat(core): add multi-tenant support
- test(openai): update API usage tests
- Allowed TYPE and SCOPE values:
https://github.com/langchain-ai/langchain/blob/master/.github/workflows/pr_lint.yml#L15-L33
2. PR description:
- Write 1-2 sentences summarizing the change.
- If this PR addresses a specific issue, please include "Fixes
#ISSUE_NUMBER" in the description to automatically close the issue when
the PR is merged.
- If there are any breaking changes, please clearly describe them.
- If this PR depends on another PR being merged first, please include
"Depends on #PR_NUMBER" inthe description.
3. Run `make format`, `make lint` and `make test` from the root of the
package(s) you've modified.
- We will not consider a PR unless these three are passing in CI.
Additional guidelines:
- We ask that if you use generative AI for your contribution, you
include a disclaimer.
- PRs should not touch more than one package unless absolutely
necessary.
- Do not update the `uv.lock` files unless or add dependencies to
`pyproject.toml` files (even optional ones) unless you have explicit
permission to do so by a maintainer.
Bumps the uv group with 1 update in the /libs/core directory:
[setuptools](https://github.com/pypa/setuptools).
Updates `setuptools` from 67.8.0 to 78.1.1
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/pypa/setuptools/blob/main/NEWS.rst">setuptools's
changelog</a>.</em></p>
<blockquote>
<h1>v78.1.1</h1>
<h2>Bugfixes</h2>
<ul>
<li>More fully sanitized the filename in PackageIndex._download. (<a
href="https://redirect.github.com/pypa/setuptools/issues/4946">#4946</a>)</li>
</ul>
<h1>v78.1.0</h1>
<h2>Features</h2>
<ul>
<li>Restore access to _get_vc_env with a warning. (<a
href="https://redirect.github.com/pypa/setuptools/issues/4874">#4874</a>)</li>
</ul>
<h1>v78.0.2</h1>
<h2>Bugfixes</h2>
<ul>
<li>Postponed removals of deprecated dash-separated and uppercase fields
in <code>setup.cfg</code>.
All packages with deprecated configurations are advised to move before
2026. (<a
href="https://redirect.github.com/pypa/setuptools/issues/4911">#4911</a>)</li>
</ul>
<h1>v78.0.1</h1>
<h2>Misc</h2>
<ul>
<li><a
href="https://redirect.github.com/pypa/setuptools/issues/4909">#4909</a></li>
</ul>
<h1>v78.0.0</h1>
<h2>Bugfixes</h2>
<ul>
<li>Reverted distutils changes that broke the monkey patching of command
classes. (<a
href="https://redirect.github.com/pypa/setuptools/issues/4902">#4902</a>)</li>
</ul>
<h2>Deprecations and Removals</h2>
<ul>
<li>Setuptools no longer accepts options containing uppercase or dash
characters in <code>setup.cfg</code>.</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="8e4868a036"><code>8e4868a</code></a>
Bump version: 78.1.0 → 78.1.1</li>
<li><a
href="100e9a61ad"><code>100e9a6</code></a>
Merge pull request <a
href="https://redirect.github.com/pypa/setuptools/issues/4951">#4951</a></li>
<li><a
href="8faf1d7e0c"><code>8faf1d7</code></a>
Add news fragment.</li>
<li><a
href="2ca4a9fe47"><code>2ca4a9f</code></a>
Rely on re.sub to perform the decision in one expression.</li>
<li><a
href="e409e80029"><code>e409e80</code></a>
Extract _sanitize method for sanitizing the filename.</li>
<li><a
href="250a6d1797"><code>250a6d1</code></a>
Add a check to ensure the name resolves relative to the tmpdir.</li>
<li><a
href="d8390feaa9"><code>d8390fe</code></a>
Extract _resolve_download_filename with test.</li>
<li><a
href="4e1e89392d"><code>4e1e893</code></a>
Merge <a
href="https://github.com/jaraco/skeleton">https://github.com/jaraco/skeleton</a></li>
<li><a
href="3a3144f0d2"><code>3a3144f</code></a>
Fix typo: <code>pyproject.license</code> ->
<code>project.license</code> (<a
href="https://redirect.github.com/pypa/setuptools/issues/4931">#4931</a>)</li>
<li><a
href="d751068fd2"><code>d751068</code></a>
Fix typo: pyproject.license -> project.license</li>
<li>Additional commits viewable in <a
href="https://github.com/pypa/setuptools/compare/v67.8.0...v78.1.1">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore <dependency name> major version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's major version (unless you unignore this specific
dependency's major version or upgrade to it yourself)
- `@dependabot ignore <dependency name> minor version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's minor version (unless you unignore this specific
dependency's minor version or upgrade to it yourself)
- `@dependabot ignore <dependency name>` will close this group update PR
and stop Dependabot creating any more for the specific dependency
(unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore <dependency name>` will remove all of the ignore
conditions of the specified dependency
- `@dependabot unignore <dependency name> <ignore condition>` will
remove the ignore condition of the specified dependency and ignore
conditions
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/langchain-ai/langchain/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore <dependency name> major version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's major version (unless you unignore this specific
dependency's major version or upgrade to it yourself)
- `@dependabot ignore <dependency name> minor version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's minor version (unless you unignore this specific
dependency's minor version or upgrade to it yourself)
- `@dependabot ignore <dependency name>` will close this group update PR
and stop Dependabot creating any more for the specific dependency
(unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore <dependency name>` will remove all of the ignore
conditions of the specified dependency
- `@dependabot unignore <dependency name> <ignore condition>` will
remove the ignore condition of the specified dependency and ignore
conditions
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/langchain-ai/langchain/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore <dependency name> major version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's major version (unless you unignore this specific
dependency's major version or upgrade to it yourself)
- `@dependabot ignore <dependency name> minor version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's minor version (unless you unignore this specific
dependency's minor version or upgrade to it yourself)
- `@dependabot ignore <dependency name>` will close this group update PR
and stop Dependabot creating any more for the specific dependency
(unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore <dependency name>` will remove all of the ignore
conditions of the specified dependency
- `@dependabot unignore <dependency name> <ignore condition>` will
remove the ignore condition of the specified dependency and ignore
conditions
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/langchain-ai/langchain/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
`deepagents` requires Python >= 3.11. Note: this won't display in the
action title in the UI if requesting 3.10, and it will also still show
`(3.10, 3.13)` since that's what the integration packages are testing
against. `deepagents` matrix title will be accurate.
Add testing for `deepagents` both (1) on scheduled interval and (2)
release of `langchain-core` or `langchain` to ensure compatibility.
Should catch breaking changes early.
We need to set `{"metadata": {"lc_source": "summarization"}}` on the
invocation so that consumers (e.g. `deepagents-cli`) can see that a
summarization LLM call is being made, and therefore take any necessary
actions (such as updating the status line to say `'Currently
summarizing...'`
See https://github.com/langchain-ai/deepagents/pull/742 for more
Related to #34693 (but for outbound)
# Before
```python
if isinstance(block, dict) and "text" in block:
text = block["text"]
break
```
Extracts text from any `dict` with a `'text'` key, including
thinking/reasoning blocks.
# After
```python
if isinstance(block, dict) and "text" in block:
block_type = block.get("type")
if block_type is None or block_type == "text":
text = block["text"]
break
```
Skips blocks with explicit non-text types (e.g., `type: 'thinking'`).
# Justification
Models like Gemini 3 return structured content with multiple block
types:
```python
[
{"type": "thinking", "text": "let me reason..."},
{"type": "text", "text": "The answer is 42"}
]
```
The old logic extracted `'let me reason...'` (the thinking block)
because it matched first. The new logic skips it and correctly extracts
`'The answer is 42'`.
The `ChatGeneration.text` field is used by `on_llm_new_token(token,
chunk=chunk)` callbacks during streaming. Consequently, it would get
tokens incorrectly for reasoning blocks.
Related: #34727
Updates `comma_list` in `libs/core/langchain_core/utils/strings.py` to
accept `Iterable[Any]` instead of `list[Any]`, making the utility more
flexible.
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
The code behind this functionality has been moved to the
langchain-community repository, and there are tests there to exercise
this functionality.
Fixes#33392
Co-authored-by: amelvil2 <amelvil2>
## Summary
- Adds explicit `tags: list[str] | None = None` parameter to sync
`LLMManagerMixin` methods
- Aligns sync methods with their async counterparts in
`AsyncCallbackHandler`
## Changes
Added `tags` parameter to:
- `on_llm_new_token`
- `on_llm_end`
- `on_llm_error`
## Why
- Sync handlers receive `tags` via `**kwargs`, but it was undocumented
in the method signature
- Async handlers already have `tags` explicitly documented
- This improves IDE autocompletion and type hints for sync handlers
Closes#34720🤖 Generated with [Claude Code](https://claude.ai/claude-code)
Co-authored-by: skyvanguard <skyvanguard@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Clarify the preference for using exact model IDs from provider
documentation over aliases to ensure reliable behavior in face of
upstream backend changes.
# Add `tool_call_id` to `on_tool_error` event data
## Summary
This PR addresses issue #33597 by adding `tool_call_id` to the
`on_tool_error` callback event data. This enables users to link tool
errors to specific tool calls in stateless agent implementations, which
is essential for building OpenAI-compatible APIs and tracking tool
execution flows.
## Problem
When streaming events using `astream_events` with `version="v2"`, the
`on_tool_error` event only included the error and input data, but lacked
the `tool_call_id`. This made it difficult to:
- Link errors to specific tool calls in stateless agent scenarios
- Implement OpenAI-compatible APIs that require tool call tracking
- Track tool execution flows when using `run_id` is not sufficient
## Solution
The fix adds `tool_call_id` propagation through the callback chain:
1. **Pass `tool_call_id` to callbacks**: Updated `BaseTool.run()` and
`BaseTool.arun()` to pass `tool_call_id` to both `on_tool_start` and
`on_tool_error` callbacks
2. **Store in event stream handler**: Modified
`_AstreamEventsCallbackHandler` to store `tool_call_id` in run info
during `on_tool_start`
3. **Include in error events**: Updated `on_tool_error` handler to
extract and include `tool_call_id` in the event data
## Changes
- **`libs/core/langchain_core/tools/base.py`**:
- Pass `tool_call_id` to `on_tool_start` in both sync and async methods
- Pass `tool_call_id` to `on_tool_error` when errors occur
- **`libs/core/langchain_core/tracers/event_stream.py`**:
- Store `tool_call_id` in run info during `on_tool_start`
- Extract `tool_call_id` from kwargs or run info in `on_tool_error`
- Include `tool_call_id` in the `on_tool_error` event data
## Testing
The fix was verified by:
1. Direct tool invocation: Confirmed `tool_call_id` appears in
`on_tool_error` event data when calling tools directly
2. Agent integration: Tested with `create_agent` to ensure
`tool_call_id` is present in error events during agent execution
```python
# Example verification
async for event in agent.astream_events(
{"messages": "Please demonstrate a tool error"},
version="v2",
):
if event["event"] == "on_tool_error":
assert "tool_call_id" in event["data"] # ✓ Now passes
print(event["data"]["tool_call_id"])
```
## Backward Compatibility
- ✅ Fully backward compatible: `tool_call_id` is optional (can be
`None`)
- ✅ No breaking changes: All changes are additive
- ✅ Existing code continues to work without modification
## Related Issues
Fixes#33597
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Changes Created
I have fixed the issue where a generic and misleading error message was
displayed when a JSON schema was missing the top-level
title
key.
[Fix: Improve error message for missing title in JSON schema
functions](https://github.com/Bhavesh007Sharma/langchain/tree/fix-json-schema-title-error)
File Modified:
libs/core/langchain_core/utils/function_calling.py
I updated the
convert_to_openai_function
validation logic to specifically check for
dict
inputs that look like schemas (
type
or
properties
keys present) but are missing the
title
key.
# Before (Generic Error)
raise ValueError(
f"Unsupported function\n\n{function}\n\nFunctions must be passed in"
" as Dict, pydantic.BaseModel, or Callable. If they're a dict they must"
" either be in OpenAI function format or valid JSON schema with
top-level"
" 'title' and 'description' keys."
)
# After (Specific Error)
if isinstance(function, dict) and ("type" in function or "properties" in
function):
msg = (
"Unsupported function\n\nTo use a JSON schema as a function, "
"it must have a top-level 'title' key to be used as the function name."
)
raise ValueError(msg)
Verification Results
Automated Tests
I created a reproduction script
reproduce_issue.py
to confirm the behavior.
Before Fix: The script would have raised the generic "Unsupported
function" error claiming description was also required.
After Fix: The script now confirms that the new, specific error message
is raised when
title
is missing.
(Note: Verification was performed by inspecting the code logic and
running a lightweight reproduction script locally, as full suite
verification had environment dependency issues.)
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
This PR fixes a signature mismatch between BaseStore and its concrete
implementations by making the `prefix` parameter keyword-only in
`yield_keys` and `ayield_keys`.
This aligns the implementations with the BaseStore interface contract,
prevents Liskov Substitution Principle violations, and ensures
consistent
method signatures across store backends.
Fixes#32637
Breaking changes
None. This change only enforces the existing abstract interface and does
not modify runtime behavior
Testing
- Verified that existing test suites pass after the signature fix.
Parts of this contribution were assisted by generative AI for
code navigation and drafting. All final design decisions and changes
were
reviewed and validated manually.
---------
Co-authored-by: Khagesh-Anayasmi <khagesh.desai@anayasmi.in>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Regression introduced in 8e3c6b109f
The commit changed the return annotation of `with_structured_output`
from `typing.Dict | BaseModel` to `builtins.dict[str, Any] | BaseModel`.
Since `BaseModel` refers to `pydantic.BaseModel (v2)`, but the test
`test_structured_output_pydantic_2_v1` uses `pydantic.v1.BaseModel`,
mypy's `warn_unreachable` setting flags the `isinstance` checks as
unreachable (since a class can't be both a `dict` and a different
`BaseModel` type).
Switching to `builtins.dict[str, Any]` made the type more precise, which
exposed this type incompatibility that was always latent but hidden by
the looser `typing.Dict` annotation.
* Making `FakeToolCallingModel` generic on its `structured_response`
doesn't help anywhere in typing.
* There are more than 120 references of `FakeToolCallingModel` in the
code where you get ` error: Need type annotation for "model"
[var-annotated]` because mypy can't resolve the generic type (we don't
see them atm because they are in files temporarily excluded from mypy
checking). We would need to explicitly type them to
`FakeToolCallingModel[Any]`
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Appears `override()`'s docstring in `langgraph` already shows
`state=new_state` as a valid usage pattern
Works since `dataclasses.replace()` accepts any field, but the
`TypedDicts` weren't updated to match. Caused mypy to flag legitimate
usage as an error.
description by @mdrxy
- Enable `test_responses_spec.py` integration tests that were previously
skipped at module level
- Widen `ToolStrategy.schema` type annotation from `type[SchemaT]` to
`type[SchemaT] | dict[str, Any]` to match actual supported usage (JSON
schema dicts were already handled at runtime)
- Fix type annotations and linting issues in test file (modernize to
`dict`/`list`, add return types, prefix unused `_request` param)
- Improve generic typing in `load_spec` utility with bounded `TypeVar`
Co-authored-by: Mason Daugherty <mason@langchain.dev>
# feat(core): add more file extensions to ignore in HTML link extraction
## Description
This PR enhances the HTML link extraction utility in
`libs/core/langchain_core/utils/html.py` by expanding the
`SUFFIXES_TO_IGNORE` list to include additional common binary file
extensions:
- `.webp`
- `.pdf`
- `.docx`
- `.xlsx`
- `.pptx`
- `.pptm`
These file types are non-HTML, non-crawlable resources. Ignoring them
prevents `find_all_links` and `extract_sub_links` from mistakenly
treating such binary assets as navigable links. This improves link
filtering, reduces unnecessary crawling, and aligns behavior with
typical web scraping expectations.
## Summary of Changes
- **Updated** `libs/core/langchain_core/utils/html.py`: Added `.webp`,
`.pdf`, `.docx`, `.xlsx`, `.pptx`, `.pptm` to `SUFFIXES_TO_IGNORE`.
## Related Issues
N/A
## Verification
- `ruff check libs/core/langchain_core/utils/html.py`: **Passed**
- `mypy libs/core/langchain_core/utils/html.py`: **Passed**
- `pytest libs/core/tests/unit_tests/utils/test_html.py`: **Passed** (11
tests)
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
# refactor(core): improve docstrings for HTML link extraction utilities
## Description
This PR updates and clarifies the docstrings for `find_all_links` and
`extract_sub_links` in
`libs/core/langchain_core/utils/html.py`.
The previous return-value descriptions were vague (e.g., "all links",
"sub links"). They have now been revised to clearly describe the
behavior and output of each function:
- **find_all_links** → “A list of all links found in the HTML.”
- **extract_sub_links** → “A list of absolute paths to sub links.”
These improvements make the utilities more understandable and
developer-friendly without altering functionality.
## Verification
- `ruff check libs/core/langchain_core/utils/html.py`: **Passed**
- `pytest libs/core/tests/unit_tests/utils/test_html.py`: **Passed**
## Checklists
- PR title follows the required format: `TYPE(SCOPE): DESCRIPTION`
- Changes are limited to the `langchain-core` package
- `make format`, `make lint`, and `make test` pass
Fixes#34282
**Before:** When using agents with tools (like file reading, web search,
etc.), the conversation looks like this:
```
[User] "Read these 10 files and summarize them"
[AI] "I'll read all 10 files" + [tool_call: read_file x 10]
[Tool] "Contents of file1.txt..."
[Tool] "Contents of file2.txt..."
[Tool] "Contents of file3.txt..."
... (7 more tool responses)
```
When the conversation gets too long, `SummarizationMiddleware` kicks in
to compress older messages. The problem was:
If you asked to keep the last 6 messages, you'd get:
```
[Summary] "Here's what happened before..."
[Tool] "Contents of file5.txt..."
[Tool] "Contents of file6.txt..."
[Tool] "Contents of file7.txt..."
[Tool] "Contents of file8.txt..."
[Tool] "Contents of file9.txt..."
[Tool] "Contents of file10.txt..."
```
The AI's original request to read the files (`[AI]` message with
`tool_calls`) was summarized away, but the tool responses remained. This
caused the error:
```
Error code: 400 - "No tool call found for function call output with call_id..."
```
Many APIs require that every tool response has a matching tool request.
Without the AI message, the tool responses are "orphaned."
## The fix
Now when the cutoff lands on tool messages, we **move backward** to
include the AI message that requested those tools:
Same scenario, keeping last 6 messages:
```
[Summary] "Here's what happened before..."
[AI] "I'll read all 10 files" + [tool_call: read_file x 10]
[Tool] "Contents of file1.txt..."
[Tool] "Contents of file2.txt..."
... (all 10 tool responses)
```
The AI message is preserved along with its tool responses, keeping them
paired together.
## Practical examples
### Example 1: Parallel tool calls
**Scenario:** Agent reads 10 files in parallel, summarization triggers
(see above)
### Example 2: Mixed conversation
**Scenario:** User asks question, AI uses tools, user says thanks
```
[User] "What's the weather?"
[AI] "Let me check" + [tool_call: get_weather]
[Tool] "72F and sunny"
[AI] "It's 72F and sunny!"
[User] "Thanks!"
```
Keeping last 2 messages:
| Before (Bug) | After (Fix) |
|--------------|-------------|
| Only `[User] "Thanks!"` kept | `[AI] + [Tool] + [AI] + [User]` all
kept |
| Lost the weather info | Tool pair preserved with response |
### Example 3: Multiple tool sequences
```
[User] "Search for X"
[AI] [tool_call: search]
[Tool] "Results for X"
[User] "Now search for Y"
[AI] [tool_call: search]
[Tool] "Results for Y"
[User] "Great!"
```
**Keeping last 3 messages:** If cutoff lands on `[Tool] "Results for
Y"`, we now include `[AI] [tool_call: search]` to keep the pair
together.
Add unit coverage for chat model provider inference across common model
name prefixes. This improves regression protection without touching
runtime
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Fixes a bug introduced with commit 85f1ba2 (released in `langchain ==
1.2.1`).
Whenever the index embedding of the langgraph-server is configured with
`azure_openai` provider, the wrong class is going to be initialized (and
fails to do so if the now unexpected credentials in environment variable
`OPENAI_API_KEY` is not provided).
Example configuration file `langgraph.json` that will reproduce the
issue:
(see
https://docs.langchain.com/langsmith/cli#adding-semantic-search-to-the-store)
```json
{
"dependencies": ["."],
"graphs": {
"chat": "src/agents/chat/graph.py:graph",
},
"store": {
"index": {
"embed": "azure_openai:text-embedding-3-small",
"dims": 1536
}
},
"python_version": "3.13",
"image_distro": "wolfi"
}
```
The agent should only make a single call to update the todo list at a
time. A parallel call doesn't make sense, but also cannot work as
there's no obvious reducer to use.
On parallel calls of the todo tool, we return ToolMessage containing to
guide the LLM to not call the tool in parallel.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Fixes#34517
Supersedes #34557, #34570
Fixes token inflation in `SummarizationMiddleware` that caused context
window overflow during summarization.
**Root cause:** When formatting messages for the summary prompt,
`str(messages)` was implicitly called, which includes all Pydantic
metadata fields (`usage_metadata`, `response_metadata`,
`additional_kwargs`, etc.). This caused the stringified representation
to use ~2.5x more tokens than `count_tokens_approximately` estimates.
**Problem:**
- Summarization triggers at 85% of context window based on
`count_tokens_approximately`
- But `str(messages)` in the prompt uses 2.5x more tokens
- Results in `ContextLengthExceeded`
**Fix:** Use `get_buffer_string()` to format messages, which produces
compact output:
```
Human: What's the weather?
AI: Let me check...[tool_calls]
Tool: 72°F and sunny
```
Instead of verbose Pydantic repr:
```python
[HumanMessage(content='What's the weather?', additional_kwargs={}, response_metadata={}), ...]
```
Fixed typo in ImportError messages where "langchain experiment" should
be "langchain_experimental" for consistency with the actual package
name.
This helps improve clarity for users who encounter these error messages
when trying to use deprecated tools that have moved to the
langchain_experimental package.
Related issues: #13858, #13859
Co-authored-by: Ademola <ademicho@gmail>
**Description:**
*Closes
#[33883](https://github.com/langchain-ai/langchain/issues/33883)*
Chat model cache keys are generated by serializing messages via
`dumps(messages)`. The optional `BaseMessage.id` field (a UUID used
solely for tracing/threading) is included in this serialization, causing
functionally identical messages to produce different cache keys. This
results in repeated API calls, cache bloat, and degraded performance in
production workloads (e.g., agents, RAG chains, long conversations).
This change normalizes messages **only for cache key generation** by
stripping the nonsemantic `id` field using Pydantic V2’s
`model_copy(update={"id": None})`. The normalization is applied in both
synchronous and asynchronous cache paths (`_generate_with_cache` /
`_agenerate_with_cache`) immediately before `dumps()`.
```python
normalized_messages = [
msg.model_copy(update={"id": None})
if getattr(msg, "id", None) is not None
else msg
for msg in messages
]
prompt = dumps(normalized_messages)
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Summary
Fixes an issue where HTMLSemanticPreservingSplitter failed to preserve
elements nested inside non-container tags. With these changes, preserved
elements are now correctly detected and handled at any nesting depth.
Root Cause
`_process_element()` only recursed into a small set of hard-coded
container tags (`html`, `body`, `div`, `main`). For other tags, the
subtree was flattened into text, preventing nested preserved elements
(inside `<p>`, `<section>`, `<article>`, etc.) from being detected.
Fix
- Updated traversal logic in _process_element (html.py) to recursively
process child elements for any tag that contains nested elements
- Avoided duplicate text extraction
- Preserved correct placeholder ordering
- Treated leaf nodes as text only
Tests
Adds regression tests covering preserved elements nested inside
non-container tags, including:
- table inside section
- nested divs
- code inside paragraph
All existing tests pass (make lint, format, test, etc).
Breaking changes
None.
Fixes
Fixes#31569
Disclaimer
GitHub Copilot was used to assist with test case design in
test_text_splitters.py and documentation comments; all code logic was
manually implemented and reviewed.
---------
Co-authored-by: julih <julih@julihs-MacBook-Pro.local>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
This PR updates an outdated GitHub Action version.
- Updated `astral-sh/setup-uv` from `v6` to `v7` in
`.github/actions/uv_setup/action.yml`
Looks like this was missed as part of
https://github.com/langchain-ai/langchain/pull/33457 so hopefully safe
to bring it into alignment.
Addresses a flaky test
When executing `exit 1` as a startup command, the shell process
terminates immediately. The code then tries to write a marker command
(`printf '...'`) to stdin, but the pipe is already broken because the
shell has exited, causing `BrokenPipeError`.
* Support sentence-transformers optional dep on python 3.14
* Bump some dep locks to use pre-built wheels instead of building them
(murmurhash, cymem, preshed, thinc, srsly, blis)
* Still not possible to use spacy: even though there are wheels
available, spacy depends on Pydantic v1 which doesn't work on Python
3.14.
* Speeds up installation and CI.
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Bump lock of MarkupSafe to 3.0.3 which has Python 3.14 pre-built wheels.
Speeds up installation and CI.
Co-authored-by: Mason Daugherty <mason@langchain.dev>
The Code of Conduct link was pointing to a non-existent file path.
Updated to use GitHub's community standards tab URL which correctly
displays the Code of Conduct.
Changed from:
https://github.com/langchain-ai/langchain/blob/master/.github/CODE_OF_CONDUCT.md
To:
https://github.com/langchain-ai/langchain/?tab=coc-ov-file
(Replace this entire block of text)
Read the full contributing guidelines:
https://docs.langchain.com/oss/python/contributing/overview
Thank you for contributing to LangChain! Follow these steps to have your
pull request considered as ready for review.
1. PR title: Should follow the format: TYPE(SCOPE): DESCRIPTION
- Examples:
- fix(anthropic): resolve flag parsing error
- feat(core): add multi-tenant support
- test(openai): update API usage tests
- Allowed TYPE and SCOPE values:
https://github.com/langchain-ai/langchain/blob/master/.github/workflows/pr_lint.yml#L15-L33
2. PR description:
- Write 1-2 sentences summarizing the change.
- If this PR addresses a specific issue, please include "Fixes
#ISSUE_NUMBER" in the description to automatically close the issue when
the PR is merged.
- If there are any breaking changes, please clearly describe them.
- If this PR depends on another PR being merged first, please include
"Depends on #PR_NUMBER" inthe description.
3. Run `make format`, `make lint` and `make test` from the root of the
package(s) you've modified.
- We will not consider a PR unless these three are passing in CI.
Additional guidelines:
- We ask that if you use generative AI for your contribution, you
include a disclaimer.
- PRs should not touch more than one package unless absolutely
necessary.
- Do not update the `uv.lock` files unless or add dependencies to
`pyproject.toml` files (even optional ones) unless you have explicit
permission to do so by a maintainer.
Extract strict from kwargs and pass it to convert_to_openai_tool when
converting tools. This ensures that when strict is provided, it's
properly used during tool conversion and removed from kwargs before
calling the parent bind method.
Also extract reasoning_content from API responses and store it in
additional_kwargs for AIMessage objects.
Fixes https://github.com/langchain-ai/langchain/issues/34341 and
https://github.com/langchain-ai/langchain/issues/34342
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
### Description
`ChatPromptTemplate.from_messages` supports multiple tuple formats for
defining message templates. One documented format is `(message class,
template)`, which allows users to specify the message type using the
class directly:
```python
ChatPromptTemplate.from_messages([
(SystemMessage, "You are a helpful assistant named {name}."),
(HumanMessage, "{input}"),
])
```
However, this syntax was broken. Passing a tuple like `(HumanMessage,
"{input}")` would raise a Pydantic validation error because the
conversion logic in `_convert_to_message_template` didn't handle
`BaseMessage` subclasses—it only recognized string-based role
identifiers like `"human"` or `"system"`.
This PR adds the missing branch to detect when the first element of a
tuple is a message class (by checking for the `type` class attribute)
and routes it through `_create_template_from_message_type`, which
already knows how to create the appropriate `MessagePromptTemplate` for
each message type.
### Changes
- Updated `_convert_to_message_template` to properly support `(message
class, template)` tuples
### Testing
Added 16 comprehensive unit tests covering:
- Basic usage with `HumanMessage`, `AIMessage`, and `SystemMessage`
classes
- Integration with `invoke()` method
- Mixed syntax (message class tuples alongside string tuples)
- Multiple template variables
- Edge cases: empty templates, static text (no variables)
- Correct extraction of `input_variables`
- Partial variables support
- Combination with `MessagesPlaceholder`
- Mustache template format
- Template operations: `append()`, `extend()`, concatenation, and
slicing
- Special characters and unicode in templates
### Issue
Fixes#33791
### Dependencies
None
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
This PR adds a regression test covering the JSON Schema `$ref` pattern
found in
MCP-style schemas, where a `$ref` points into a list-based structure
such as:
#/properties/body/anyOf/1/properties/Message/properties/bccRecipients/items
This pattern historically failed due to incorrect handling of numeric
list
components in `_retrieve_ref`. The underlying bug has since been fixed,
and
this test ensures coverage so we don't regress on list-index `$ref`
resolution.
The new test (`test_dereference_refs_list_index_items_ref_mcp_like`)
verifies:
- correct traversal into `anyOf[1]`
- proper dereferencing of `items.$ref`
- no errors thrown
- `ccRecipients.items` is identical to the resolved schema of
`bccRecipients.items`
No code changes are included, just the one test — this PR adds coverage
to preserve the expected
behavior and documents support for this real-world MCP schema pattern.
Related to #32012.
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
## Description
Fixed `BaseCallbackManager.merge()` method to correctly preserve the
distinction between `handlers` and `inheritable_handlers` during merge
operations.
Previously, the merge method was using `add_handler()` which incorrectly
added handlers to both lists when `inherit=True`, causing
cross-contamination between regular and inheritable handlers.
The fix directly passes the combined handler lists to the constructor
instead of using `add_handler()`, ensuring proper separation is
maintained.
## Issue
Fixes#32028
## Dependencies
None
## Testing
- Modified existing test `test_merge_preserves_handler_distinction()` to
verify handlers remain properly separated after merge
## Checklist
- [x] **Breaking Changes**: No breaking changes - only fixes incorrect
behavior
- [x] **Type Hints**: All functions have complete type annotations
- [x] **Tests**: Fix is fully tested with existing unit test
- [x] **Security**: No security implications
- [x] **Documentation**: No documentation changes needed - bug fix only
- [x] **Code Quality**: Passes lint and format checks
- [x] **Commit Message**: Follows Conventional Commits format
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
* FIxed where possible
* Used `cast` when not possible to fix
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
## Problem
The `draw_mermaid_png()` function fails with HTTP 400 when using named
background colors like `white`. This is because named colors get
prefixed with `!` (e.g., `!white`) but this special character is not
URL-encoded before being added to the API URL.
As reported in #34444, the URL parameter `bgColor=!white` causes
mermaid.ink to return a 400 Bad Request error.
## Solution
URL-encode the `background_color` parameter using `urllib.parse.quote()`
before constructing the API URL. This ensures special characters like
`!` are properly encoded as `%21`.
## Changes
- Added `import urllib.parse`
- URL-encode `background_color` value with
`urllib.parse.quote(str(background_color), safe="")`
- Added 2 unit tests:
- `test_mermaid_bgcolor_url_encoding`: Verifies named colors are
properly encoded
- `test_mermaid_bgcolor_hex_not_encoded`: Verifies hex colors work
correctly
## Testing
```bash
pytest tests/unit_tests/runnables/test_graph.py::test_mermaid_bgcolor_url_encoding -v
pytest tests/unit_tests/runnables/test_graph.py::test_mermaid_bgcolor_hex_not_encoded -v
```
Both tests pass.
Fixes#34444
---
*This contribution was made with AI assistance (Claude).*
Co-authored-by: Mr-Neutr0n <mrneutron@users.noreply.github.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
URL-encode the bgColor parameter to fix 400 errors from mermaid.ink API.
The `!` character in `!white` was not encoded, causing API failures.
Fixes#34444
Moves `_ORIGIN_MAP` dict from inside `_py_38_safe_origin()` to module
level constant. This avoids dict allocation on every function call,
reducing garbage collection pressure during frequent tool conversions.
The function is called during typed dict to pydantic model conversion
which happens during tool binding and invocation - a hot path in
LangChain.
**Testing:** `make lint` passes
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
* Fixed a few TC
* Added a few Pydantic classes to
`flake8-type-checking.runtime-evaluated-base-classes` (not as much as I
would have imagined)
* Added a few `noqa: TC`
* Activated TC rules
Moves hex color validation regex from inside
`_render_mermaid_using_api()` to module-level constant
`_HEX_COLOR_PATTERN`. This avoids recompiling the regex on every
function call, improving performance when rendering multiple Mermaid
graphs.
**Testing:**
- `make lint` passes
- `make test` passes
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
## Summary
Enhances the `init_chat_model` function with comprehensive input
validation, improved model inference patterns, and better error handling
to provide a significantly improved user experience.
## Changes Made
- ✅ **Input Validation**: Added comprehensive type and value checking
for all parameters
- ✅ **Enhanced Model Inference**: Improved pattern matching with
case-insensitive support and new model patterns
- ✅ **Better Error Messages**: Detailed error messages with examples and
documentation links
- ✅ **Comprehensive Tests**: Added extensive test coverage for all new
functionality
- ✅ **Documentation**: Enhanced docstrings and examples
## Backward Compatibility
All changes are fully backward compatible. No breaking changes
introduced.
## Testing
- Added 6 new test functions covering input validation, model inference,
and error handling
- All existing tests continue to pass
- Comprehensive parametrized testing for various model patterns
## User Experience Improvements
- Better error messages help users quickly resolve configuration issues
- Enhanced model inference reduces the need to specify providers
explicitly
- Comprehensive input validation catches issues early with helpful
guidance
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
## Summary
Fixes#34247
When using `Annotated[type, Field(description="...")]` syntax with the
`@tool` decorator, field descriptions were being lost during schema
generation. The `_get_annotation_description()` function only checked
for string annotations but not for Pydantic `FieldInfo` objects.
## Changes
- Extended `_get_annotation_description()` to also extract descriptions
from `FieldInfo` objects within `Annotated` types
- Added import for `pydantic.fields.FieldInfo`
- Added unit test to verify `Field(description=...)` is preserved
## Why this approach
The fix is minimal and targeted - it extends the existing description
extraction logic rather than restructuring the schema generation. This
maintains backward compatibility while supporting both annotation
styles:
```python
# Both now work correctly:
topic: Annotated[str, "The research topic"] # existing
topic: Annotated[str, Field(description="...")] # now fixed
```
## Known limitation
This fix only handles `pydantic.fields.FieldInfo` (Pydantic v2). The v1
compatibility layer (`pydantic.v1.fields.FieldInfo`) is a different
class and will not have descriptions extracted. This is intentional:
- Pydantic v1 is deprecated; users should migrate to v2
- The v1 compat layer exists for legacy model migration, not new tool
definitions
- Duck-typing on `description` attribute could match unintended objects
If v1 `Field` support is needed, it can be addressed in a follow-up PR
with explicit handling.
## Testing
- Added `test_tool_field_description_preserved()` covering required and
optional params
- Verified existing `test_tool_annotated_descriptions` still passes
- Lint and type checks pass
---
> [!NOTE]
> This PR was developed with AI agent assistance (Factory/Droid).
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
## Summary
- Fixes issue where Pydantic default values from `args_schema` were not
passed to tool functions when the caller omits optional arguments
- Modified `_parse_input()` in `libs/core/langchain_core/tools/base.py`
to include fields with non-None defaults
- Added unit tests to verify default args behavior for both sync and
async tools
## Problem
When a tool has an `args_schema` with default values:
```python
class SearchArgs(BaseModel):
query: str = Field(..., description="Search query")
page: int = Field(default=1, description="Page number")
size: int = Field(default=10, description="Results per page")
@tool("search", args_schema=SearchArgs)
def search_tool(query: str, page: int, size: int) -> str:
return f"query={query}, page={page}, size={size}"
# This threw: TypeError: search_tool() missing 2 required positional arguments
search_tool.invoke({"query": "test"})
```
The defaults from `args_schema` were being discarded because
`_parse_input()` filtered validated results to only include keys from
the original input.
## Solution
Changed the filtering logic to:
1. Include all fields that were in the original input (validated)
2. Also include fields with non-None defaults from the Pydantic schema
This applies user-defined defaults (like `Field(default=1)`) while
excluding synthetic fields from `*args`/`**kwargs` which have
`default=None`.
## Test plan
- [x] Added `test_tool_args_schema_default_values` - tests sync tool
with defaults
- [x] Added `test_tool_args_schema_default_values_async` - tests async
tool with defaults
- [x] All existing tests pass (150 passed, 4 skipped)
- [x] Lint passes
Fixes#34384
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
## Summary
Fixes#33970
`get_buffer_string` was only checking for the deprecated `function_call`
field in `additional_kwargs`, which modern LLM providers no longer
return. This fix updates the function to check for the modern
`tool_calls` field first, falling back to `function_call` for legacy
compatibility.
## Changes
- Check `AIMessage.tool_calls` first (modern standard)
- Fall back to `additional_kwargs["function_call"]` (legacy support)
- Added 3 unit tests covering tool_calls, empty content, and precedence
behavior
## Testing
```python
# Before fix: tool_calls info was lost
msg = AIMessage(content="Hi", tool_calls=[{"name": "search", ...}])
get_buffer_string([msg]) # "AI: Hi" (no tool info)
# After fix: tool_calls are included
get_buffer_string([msg]) # "AI: Hi[{\"name\": \"search\", ...}]"
```
- All existing `get_buffer_string` tests pass
- Legacy `function_call` behavior preserved
---
> [!NOTE]
> This PR was developed with AI agent assistance (Factory/Droid).
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Adds [PEP 702](https://peps.python.org/pep-0702/) `__deprecated__`
attribute support to the `@deprecated` decorator, enabling IDE and type
checker integration for deprecation warnings.
---
PEP 702 introduced the `__deprecated__` attribute convention, which type
checkers (Pyright, mypy) and IDEs (VS Code with Pylance, PyCharm) can
use to surface deprecations directly in the editor. This PR sets
`__deprecated__` on all objects decorated with `@deprecated`.
With this change, developers using supported IDEs will see:
- **Strikethrough text** on deprecated symbols
- **Hover messages** showing the deprecation reason and suggested
alternative
- **Diagnostic warnings** during type checking (e.g., `pyright`, `mypy`)
### References
- [PEP 702 – Marking deprecations using the type
system](https://peps.python.org/pep-0702/)
- [`typing.deprecated`
specification](https://typing.python.org/en/latest/spec/directives.html#deprecated)
Adds automatic tool call counting to tracing by means of a new
`store_tool_call_count_in_run()`, which calls on newly added
`count_tool_calls_in_run()`.
Runs on successful LLM completion. Does not run on errored runs.
### Description:
earlier we have to use like below:
```python
from langchain_core.messages import trim_messages
from langchain_core.messages.utils import count_tokens_approximately
trim_messages(..., token_counter=count_tokens_approximately)
```
Now can be used as like this also
```python
from langchain_core.messages import trim_messages
trim_messages(..., token_counter="approximate")
```
- [x] **Added tests**
- [x] **Lint and test**: Run this as I made change in langchain/core, uv
run --group test pytest tests/unit_tests/messages/test_utils.py -v
<img width="1006" height="66" alt="image"
src="https://github.com/user-attachments/assets/c6938c29-a781-4e7f-871b-8e888ee764b7"
/>
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Adds `usage_metadata` (token counts, etc.) to the run metadata in
`LangChainTracer`.
When an LLM run ends, usage metadata is extracted from all generations
and aggregated using the existing `add_usage` helper, then stored in
`run.extra["metadata"]["usage_metadata"]`.
The original data in outputs remains unchanged.
Also, see #34415
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
ref https://github.com/langchain-ai/langchainjs/pull/9665
Fixes trace persistence for iterator/generator inputs (like
`RunnableGenerator`) where the full input isn't available at chain
start. Instead of POSTing a run with incomplete inputs on start and
PATCHing later, this defers the POST until chain end when inputs are
fully realized.
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Replace direct `__annotations__` access with `get_type_hints()` in
`_convert_any_typed_dicts_to_pydantic` to handle [PEP
649](https://peps.python.org/pep-0649/) deferred annotations in Python
3.14:
> [`Changed in version 3.14: Annotations are now lazily evaluated by
default`](https://docs.python.org/3/reference/compound_stmts.html#annotations)
Before:
```python
class MyTool(TypedDict):
name: str
MyTool.__annotations__ # {'name': 'str'} - string, not type
issubclass('str', ...) # TypeError: arg 1 must be a class
```
After:
```python
get_type_hints(MyTool) # {'name': <class 'str'>} - actual type
```
Fixes#34291
Just a small fix of some broken hyperlinks in the documentation of the
function `langchain_openai/chat_models/base.py#with_structured_output`
and a rephrase of the reference to supported models.
Co-authored-by: Thomas Reuhl <thomas.reuhl@telekom.de>
Bumps
[actions/download-artifact](https://github.com/actions/download-artifact)
from 6 to 7.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/actions/download-artifact/releases">actions/download-artifact's
releases</a>.</em></p>
<blockquote>
<h2>v7.0.0</h2>
<h2>v7 - What's new</h2>
<blockquote>
<p>[!IMPORTANT]
actions/download-artifact@v7 now runs on Node.js 24 (<code>runs.using:
node24</code>) and requires a minimum Actions Runner version of 2.327.1.
If you are using self-hosted runners, ensure they are updated before
upgrading.</p>
</blockquote>
<h3>Node.js 24</h3>
<p>This release updates the runtime to Node.js 24. v6 had preliminary
support for Node 24, however this action was by default still running on
Node.js 20. Now this action by default will run on Node.js 24.</p>
<h2>What's Changed</h2>
<ul>
<li>Update GHES guidance to include reference to Node 20 version by <a
href="https://github.com/patrikpolyak"><code>@patrikpolyak</code></a>
in <a
href="https://redirect.github.com/actions/download-artifact/pull/440">actions/download-artifact#440</a></li>
<li>Download Artifact Node24 support by <a
href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a
href="https://redirect.github.com/actions/download-artifact/pull/415">actions/download-artifact#415</a></li>
<li>fix: update <code>@actions/artifact</code> to fix Node.js 24
punycode deprecation by <a
href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a
href="https://redirect.github.com/actions/download-artifact/pull/451">actions/download-artifact#451</a></li>
<li>prepare release v7.0.0 for Node.js 24 support by <a
href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a
href="https://redirect.github.com/actions/download-artifact/pull/452">actions/download-artifact#452</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/patrikpolyak"><code>@patrikpolyak</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/download-artifact/pull/440">actions/download-artifact#440</a></li>
<li><a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/download-artifact/pull/415">actions/download-artifact#415</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/download-artifact/compare/v6.0.0...v7.0.0">https://github.com/actions/download-artifact/compare/v6.0.0...v7.0.0</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="37930b1c2a"><code>37930b1</code></a>
Merge pull request <a
href="https://redirect.github.com/actions/download-artifact/issues/452">#452</a>
from actions/download-artifact-v7-release</li>
<li><a
href="72582b9e0a"><code>72582b9</code></a>
doc: update readme</li>
<li><a
href="0d2ec9d4cb"><code>0d2ec9d</code></a>
chore: release v7.0.0 for Node.js 24 support</li>
<li><a
href="fd7ae8fda6"><code>fd7ae8f</code></a>
Merge pull request <a
href="https://redirect.github.com/actions/download-artifact/issues/451">#451</a>
from actions/fix-storage-blob</li>
<li><a
href="d484700543"><code>d484700</code></a>
chore: restore minimatch.dep.yml license file</li>
<li><a
href="03a808050e"><code>03a8080</code></a>
chore: remove obsolete dependency license files</li>
<li><a
href="56fe6d904b"><code>56fe6d9</code></a>
chore: update <code>@actions/artifact</code> license file to 5.0.1</li>
<li><a
href="8e3ebc4ab4"><code>8e3ebc4</code></a>
chore: update package-lock.json with <code>@actions/artifact</code><a
href="https://github.com/5"><code>@5</code></a>.0.1</li>
<li><a
href="1e3c4b4d49"><code>1e3c4b4</code></a>
fix: update <code>@actions/artifact</code> to ^5.0.0 for Node.js 24
punycode fix</li>
<li><a
href="458627d354"><code>458627d</code></a>
chore: use local <code>@actions/artifact</code> package for Node.js 24
testing</li>
<li>Additional commits viewable in <a
href="https://github.com/actions/download-artifact/compare/v6...v7">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps
[actions/upload-artifact](https://github.com/actions/upload-artifact)
from 5 to 6.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/actions/upload-artifact/releases">actions/upload-artifact's
releases</a>.</em></p>
<blockquote>
<h2>v6.0.0</h2>
<h2>v6 - What's new</h2>
<blockquote>
<p>[!IMPORTANT]
actions/upload-artifact@v6 now runs on Node.js 24 (<code>runs.using:
node24</code>) and requires a minimum Actions Runner version of 2.327.1.
If you are using self-hosted runners, ensure they are updated before
upgrading.</p>
</blockquote>
<h3>Node.js 24</h3>
<p>This release updates the runtime to Node.js 24. v5 had preliminary
support for Node.js 24, however this action was by default still running
on Node.js 20. Now this action by default will run on Node.js 24.</p>
<h2>What's Changed</h2>
<ul>
<li>Upload Artifact Node 24 support by <a
href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a
href="https://redirect.github.com/actions/upload-artifact/pull/719">actions/upload-artifact#719</a></li>
<li>fix: update <code>@actions/artifact</code> for Node.js 24 punycode
deprecation by <a
href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a
href="https://redirect.github.com/actions/upload-artifact/pull/744">actions/upload-artifact#744</a></li>
<li>prepare release v6.0.0 for Node.js 24 support by <a
href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a
href="https://redirect.github.com/actions/upload-artifact/pull/745">actions/upload-artifact#745</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/upload-artifact/compare/v5.0.0...v6.0.0">https://github.com/actions/upload-artifact/compare/v5.0.0...v6.0.0</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="b7c566a772"><code>b7c566a</code></a>
Merge pull request <a
href="https://redirect.github.com/actions/upload-artifact/issues/745">#745</a>
from actions/upload-artifact-v6-release</li>
<li><a
href="e516bc8500"><code>e516bc8</code></a>
docs: correct description of Node.js 24 support in README</li>
<li><a
href="ddc45ed9bc"><code>ddc45ed</code></a>
docs: update README to correct action name for Node.js 24 support</li>
<li><a
href="615b319bd2"><code>615b319</code></a>
chore: release v6.0.0 for Node.js 24 support</li>
<li><a
href="017748b48f"><code>017748b</code></a>
Merge pull request <a
href="https://redirect.github.com/actions/upload-artifact/issues/744">#744</a>
from actions/fix-storage-blob</li>
<li><a
href="38d4c7997f"><code>38d4c79</code></a>
chore: rebuild dist</li>
<li><a
href="7d27270e0c"><code>7d27270</code></a>
chore: add missing license cache files for <code>@actions/core</code>,
<code>@actions/io</code>, and mi...</li>
<li><a
href="5f643d3c94"><code>5f643d3</code></a>
chore: update license files for <code>@actions/artifact</code><a
href="https://github.com/5"><code>@5</code></a>.0.1 dependencies</li>
<li><a
href="1df1684032"><code>1df1684</code></a>
chore: update package-lock.json with <code>@actions/artifact</code><a
href="https://github.com/5"><code>@5</code></a>.0.1</li>
<li><a
href="b5b1a91840"><code>b5b1a91</code></a>
fix: update <code>@actions/artifact</code> to ^5.0.0 for Node.js 24
punycode fix</li>
<li>Additional commits viewable in <a
href="https://github.com/actions/upload-artifact/compare/v5...v6">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Issues with combining flex and nano
```shell
FAILED tests/integration_tests/chat_models/test_base.py::test_openai_invoke - openai.InternalServerError: Error code: 500 - {'error': {'message': 'The server had an error while processing your request. Sorry about that!', 'type': 'server_error', 'param': None, 'code': None}}
FAILED tests/integration_tests/chat_models/test_base.py::test_stream - openai.InternalServerError: Error code: 500 - {'error': {'message': 'The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID req_e726769d95994fd4bccbe55680a35f59 in your email.)', 'type': 'server_error', 'param': None, 'code': None}}
FAILED tests/integration_tests/chat_models/test_base.py::test_flex_usage_responses[False] - openai.InternalServerError: Error code: 500 - {'error': {'message': 'An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID req_935316418319494d8682e4adcd67ab47 in your message.', 'type': 'server_error', 'param': None, 'code': 'server_error'}}
FAILED tests/integration_tests/chat_models/test_base.py::test_flex_usage_responses[True] - openai.APIError: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID req_f3c164d0d1f045a5a0f5965ab5c253bf in your message.
```
If the `stdout` "done marker" arrives before the `stderr` output is
enqueued, the method returns early without capturing the `stderr` line.
The two reader threads run independently with no synchronization
guaranteeing `stderr` arrives before the done marker.
In environments with Python 3.10, timing differences can cause the
`stdout` marker to win the race, resulting in `<no output>` instead of
`[stderr]` error.
Observed as a flaky test on `test_stderr_output_labeling` in CI:
```shell
FAILED tests/unit_tests/agents/middleware/implementations/test_shell_tool.py::test_stderr_output_labeling - AssertionError: assert '[stderr] error' in '<no output>'
```
Use of the fixture `_base_vcr_config` is deprecated with alternative
function `base_vcr_config()`
This way:
* we don't need to import `_base_vcr_config` seen as unused (which leads
to ruff violations PLC0414 and F811)
* we don't need to make a copy since a new dict is created at each
function invocation
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Added test that fails on `master`.
`ToolNode` uses `get_type_hints` which doesn't work properly w/ partial
funcs on Python 3.12+
The diff here is nice anyways when we inline the logic.
## Summary
When invoking a tool with a `ToolCall`, the `tool_call_id` is extracted
but was **not forwarded** to callback handlers in `on_tool_start`. This
made it impossible for callback handlers to correlate tool executions
with the original LLM tool calls.
This fix adds `tool_call_id=tool_call_id` to both:
- Sync `run()` method's `on_tool_start` call
- Async `arun()` method's `on_tool_start` call
## Changes
- **`libs/core/langchain_core/tools/base.py`**: Added `tool_call_id`
parameter to `on_tool_start` calls (2 lines)
- **`libs/core/tests/unit_tests/test_tools.py`**: Added 6 comprehensive
tests covering:
- Sync tool invocation via `invoke()`
- Async tool invocation via `ainvoke()`
- `tool_call_id` is `None` when invoked without a ToolCall
- Empty string `tool_call_id` edge case
- Direct `run()` method
- Direct `arun()` method
## Test plan
- [x] All 147 existing tests pass
- [x] 6 new tests added and passing
- [x] Linting passes
Fixes#34168
---
This PR was developed with AI assistance (Claude).
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
With this we get the correct types for `_runnable_support` annotated
functions.
* return list[BaseMessage] when messages is not None
* return Runnable when messages is None
* typing of function args
# PR Title: fix(core): prevent async task garbage collection (RUF006)
## Description
This PR addresses a cryptic issue (flagged by Ruff rule RUF006) where
`asyncio` tasks created via `loop.create_task` could be garbage
collected mid-execution because no strong reference was maintained.
In `libs/core/langchain_core/language_models/llms.py`, the retry
decorator's `_before_sleep` hook creates a fire-and-forget task for
logging/callbacks. If the garbage collector runs before this task
completes, the task may be destroyed, leading to silent failures.
## Changes
- Introduced a module-level set `_background_tasks` to hold strong
references to running tasks.
- Updated `_before_sleep` to add new tasks to this set.
- Added a `done_callback` to remove the task from the set upon
completion, preventing memory leaks.
## Verification
- Verified logic with a standalone script to ensure tasks are
added/removed from the set correctly.
- This is a standard pattern recommended in the Python `asyncio`
documentation.
## Checklist
- [x] I have read the contributing guidelines.
- [x] I have run tests locally (logic verification).
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This PR changes how we find the cutoff for summarization, summarizing
content more eagerly if the initial cutoff point isn't safe (ie, would
break apart AI + tool message pairs)
This new algorithm is quite simple - it looks at the initial cutoff
point, if it's not safe, moves forward through the message list until it
finds the first non tool message.
For example:
```
H
AI
TM
--- theoretical cutoff based keep=('messages', 3)
TM
AI
TM
```
```
H
AI
TM
TM
--- actual cutoff, more aggressive summarization
AI
TM
```
The `HumanInTheLoopMiddleware` is missing a type annotation for the
context schema. Without the fix in this PR, the following code does not
type check:
```
graph = create_agent(
"gpt-5",
tools=[send_email_tool, read_email_tool],
middleware=[
HumanInTheLoopMiddleware(
interrupt_on={
# Require approval or rejection for sending emails
"send_email_tool": {
"allowed_decisions": ["approve", "reject"],
},
# Auto-approve reading emails
"read_email_tool": False,
}
),
],
context_schema=ContextSchema,
)
```
```
Argument of type "list[HumanInTheLoopMiddleware]" cannot be assigned to parameter "middleware" of type "Sequence[AgentMiddleware[StateT_co@create_agent, ContextT@create_agent]]" in function "create_agent"
"HumanInTheLoopMiddleware" is not assignable to "AgentMiddleware[AgentState[Unknown], ContextSchema | None]"
Type parameter "ContextT@AgentMiddleware" is invariant, but "None" is not the same as "ContextSchema | None"
```
- **Description:** if you dont pass in schema= or schema_= to
StrucutredPrompt(...) today you get a confusing KeyError. Raise a more
readable ValueError instead.
- **Issue:** na
- **Dependencies:** na
* `create_agent`'s `system_prompt` allows `str | SystemMessage`
* added `system_message: SystemMessage` on `ModelRequest`
* `ModelRequest.system_prompt` is a function of `system_message.text`,
now deprecated
* disallow setting `system_prompt` and `system_message`
* `ModelRequest.system_prompt` can still be set (w/ custom setattr) for
custom backwards compat, but the updates just get propogated to the
`ModelRequest.system_message`
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- **Description:** When formatting an error, `PydanticOutputParser`
dumps json with default `ensure_ascii=True`
- **Issue:** Fixes#34005
- **Dependencies:** None
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. **We will not consider
a PR unless these three are passing in CI.** See [contribution
guidelines](https://docs.langchain.com/oss/python/contributing) for
more.
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Fixed a bug where GPT-5 temperature validation was case-sensitive,
causing issues when users
specified Azure deployment names or model names in uppercase (e.g.,
`"GPT-5-2025-01-01"`, `"GPT-5-NANO"`). The validation now correctly
handles model names regardless of case.
Changes made:
- Updated `validate_temperature()` method in `BaseChatOpenAI` to perform
case-insensitive
model name comparisons
- Updated `_get_encoding_model()` method to use case-insensitive checks
for tiktoken encoder
selection
- Added comprehensive unit tests to verify case-insensitive behavior
with various case
combinations
**Issue:** Fixes#34003
**Dependencies:** None
**Test Coverage:**
- All existing tests pass
- New test `test_gpt_5_temperature_case_insensitive` covers uppercase,
lowercase, and
mixed-case model names
- Tests verify both non-chat GPT-5 models (temperature removed) and chat
models (temperature
preserved)
- Lint and format checks pass (`make lint`, `make format`)
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
:…l logic
Addresses Issue #34007.
Fixes a bug where aliases like 'mistral:' were inferred correctly as a
provider but the prefix was not stripped from the model name, causing
API 400 errors. Added logic to strip prefix when inference succeeds.
**Description**
This PR resolves a logic error in `init_chat_model` where inferred
provider aliases (specifically `mistral:`) were correctly identified but
not stripped from the model string.
**The Problem**
When passing a string like `mistral:ministral-8b-latest`, the factory
logic correctly inferred the provider as `mistralai` but failed to enter
the string-splitting block because the alias `mistral` was not in the
hardcoded `_SUPPORTED_PROVIDERS` list. This caused the raw string
`mistral:ministral-8b-latest` to be passed to the `ChatMistralAI`
constructor, resulting in a 400 API error.
**The Fix**
I updated `_parse_model` in
`libs/langchain/langchain/chat_models/base.py`. The logic now attempts
to infer the provider from the prefix *before* determining whether to
split the string. This ensures that valid aliases trigger the stripping
logic, passing only the clean `model_name` to the integration class.
**Issue**
Fixes#34007
**Dependencies**
None.
**Verification**
Validated locally with a reproduction script:
- Input: `mistral:ministral-8b-latest`
- Result: Successfully instantiates `ChatMistralAI` with
`model="ministral-8b-latest"`.
- Validated that standard inputs (e.g., `gpt-4o`) remain unaffected.
Co-authored-by: ioop <ioop@Sidharths-MacBook-Air.local>
Closes https://github.com/langchain-ai/langchain/issues/33983
* Adds `ModelRetryMiddleware` modeled after `ToolRetryMiddleware`
* Uses `on_failure` modes of `error` and `continue` to match the
`exit_behavior` modes of model + tool call limit middleware
* In a backwards compatible manner, aligns the API of
`ToolRetryMiddleware`'s `on_failure` with the above
* Centralize common "retry" utils across these middlewares
### Description
This PR adds support for configuring HTTP/HTTPS proxies when rendering
Mermaid diagrams as PNG images using the remote Mermaid.INK API. This
enhancement allows users in restricted network environments to access
the API via a proxy, making the remote rendering feature more robust and
accessible.
The changes include:
- Added optional `proxies` parameter to `draw_mermaid_png` and
`_render_mermaid_using_api` functions
- Updated `Graph.draw_mermaid_png` method to support and pass through
proxy configuration
- Enhanced docstrings with usage examples for the new parameter
- Maintained full backward compatibility with existing code
### Usage Example
```python
proxies = {
"http": "http://127.0.0.1:7890",
"https": "http://127.0.0.1:7890"
}
display(Image(chain.get_graph().draw_mermaid_png(proxies=proxies)))
```
### Dependencies
No new dependencies required. Uses existing `requests` library for HTTP
requests.
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
- Respect 300k token limit for embeddings API requests #33668
- fix create_agent / response_format for Responses API #33939
- fix response.incomplete event is not handled when using
stream_mode=['messages'] #33871
Now returns (`_iter`, `tokens`, `indices`, token_counts`). The
`token_counts` are calculated directly during tokenization, which is
more accurate and efficient than splitting strings later.
## Description
Fixes#31227 - Resolves the issue where `OpenAIEmbeddings` exceeds
OpenAI's 300,000 token per request limit, causing 400 BadRequest errors.
## Problem
When embedding large document sets, LangChain would send batches
containing more than 300,000 tokens in a single API request, causing
this error:
```
openai.BadRequestError: Error code: 400 - {'error': {'message': 'Requested 673477 tokens, max 300000 tokens per request'}}
```
The issue occurred because:
- The code chunks texts by `embedding_ctx_length` (8191 tokens per
chunk)
- Then batches chunks by `chunk_size` (default 1000 chunks per request)
- **But didn't check**: Total tokens per batch against OpenAI's 300k
limit
- Result: `1000 chunks × 8191 tokens = 8,191,000 tokens` → Exceeds
limit!
## Solution
This PR implements dynamic batching that respects the 300k token limit:
1. **Added constant**: `MAX_TOKENS_PER_REQUEST = 300000`
2. **Track token counts**: Calculate actual tokens for each chunk
3. **Dynamic batching**: Instead of fixed `chunk_size` batches,
accumulate chunks until approaching the 300k limit
4. **Applied to both sync and async**: Fixed both
`_get_len_safe_embeddings` and `_aget_len_safe_embeddings`
## Changes
- Modified `langchain_openai/embeddings/base.py`:
- Added `MAX_TOKENS_PER_REQUEST` constant
- Replaced fixed-size batching with token-aware dynamic batching
- Applied to both sync (line ~478) and async (line ~527) methods
- Added test in `tests/unit_tests/embeddings/test_base.py`:
- `test_embeddings_respects_token_limit()` - Verifies large document
sets are properly batched
## Testing
All existing tests pass (280 passed, 4 xfailed, 1 xpassed).
New test verifies:
- Large document sets (500 texts × 1000 tokens = 500k tokens) are split
into multiple API calls
- Each API call respects the 300k token limit
## Usage
After this fix, users can embed large document sets without errors:
```python
from langchain_openai import OpenAIEmbeddings
from langchain_chroma import Chroma
from langchain_text_splitters import CharacterTextSplitter
# This will now work without exceeding token limits
embeddings = OpenAIEmbeddings()
documents = CharacterTextSplitter().split_documents(large_documents)
Chroma.from_documents(documents, embeddings)
```
Resolves#31227
---------
Co-authored-by: Kaparthy Reddy <kaparthyreddy@Kaparthys-MacBook-Air.local>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
* use `override` instead of directly patching things on `ModelRequest`
* rely on `ToolNode` for execution of tools related to said middleware,
using `wrap_model_call` to inject the relevant claude tool specs +
allowing tool node to forward them along to corresponding langchain tool
implementations
* making the same change for the native shell tool middleware
* allowing shell tool middleware to specify a name for the shell tool
(negative diff then for claude bash middleware)
long term I think the solution might be to attach metadata to a tool to
map the provider spec to a langchain implementation, which we could also
take some lessons from on the MCP front.
Wasn't immediately obvious that `get_num_tokens_from_messages` adds
additional prefixes to represent user roles in conversation, which adds
to the overall token count.
```python
from langchain_google_genai import GoogleGenerativeAI
llm = GoogleGenerativeAI(model="gemini-2.5-flash")
num_tokens = llm.get_num_tokens("Hello, world!")
print(f"Number of tokens: {num_tokens}")
# Number of tokens: 4
```
```python
from langchain.messages import HumanMessage
messages = [HumanMessage(content="Hello, world!")]
num_tokens = llm.get_num_tokens_from_messages(messages)
print(f"Number of tokens: {num_tokens}")
# Number of tokens: 6
```
middleware tests have gotten quite unwieldy, major restructuring, sets
the stage for coverage increase
this is super hard to review -- as a proof that we've retained important
tests, I ran coverage on `master` and this branch and confirmed
identical coverage.
* moving all middleware related tests to `agents/middleware` folder
* consolidating related test files
* adding coverage utility to makefile
**Description:** This PR adds support for DeepSeek's beta strict mode
feature for structured
outputs and tool calling. It overrides `bind_tools()` and
`with_structured_output()` to automatically use
DeepSeek's beta endpoint (https://api.deepseek.com/beta) when
`strict=True`. Both methods need overriding because they're independent
entry points and user can call either directly. When DeepSeek's strict
mode graduates from beta, we can just remove both overriden methods. You
can read more about the beta feature here:
https://api-docs.deepseek.com/guides/function_calling#strict-mode-beta
**Issue:** Implements #32670
**Dependencies:** None
**Sample Code**
```python
from langchain_deepseek import ChatDeepSeek
from pydantic import BaseModel, Field
from typing import Optional
import os
# Enter your DeepSeek API Key here
API_KEY = "YOUR_API_KEY"
# location, temperature, condition are required fields
# humidity is optional field with default value
class WeatherInfo(BaseModel):
location: str = Field(description="City name")
temperature: int = Field(description="Temperature in Celsius")
condition: str = Field(description="Weather condition (sunny, cloudy, rainy)")
humidity: Optional[int] = Field(default=None, description="Humidity percentage")
llm = ChatDeepSeek(
model="deepseek-chat",
api_key=API_KEY,
)
# just to confirm that a new instance will use the default base url (instead of beta)
print(f"Default API base: {llm.api_base}")
# Test 1: bind_tools with strict=True shoud list all the tools calls
print("\nTest 1: bind_tools with strict=True")
llm_with_tools = llm.bind_tools([WeatherInfo], strict=True)
response = llm_with_tools.invoke("Tell me the weather in New York. It's 22 degrees, sunny.")
print(response.tool_calls)
# Test 2: with_structured_output with strict=True
print("\nTest 2: with_structured_output with strict=True")
structured_llm = llm.with_structured_output(WeatherInfo, strict=True)
result = structured_llm.invoke("Tell me the weather in New York.")
print(f" Result: {result}")
assert isinstance(result, WeatherInfo), "Result should be a WeatherInfo instance"
```
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
**Description:**
Fixes the OpenCLIP × Chroma regression that caused nested embedding
errors when adding or searching image data.
The test case `test_openclip_chroma_embed_no_nesting_error` has been
restored and verified to work correctly with the current LangChain core
dependencies.
Functional validation confirms that `similarity_search_by_image` now
returns correct, metadata‑preserving results.
**Issue:**
Fixes #33851
**Dependencies:**
No new dependencies introduced.
**Testing:**
All tests under
```bash
uv run --group test pytest tests/unit_tests
```
result:
```
30 passed in 91.26s (0:01:31)
```
have passed successfully using Python 3.13.9 and uv‑managed environment.
This confirms that the regression has been fixed.
Running
```bash
make test
```
still produces cleanup‑time `AttributeError: 'ProactorEventLoop' object
has no attribute '_ssock'` on Windows (Python 3.13+).
This is a benign asyncio teardown message rather than a functional
failure.
`uv run pytest` closes event loops immediately after tests, while `make
test` invokes pytest through a secondary process layer that leaves a
background loop alive at interpreter shutdown.
This difference in teardown behavior explains the extra messages seen
only when using `make test`.
**Summary:**
- Verified the OpenCLIP + Chroma image pipeline works correctly.
- `uv run --group test pytest` fully passes; the fix is complete.
- The residual `_ssock` warnings occur only during
Windows asyncio cleanup and are not related to this code change.
This is my first time contributing code, please contact me with any
questions
---
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
When Groq returns tool calls with no arguments, it sends arguments:
`'null'` (JSON null), but LangChain's core parsing expects either a dict
or converts null to Python None, which fails the `isinstance(args_,
dict)` check and incorrectly marks the tool call as invalid.
Related to #32017
**PR title**
```
docs(langchain): correct IBM provider link in chat_models docstring
```
**PR message**
**Description**
Fix broken link in the `chat_models` docstring. The **ibm** bullet
incorrectly linked to the DeepSeek provider page; update it to the
canonical IBM provider docs.
This only affects generated API reference content on
`reference.langchain.com`. No runtime behavior changes.
**Issue**
N/A (documentation-only).
**Dependencies**
None.
**Testing & quality**
* Ran `make format`, `make lint`, and `make test` in the package (no
code changes expected to affect tests).
Replaces #33618
**Description:** Fixes the bug in the `load()` function where secret
placeholders in plain dicts were not replaced, even if they match a key
in `secrets_map`, and adds a test case.
Example:
```py
obj = {"api_key": "__SECRET_API_KEY__"}
secret_key = "secret_key_1234"
secrets_map = {"__SECRET_API_KEY__": secret_key}
result = load(obj, secrets_map=secrets_map)
```
Before this change, printing `api_key` in `result` would output
`"__SECRET_API_KEY__"`. Now, it will properly output
`"secret_key_1234"`.
**Issue:** Fixes#31804
**Dependencies:** None
`make format`, `make lint`, and `make test` have all passed on my
machine.
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
**Description:**
Adds support for prompt caching usage metadata in ChatGroq. The
integration now captures cached token information from the Groq API
response and includes it in the `input_token_details` field of the
`usage_metadata`.
Changes:
- Created new `_create_usage_metadata()` helper function to centralize
usage metadata creation logic
- Extracts `cached_tokens` from `prompt_tokens_details` in API responses
and maps to `input_token_details.cache_read`
- Integrated the helper function in both streaming
(`_convert_chunk_to_message_chunk`) and non-streaming
(`_create_chat_result`) code paths
- Added comprehensive unit tests to verify caching metadata handling and
backward compatibility
This enables users to monitor prompt caching effectiveness when using
Groq models with prompt caching enabled.
**Issue:** N/A
**Dependencies:** None
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
The `draw_png()` method currently does not support drawing subgraphs.
This PR adds the ability to render subgraph outlines, improving
visualization clarity when working with nested structures.
This PR fixes#32234 and improves HuggingFace chat model integration by:
Ensuring ChatHuggingFace inherits key parameters (temperature,
max_tokens, top_p, streaming, etc.) from the underlying LLM when not
explicitly set.
Adding and updating unit tests to verify property inheritance.
No breaking changes; these updates enhance reliability and
maintainability.
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
- **Description:** Updated Function Signature of `create_agent`, the
system prompt can be both a list and string. I see no harm in doing
this, since SystemMessage accepts both.
- **Issue:** #33630
---------
Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>
The `@shielded` decorator in async callback managers was not preserving
context variables, breaking OpenTelemetry instrumentation and other
context-dependent functionality.
## Problem
When using async callbacks with the `@shielded` decorator (applied to
methods like `on_llm_end`, `on_chain_end`, etc.), context variables were
not being preserved across the shield boundary. This caused issues with:
- OpenTelemetry span context propagation
- Other instrumentation that relies on context variables
- Inconsistent context behavior between sync and async execution
The issue was reproducible with:
```python
from contextvars import copy_context
import asyncio
from langgraph.graph import StateGraph
# Sync case: context remains consistent
print("SYNC")
print(copy_context()) # Same object
graph.invoke({"result": "init"})
print(copy_context()) # Same object
# Async case: context was inconsistent (before fix)
print("ASYNC")
asyncio.run(graph.ainvoke({"result": "init"}))
print(copy_context()) # Different object than expected
```
## Root Cause
The original `shielded` decorator implementation:
```python
async def wrapped(*args: Any, **kwargs: Any) -> Any:
return await asyncio.shield(func(*args, **kwargs))
```
Used `asyncio.shield()` directly without preserving the current
execution context, causing context variables to be lost.
## Solution
Modified the `shielded` decorator to:
1. Capture the current context using `copy_context()`
2. Create a task with explicit context using `asyncio.create_task(coro,
context=ctx)` for Python 3.11+
3. Shield the context-aware task
4. Fallback to regular task creation for Python < 3.11
```python
async def wrapped(*args: Any, **kwargs: Any) -> Any:
# Capture the current context to preserve context variables
ctx = copy_context()
coro = func(*args, **kwargs)
try:
# Create a task with the captured context to preserve context variables
task = asyncio.create_task(coro, context=ctx)
return await asyncio.shield(task)
except TypeError:
# Python < 3.11 fallback
task = asyncio.create_task(coro)
return await asyncio.shield(task)
```
## Testing
- Added comprehensive test
`test_shielded_callback_context_preservation()` that validates context
variables are preserved across shielded callback boundaries
- Verified the fix resolves the original LangGraph context consistency
issue
- Confirmed all existing callback manager tests still pass
- Validated OpenTelemetry-like instrumentation scenarios work correctly
The fix is minimal, maintains backward compatibility, and ensures proper
context preservation for both modern Python versions and older ones.
Fixes#31398.
<!-- START COPILOT CODING AGENT TIPS -->
---
💬 Share your feedback on Copilot coding agent for the chance to win a
$200 gift card! Click
[here](https://survey.alchemer.com/s3/8343779/Copilot-Coding-agent) to
start the survey.
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
# Description
This submission is a part of a school project from our team of 4
@EminGul @williamzhu54 @annay54 @donttouch22.
Our pull request fixes the issue with RunnableParallel scheme being
empty by returning the correct schema output when children runnable
input schemas use TypedDicts.
# Issue
Fixes#24326
# Dependencies
No extra dependencies required for this fix.
# Feedback
Any feedback and advice is gladly welcomed. Please feel free to let us
know what we can change or improve upon regarding this issue.
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
* for run count + thread count overflow we should warn model not to call
again
* don't tally mocked tool calls in thread limit -- consider the
following
* run limit is 1
* thread limit is 3
* first run calls the tool 2 times, 1 executes, 1 is blocked
* we should only count the successful execution above towards the total
thread count
* raise more helpful warnings on invalid config
* improving typing (covariance)
* adding in support for continuing w/ tool calls not yet at threshold,
switching default to continue
* moving all logic into after model
```py
ExitBehavior = Literal["continue", "error", "end"]
"""How to handle execution when tool call limits are exceeded.
- `"continue"`: Block exceeded tools with error messages, let other tools continue (default)
- `"error"`: Raise a `ToolCallLimitExceededError` exception
- `"end"`: Stop execution immediately, injecting a ToolMessage and an AI message
for the single tool call that exceeded the limit. Raises `NotImplementedError`
if there are multiple tool calls
"""
```
To fix nondeterministic results causing integration testing to sometimes
fail
Also speeds up from 10s to 0.5
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
**Description:** Add link to Code of Conduct in the Additional resources
section to make community guidelines more accessible for all
contributors.
**Rationale:**
- **Community Health:** Making the Code of Conduct easily discoverable
helps set clear expectations for community behavior and fosters a more
inclusive, respectful environment
- **New Contributor Experience:** Many new contributors look to the
README as the primary source of project information. Having the Code of
Conduct readily available helps onboard them properly
- **Best Practices:** Prominent Code of Conduct links are considered a
best practice in open source projects and improve project accessibility
- **Low Impact:** This is a simple, non-breaking change that
significantly improves documentation completeness
**Issue:** N/A
**Dependencies:** None
- standardize on using model IDs, no more aliases - makes future
maintenance easier
- use latest models in docstrings to highlight support
- remove remaining sonnet 3-7 usage due to deprecation
Depends on #33751
- use latest models in examples to highlight support
- standardize on using IDs in examples - no more aliases to improve
determinism in future tests
- bump lock
- in integration tests, fix stale casettes and use `MODEL_NAME`
uniformly where possible
- add case for default max tokens for sonnet-4-5 (was missing)
While working on ToolRuntime in TS I discovered that Python still uses
`thread_model_call_count` and `run_model_call_count` in ToolNode tests
which afaik we removed.
Moving all `ToolNode` related improvements back to LangGraph and
importing them in LC!
pairing w/ https://github.com/langchain-ai/langgraph/pull/6321
this fixes a couple of things:
1. `InjectedState`, store etc will continue to work as expected no
matter where the import is from
2. `ToolRuntime` is now usable w/in langgraph, woohoo!
* attach the latest `AIMessage` to all `StructuredOutputError`s so that
relevant middleware can use as desired
* raise `StructuredOutputError` from `ProviderStrategy` logic in case of
failed parsing (so that we can retry from middleware)
* added a test suite w/ example custom middleware that retries for tool
+ provider strategy
Long term, we could add our own opinionated structured output retry
middleware, but this at least unblocks folks who want to use custom
retry logic in the short term :)
```py
class StructuredOutputRetryMiddleware(AgentMiddleware):
"""Retries model calls when structured output parsing fails."""
def __init__(self, max_retries: int) -> None:
self.max_retries = max_retries
def wrap_model_call(
self, request: ModelRequest, handler: Callable[[ModelRequest], ModelResponse]
) -> ModelResponse:
for attempt in range(self.max_retries + 1):
try:
return handler(request)
except StructuredOutputError as exc:
if attempt == self.max_retries:
raise
ai_content = exc.ai_message.content
error_message = (
f"Your previous response was:\n{ai_content}\n\n"
f"Error: {exc}. Please try again with a valid response."
)
request.messages.append(HumanMessage(content=error_message))
```
Updated the README to clarify LangChain's focus on building agents and
LLM-powered applications. Added a section for community discussions and
refined the ecosystem description.
if "url" in annotation: in Line 15 , already ensures "url" is key in
annotation , so no need to check again to set "url" key in out object
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
The LLM shouldn't be seeing parameters it cannot control in the
ToolMessage error it gets when it invokes a tool with incorrect args.
This fixes the behavior within langchain to address immediate issue.
We may want to change the behavior in langchain_core as well to prevent
validation of injected arguments. But this would be done in a separate
change
added some noqas, this is a quick patch to support a bug uncovered in
the quickstart, will resolve fully depending on where we centralize
ToolNode stuff.
**Description:** Added a beginner-friendly tip to the README to help
first-time contributors find a starting point. This is a documentation
improvement aimed at lowering the barrier for newcomers to participate
in open source.
**Issue:** No related issue
**Dependencies:** None
---
## Note to maintainers
I'm new to open source and this is my first PR! If there's anything that
needs improvement, please guide me and I'll be happy to learn and make
changes. Thank you for your patience! 😊
## What does this PR do?
- Added a noticeable beginner tip box after the badges section in README
- Provided specific guidance (Good First Issues link)
- Encourages newcomers to start with documentation fixes
## Why is this change needed?
- Makes it easier for new contributors to get started
- Provides clear direction and reduces confusion
- Creates a more welcoming open source community environment
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
* The dependency is not used.
* It takes a long time to build in Python 3.14 as there are no prebuilt
binaries yet. This slows down CI a lot.
Co-authored-by: Mason Daugherty <mason@langchain.dev>
the fact that this was broken showcases that we need significantly
better test coverage, this is literally the most minimalistic usage of
this middleware there could be 😿
will document these two gotchas better for custom middleware
```py
from langchain.agents.middleware.shell_tool import ShellToolMiddleware
from langchain.agents import create_agent
agent = create_agent(model="openai:gpt-4",middleware = [ShellToolMiddleware()])
agent.invoke({"messages":[{"role": "user", "content": "hi"}]})
```
* Fix detection of support of context in `asyncio.create_task`
* Fix: in Python 3.14 `asyncio.get_event_loop()` raises an exception if
there's no running loop
* Bump pydantic to version 2.12
* Skips tests with pydantic v1 models as they are not supported with
Python 3.14
* Run core tests with Python 3.14 in CI.
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>
mostly #33520
also tacking on change to make sure we're only looking at client side
calls for the jump to end
---------
Co-authored-by: Nuno Campos <nuno@boringbits.io>
- Both middleware share the same implementation, the only difference is
one uses Claude's server-side tool definition, whereas the other one
uses a generic tool definition compatible with all models
- Implemented 3 execution policies (responsible for actually running the
shell process)
- HostExecutionPolicy runs the shell as subprocess, appropriate for
already sandboxed environments, eg when run inside a dedicated docker
container
- CodexSandboxExecutionPolicy runs the shell using the sandbox command
from the Codex CLI which implements sandboxing techniques for Linux and
Mac OS.
- DockerExecutionPolicy runs the shell inside a dedicated Docker
container for isolation.
- Implements all behaviours described in
https://docs.claude.com/en/docs/agents-and-tools/tool-use/bash-tool#handle-large-outputs
including timeouts, truncation, output redaction, etc
---------
Co-authored-by: Sydney Runkle <54324534+sydney-runkle@users.noreply.github.com>
Co-authored-by: Sydney Runkle <sydneymarierunkle@gmail.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Middleware Classes
Text Editor Tools
- StateClaudeTextEditorToolMiddleware: In-memory text editor using agent
state
- FilesystemClaudeTextEditorToolMiddleware: Text editor operating on
real filesystem
Implementing Claude's text editor tools
https://docs.claude.com/en/docs/agents-and-tools/tool-use/text-editor-tool
Operations: view, create, str_replace, insert
Memory Tools
- StateClaudeMemoryToolMiddleware: Memory persistence in agent state
- FilesystemClaudeMemoryToolMiddleware: Memory persistence on filesystem
Implementing Claude's memory tools
https://docs.claude.com/en/docs/agents-and-tools/tool-use/memory-tool
Operations: Same as text editor plus delete and rename
File Search Tools
- StateFileSearchMiddleware: Search state-based files
Provides Glob and Grep tools with same schema as used by Claude Code
(but compatible with any model)
- Glob: Pattern matching (e.g., **/*.py, src/**/*.ts), sorted by
modification time
- Grep: Regex content search with output modes (files_with_matches,
content, count)
Usage
``` from langchain.agents import create_agent from langchain.agents.middleware import (
StateTextEditorToolMiddleware, StateFileSearchMiddleware, )
agent = create_agent( model=model, tools=[], middleware=[
StateTextEditorToolMiddleware(), StateFileSearchMiddleware(), ], ) ```
---------
Co-authored-by: Nuno Campos <nuno@boringbits.io>
Adds special private helper to allow direct injection of `ToolRuntime`
in tools, plus adding guards for generic annotations w/ `get_origin`.
Went w/ the private helper so that we didn't change behavior for other
injected types.
To make migration easier, things are more backwards compat
Very minimal footprint here
Will need to upgrade migration guide and other docs w/ this change
Adds `ToolRetryMiddleware` to automatically retry failed tool calls with
configurable exponential backoff, exception filtering, and error
handling.
## Example
```python
from langchain.agents import create_agent
from langchain.agents.middleware import ToolRetryMiddleware
from langchain_openai import ChatOpenAI
# Retry up to 3 times with exponential backoff
retry = ToolRetryMiddleware(
max_retries=3,
initial_delay=1.0,
backoff_factor=2.0,
)
agent = create_agent(
model=ChatOpenAI(model="gpt-4"),
tools=[search_tool, database_tool],
middleware=[retry],
)
# Tool failures are automatically retried
result = agent.invoke({"messages": [{"role": "user", "content": "Search for AI news"}]})
```
For advanced usage with specific exception handling:
```python
from requests.exceptions import Timeout, HTTPError
def should_retry(exc: Exception) -> bool:
# Only retry on 5xx errors or timeouts
if isinstance(exc, HTTPError):
return 500 <= exc.response.status_code < 600
return isinstance(exc, Timeout)
retry = ToolRetryMiddleware(
max_retries=4,
retry_on=should_retry,
tools=["search_database"], # Only apply to specific tools
)
```
Largely:
- Remove explicit `"Default is x"` since new refs show default inferred
from sig
- Inline code (useful for eventual parsing)
- Fix code block rendering (indentations)
The one risk point that I can see here is that model + tool call
counting now occurs in the `after_model` hook which introduces order
dependency (what if you have HITL execute before this hook and we jump
early to `model`, for example).
This is something users can work around at the moment and we can
document. We could also introduce a priority concept to middleware.
## Description
Fixes#33453
`ModelResponse` was defined in `types.py` and included in its `__all__`
list, but was not exported from the middleware package's `__init__.py`.
This caused `ImportError` when attempting to import it directly
from `langchain.agents.middleware`, despite being documented as a public
export.
## Changes
- Added `ModelResponse` to the import statement in
`langchain/agents/middleware/__init__.py`
- Added `ModelResponse` to the `__all__` list in
`langchain/agents/middleware/__init__.py`
- Added comprehensive unit tests in `test_imports.py` to verify the
import works correctly
## Issue
The original issue reported that the following import failed:
```python
from langchain.agents.middleware import ModelResponse
# ImportError: cannot import name 'ModelResponse' from
'langchain.agents.middleware'
The workaround was to import from the submodule:
from langchain.agents.middleware.types import ModelResponse # Workaround
Solution
After this fix, ModelResponse can be imported directly as documented:
from langchain.agents.middleware import ModelResponse # Now works!
Testing
- ✅ Added 3 unit tests in
tests/unit_tests/agents/middleware/test_imports.py
- ✅ All tests pass locally: make format, make lint, make test
- ✅ Verified ModelResponse is properly exported and importable
- ✅ Verified ModelResponse appears in __all__ list
Dependencies
None. This is a simple export fix with no new dependencies.
---------
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Bumps [astral-sh/setup-uv](https://github.com/astral-sh/setup-uv) from 6
to 7.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/astral-sh/setup-uv/releases">astral-sh/setup-uv's
releases</a>.</em></p>
<blockquote>
<h2>v7.0.0 🌈 node24 and a lot of bugfixes</h2>
<h2>Changes</h2>
<p>This release comes with a load of bug fixes and a speed up. Because
of switching from node20 to node24 it is also a breaking change. If you
are running on GitHub hosted runners this will just work, if you are
using self-hosted runners make sure, that your runners are up to date.
If you followed the normal installation instructions your self-hosted
runner will keep itself updated.</p>
<p>This release also removes the deprecated input
<code>server-url</code> which was used to download uv releases from a
different server.
The <a
href="https://github.com/astral-sh/setup-uv?tab=readme-ov-file#manifest-file">manifest-file</a>
input supersedes that functionality by adding a flexible way to define
available versions and where they should be downloaded from.</p>
<h3>Fixes</h3>
<ul>
<li>The action now respects when the environment variable
<code>UV_CACHE_DIR</code> is already set and does not overwrite it. It
now also finds <a
href="https://docs.astral.sh/uv/reference/settings/#cache-dir">cache-dir</a>
settings in config files if you set them.</li>
<li>Some users encountered problems that <a
href="https://github.com/astral-sh/setup-uv?tab=readme-ov-file#disable-cache-pruning">cache
pruning</a> took forever because they had some <code>uv</code> processes
running in the background. Starting with uv version <code>0.8.24</code>
this action uses <code>uv cache prune --ci --force</code> to ignore the
running processes</li>
<li>If you just want to install uv but not have it available in path,
this action now respects <code>UV_NO_MODIFY_PATH</code></li>
<li>Some other actions also set the env var <code>UV_CACHE_DIR</code>.
This action can now deal with that but as this could lead to unwanted
behavior in some edgecases a warning is now displayed.</li>
</ul>
<h3>Improvements</h3>
<p>If you are using minimum version specifiers for the version of uv to
install for example</p>
<pre lang="toml"><code>[tool.uv]
required-version = ">=0.8.17"
</code></pre>
<p>This action now detects that and directly uses the latest version.
Previously it would download all available releases from the uv repo
to determine the highest matching candidate for the version specifier,
which took much more time.</p>
<p>If you are using other specifiers like <code>0.8.x</code> this action
still needs to download all available releases because the specifier
defines an upper bound (not 0.9.0 or later) and "latest" would
possibly not satisfy that.</p>
<h2>🚨 Breaking changes</h2>
<ul>
<li>Use node24 instead of node20 <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/608">#608</a>)</li>
<li>Remove deprecated input server-url <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/607">#607</a>)</li>
</ul>
<h2>🐛 Bug fixes</h2>
<ul>
<li>Respect UV_CACHE_DIR and cache-dir <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/612">#612</a>)</li>
<li>Use --force when pruning cache <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/611">#611</a>)</li>
<li>Respect UV_NO_MODIFY_PATH <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/603">#603</a>)</li>
<li>Warn when <code>UV_CACHE_DIR</code> has changed <a
href="https://github.com/jamesbraza"><code>@jamesbraza</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/601">#601</a>)</li>
</ul>
<h2>🚀 Enhancements</h2>
<ul>
<li>Shortcut to latest version for minimum version specifier <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/598">#598</a>)</li>
</ul>
<h2>🧰 Maintenance</h2>
<ul>
<li>Bump dependencies <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/613">#613</a>)</li>
<li>Fix test-uv-no-modify-path <a
href="https://github.com/eifinger"><code>@eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/604">#604</a>)</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="3259c6206f"><code>3259c62</code></a>
Bump deps (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/633">#633</a>)</li>
<li><a
href="bf8e8ed895"><code>bf8e8ed</code></a>
Split up documentation (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/632">#632</a>)</li>
<li><a
href="9c6b5e9fb5"><code>9c6b5e9</code></a>
Add resolution-strategy input to support oldest compatible version
selection ...</li>
<li><a
href="a5129e99f4"><code>a5129e9</code></a>
Add copilot-instructions.md (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/630">#630</a>)</li>
<li><a
href="d18bcc753a"><code>d18bcc7</code></a>
Add value of UV_PYTHON_INSTALL_DIR to path (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/628">#628</a>)</li>
<li><a
href="bd1f875aba"><code>bd1f875</code></a>
Set output venv when activate-environment is used (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/627">#627</a>)</li>
<li><a
href="1a91c3851d"><code>1a91c38</code></a>
chore: update known checksums for 0.9.2 (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/626">#626</a>)</li>
<li><a
href="c79f606987"><code>c79f606</code></a>
chore: update known checksums for 0.9.1 (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/625">#625</a>)</li>
<li><a
href="e0249f1599"><code>e0249f1</code></a>
Fall back to PR for updating known versions (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/623">#623</a>)</li>
<li><a
href="6d2eb15b49"><code>6d2eb15</code></a>
Cache python installs (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/621">#621</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/astral-sh/setup-uv/compare/v6...v7">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
This is tool emulation middleware. The idea is to help test out an agent
that may have some tools that either take a long time to run or are
expensive to set up. This could allow simulating the behavior a bit.
**Description:**
currently `mustache_schema("{{x.y}} {{x}}")` will error. pr fixes
**Issue:** na
**Dependencies:**na
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Easiest to review side by side (not inline)
* Adding `dict` type requests + responses so that we can ship config w/
interrupts. Also more extensible.
* Keeping things generic in terms of `interrupt_on` rather than
`tool_config`
* Renaming allowed decisions -- approve, edit, reject
* Draws differentiation between actions (requested + performed by the
agent), in this case tool calls, though we generalize beyond that and
decisions - human feedback for said actions
New request structure
```py
class Action(TypedDict):
"""Represents an action with a name and arguments."""
name: str
"""The type or name of action being requested (e.g., "add_numbers")."""
arguments: dict[str, Any]
"""Key-value pairs of arguments needed for the action (e.g., {"a": 1, "b": 2})."""
DecisionType = Literal["approve", "edit", "reject"]
class ReviewConfig(TypedDict):
"""Policy for reviewing a HITL request."""
action_name: str
"""Name of the action associated with this review configuration."""
allowed_decisions: list[DecisionType]
"""The decisions that are allowed for this request."""
description: NotRequired[str]
"""The description of the action to be reviewed."""
arguments_schema: NotRequired[dict[str, Any]]
"""JSON schema for the arguments associated with the action, if edits are allowed."""
class HITLRequest(TypedDict):
"""Request for human feedback on a sequence of actions requested by a model."""
action_requests: list[Action]
"""A list of agent actions for human review."""
review_configs: list[ReviewConfig]
"""Review configuration for all possible actions."""
```
New response structure
```py
class ApproveDecision(TypedDict):
"""Response when a human approves the action."""
type: Literal["approve"]
"""The type of response when a human approves the action."""
class EditDecision(TypedDict):
"""Response when a human edits the action."""
type: Literal["edit"]
"""The type of response when a human edits the action."""
edited_action: Action
"""Edited action for the agent to perform.
Ex: for a tool call, a human reviewer can edit the tool name and args.
"""
class RejectDecision(TypedDict):
"""Response when a human rejects the action."""
type: Literal["reject"]
"""The type of response when a human rejects the action."""
message: NotRequired[str]
"""The message sent to the model explaining why the action was rejected."""
Decision = ApproveDecision | EditDecision | RejectDecision
class HITLResponse(TypedDict):
"""Response payload for a HITLRequest."""
decisions: list[Decision]
"""The decisions made by the human."""
```
User facing API:
NEW
```py
HumanInTheLoopMiddleware(interrupt_on={
'send_email': True,
# can also use a callable for description that takes tool call, state, and runtime
'execute_sql': {
'allowed_decisions': ['approve', 'edit', 'reject'],
'description': 'please review sensitive tool execution'},
}
})
Command(resume={"decisions": [{"type": "approve"}, {"type": "reject": "message": "db down"}]})
```
OLD
```py
HumanInTheLoopMiddleware(interrupt_on={
'send_email': True,
'execute_sql': {
'allow_accept': True,
'allow_edit': True,
'allow_respond': True,
description='please review sensitive tool execution'
},
})
Command(resume=[{"type": "approve"}, {"type": "reject": "message": "db down"}])
```
Hi there! Thank you for even being interested in contributing to LangChain.
As an open-source project in a rapidly developing field, we are extremely open to contributions, whether they involve new features, improved infrastructure, better documentation, or bug fixes.
To learn how to contribute to LangChain, please follow the [contribution guide here](https://docs.langchain.com/oss/python/contributing).
description:Report a bug in LangChain. To report a security issue, please instead use the security option below. For questions, please use the LangChain forum.
description:Report a bug in LangChain. To report a security issue, please instead use the security option (below). For questions, please use the LangChain forum (below).
labels:["bug"]
type:bug
body:
@@ -8,16 +8,15 @@ body:
value:|
Thank you for taking the time to file a bug report.
Use this to report BUGS in LangChain. For usage questions, feature requests and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
For usage questions, feature requests and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
Relevant links to check before filing a bug report to see if your issue has already been reported, fixed or
if there's another way to solve your problem:
Check these before submitting to see if your issue has already been reported, fixed or if there's another way to solve your problem:
- label:This is not related to the langchain-community package.
required:true
- label:I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
required:true
- label:I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
required:true
- type:checkboxes
id:package
attributes:
label:Package (Required)
description:|
Which `langchain` package(s) is this bug related to? Select at least one.
Note that if the package you are reporting for is not listed here, it is not in this repository (e.g. `langchain-google-genai` is in [`langchain-ai/langchain-google`](https://github.com/langchain-ai/langchain-google/)).
Please report issues for other packages to their respective repositories.
options:
- label:langchain
- label:langchain-openai
- label:langchain-anthropic
- label:langchain-classic
- label:langchain-core
- label:langchain-model-profiles
- label:langchain-tests
- label:langchain-text-splitters
- label:langchain-chroma
- label:langchain-deepseek
- label:langchain-exa
- label:langchain-fireworks
- label:langchain-groq
- label:langchain-huggingface
- label:langchain-mistralai
- label:langchain-nomic
- label:langchain-ollama
- label:langchain-perplexity
- label:langchain-prompty
- label:langchain-qdrant
- label:langchain-xai
- label:Other / not sure / general
- type:textarea
id:related
validations:
required:false
attributes:
label:Related Issues / PRs
description:|
If this bug is related to any existing issues or pull requests, please link them here.
placeholder:|
* e.g. #123, #456
- type:textarea
id:reproduction
validations:
required:true
attributes:
label:Example Code
label:Reproduction Steps / Example Code (Python)
description:|
Please add a self-contained, [minimal, reproducible, example](https://stackoverflow.com/help/minimal-reproducible-example) with your use case.
@@ -53,15 +93,12 @@ body:
**Important!**
* Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
* Reduce your code to the minimum required to reproduce the issue if possible. This makes it much easier for others to help you.
* Use code tags (e.g., ```python ... ```) to correctly [format your code](https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting).
* INCLUDE the language label (e.g. `python`) after the first three backticks to enable syntax highlighting. (e.g., ```python rather than ```).
* Avoid screenshots, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
* Reduce your code to the minimum required to reproduce the issue if possible.
(This will be automatically formatted into code, so no need for backticks.)
render:python
placeholder:|
The following code:
```python
from langchain_core.runnables import RunnableLambda
def bad_code(inputs) -> int:
@@ -69,17 +106,14 @@ body:
chain = RunnableLambda(bad_code)
chain.invoke('Hello!')
```
- type:textarea
id:error
validations:
required:false
attributes:
label:Error Message and Stack Trace (if applicable)
description:|
If you are reporting an error, please include the full error message and stack trace.
placeholder:|
Exception + full stack trace
If you are reporting an error, please copy and paste the full error message and
stack trace.
(This will be automatically formatted into code, so no need for backticks.)
render:shell
- type:textarea
id:description
attributes:
@@ -99,9 +133,7 @@ body:
attributes:
label:System Info
description:|
Please share your system info with us. Do NOT skip this step and please don't trim
the output. Most users don't include enough information here and it makes it harder
for us to help you.
Please share your system info with us.
Run the following command in your terminal and paste the output here:
@@ -113,8 +145,6 @@ body:
from langchain_core import sys_info
sys_info.print_sys_info()
```
alternatively, put the entire output of `pip freeze` here.
- label:This is not related to the langchain-community package.
required:true
- type:checkboxes
id:package
attributes:
label:Package (Required)
description:|
Which `langchain` package(s) is this request related to? Select at least one.
Note that if the package you are requesting for is not listed here, it is not in this repository (e.g. `langchain-google-genai` is in `langchain-ai/langchain`).
Please submit feature requests for other packages to their respective repositories.
Thank you for contributing to LangChain! Follow these steps to mark your pull request as ready for review. **If any of these steps are not completed, your PR will not be considered for review.**
Read the full contributing guidelines: https://docs.langchain.com/oss/python/contributing/overview
If you paste a large clearly AI generated description here your PR may be IGNORED or CLOSED!
Thank you for contributing to LangChain! Follow these steps to have your pull request considered as ready for review.
1. PR title: Should follow the format: TYPE(SCOPE): DESCRIPTION
- [ ]**PR title**: Follows the format: {TYPE}({SCOPE}): {DESCRIPTION}
- Once you've written the title, please delete this checklist item; do not include it in the PR.
-test(openai): update API usage tests
-Allowed TYPE and SCOPE values: https://github.com/langchain-ai/langchain/blob/master/.github/workflows/pr_lint.yml#L15-L33
- [ ]**PR message**: ***Delete this entire checklist*** and replace with
- **Description:** a description of the change. Include a [closing keyword](https://docs.github.com/en/issues/tracking-your-work-with-issues/using-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword) if applicable to a relevant issue.
- **Issue:** the issue # it fixes, if applicable (e.g. Fixes #123)
- **Dependencies:** any dependencies required for this change
2.PR description:
- [ ]**Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. **We will not consider a PR unless these three are passing in CI.** See [contribution guidelines](https://docs.langchain.com/oss/python/contributing) for more.
- Write 1-2 sentences summarizing the change.
- If this PR addresses a specific issue, please include "Fixes #ISSUE_NUMBER" in the description to automatically close the issue when the PR is merged.
- If there are any breaking changes, please clearly describe them.
- If this PR depends on another PR being merged first, please include "Depends on #PR_NUMBER" in the description.
3. Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified.
- We will not consider a PR unless these three are passing in CI.
4. How did you verify your code works?
Additional guidelines:
-Most PRs should not touch more than one package.
- Please do not add dependencies to `pyproject.toml` files (even optional ones) unless they are **required** for unit tests. Likewise, please do not update the `uv.lock` files unless you are adding a required dependency.
-Changes should be backwards compatible.
- Make sure optional dependencies are imported within a function.
-We ask that if you use generative AI for your contribution, you include a disclaimer.
- PRs should not touch more than one package unless absolutely necessary.
-Do not update the `uv.lock` files or add dependencies to `pyproject.toml` files (even optional ones) unless you have explicit permission to do so by a maintainer.
## Social handles (optional)
<!-- If you'd like a shoutout on release, add your socials below -->
│ ├── standard-tests/ # Shared test suite for integrations
│ ├── model-profiles/ # Model configuration profiles
├── .github/ # CI/CD workflows and templates
├── .vscode/ # VSCode IDE standard settings and recommended extensions
└── README.md # Information about LangChain
```
✅ **Good - Stable Interface:**
- **Core layer** (`langchain-core`): Base abstractions, interfaces, and protocols. Users should not need to know about this layer directly.
- **Implementation layer** (`langchain`): Concrete implementations and high-level public utilities
- **Integration layer** (`partners/`): Third-party service integrations. Note that this monorepo is not exhaustive of all LangChain integrations; some are maintained in separate repos, such as `langchain-ai/langchain-google` and `langchain-ai/langchain-aws`. Usually these repos are cloned at the same level as this monorepo, so if needed, you can refer to their code directly by navigating to `../langchain-google/` from this monorepo.
- **Testing layer** (`standard-tests/`): Standardized integration tests for partner integrations
Suggest PR titles that follow Conventional Commits format. Refer to .github/workflows/pr_lint for allowed types and scopes. Note that all commit/PR titles should be in lowercase with the exception of proper nouns/named entities. All PR titles should include a scope with no exceptions. For example:
```txt
feat(langchain): add new chat completion feature
fix(core): resolve type hinting issue in vector store
"""Send an email to a recipient with specified priority.
Any additional context about the function can go here.
Args:
to: The email address of the recipient.
msg: The message body to send.
priority: Email priority level.
Returns:
`True` if email was sent successfully, `False` otherwise.
Raises:
InvalidEmailError: If the email address format is invalid.
SMTPConnectionError: If unable to connect to email server.
"""
```
- Types go in function signatures, NOT in docstrings
- If a default is present, DO NOT repeat it in the docstring unless there is post-processing or it is set conditionally.
- Focus on "why" rather than "what" in descriptions
- Document all parameters, return values, and exceptions
- Keep descriptions concise but clear
- Ensure American English spelling (e.g., "behavior", not "behaviour")
## Additional resources
- **Documentation:** https://docs.langchain.com/oss/python/langchain/overview and source at https://github.com/langchain-ai/docs or `../docs/`. Prefer the local install and use file search tools for best results. If needed, use the docs MCP server as defined in `.mcp.json` for programmatic access.
│ ├── standard-tests/ # Shared test suite for integrations
│ ├── model-profiles/ # Model configuration profiles
├── .github/ # CI/CD workflows and templates
├── .vscode/ # VSCode IDE standard settings and recommended extensions
└── README.md # Information about LangChain
```
✅ **Good - Stable Interface:**
- **Core layer** (`langchain-core`): Base abstractions, interfaces, and protocols. Users should not need to know about this layer directly.
- **Implementation layer** (`langchain`): Concrete implementations and high-level public utilities
- **Integration layer** (`partners/`): Third-party service integrations. Note that this monorepo is not exhaustive of all LangChain integrations; some are maintained in separate repos, such as `langchain-ai/langchain-google` and `langchain-ai/langchain-aws`. Usually these repos are cloned at the same level as this monorepo, so if needed, you can refer to their code directly by navigating to `../langchain-google/` from this monorepo.
- **Testing layer** (`standard-tests/`): Standardized integration tests for partner integrations
Suggest PR titles that follow Conventional Commits format. Refer to .github/workflows/pr_lint for allowed types and scopes. Note that all commit/PR titles should be in lowercase with the exception of proper nouns/named entities. All PR titles should include a scope with no exceptions. For example:
```txt
feat(langchain): add new chat completion feature
fix(core): resolve type hinting issue in vector store
"""Send an email to a recipient with specified priority.
Any additional context about the function can go here.
Args:
to: The email address of the recipient.
msg: The message body to send.
priority: Email priority level.
Returns:
`True` if email was sent successfully, `False` otherwise.
Raises:
InvalidEmailError: If the email address format is invalid.
SMTPConnectionError: If unable to connect to email server.
"""
```
- Types go in function signatures, NOT in docstrings
- If a default is present, DO NOT repeat it in the docstring unless there is post-processing or it is set conditionally.
- Focus on "why" rather than "what" in descriptions
- Document all parameters, return values, and exceptions
- Keep descriptions concise but clear
- Ensure American English spelling (e.g., "behavior", not "behaviour")
## Additional resources
- **Documentation:** https://docs.langchain.com/oss/python/langchain/overview and source at https://github.com/langchain-ai/docs or `../docs/`. Prefer the local install and use file search tools for best results. If needed, use the docs MCP server as defined in `.mcp.json` for programmatic access.
<img src="https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square" alt="Open in Dev Containers">
<a href="https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain" target="_blank"><img src="https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode" alt="Open in Dev Containers"></a>
<a href="https://codespaces.new/langchain-ai/langchain" target="_blank"><img src="https://github.com/codespaces/badge.svg" alt="Open in Github Codespace" title="Open in Github Codespace" width="150" height="20"></a>
LangChain is a framework for building LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development — all while future-proofing decisions as the underlying technology evolves.
LangChain is a framework for building agents and LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development – all while future-proofing decisions as the underlying technology evolves.
```bash
pip install -U langchain
pip install langchain
```
If you're looking for more advanced customization or agent orchestration, check out [LangGraph](https://docs.langchain.com/oss/python/langgraph/overview), our framework for building controllable agent workflows.
---
**Documentation**: To learn more about LangChain, check out [the docs](https://docs.langchain.com/).
**Documentation**:
If you're looking for more advanced customization or agent orchestration, check out [LangGraph](https://langchain-ai.github.io/langgraph/), our framework for building controllable agent workflows.
- [docs.langchain.com](https://docs.langchain.com/oss/python/langchain/overview) – Comprehensive documentation, including conceptual overviews and guides
- [reference.langchain.com/python](https://reference.langchain.com/python) – API reference docs for LangChain packages
- [Chat LangChain](https://chat.langchain.com/) – Chat with the LangChain documentation and get answers to your questions
**Discussions**: Visit the [LangChain Forum](https://forum.langchain.com) to connect with the community and share all of your technical questions, ideas, and feedback.
> [!NOTE]
> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
@@ -52,26 +49,28 @@ LangChain helps developers build applications powered by LLMs through a standard
Use LangChain for:
- **Real-time data augmentation**. Easily connect LLMs to diverse data sources and external/internal systems, drawing from LangChain’s vast library of integrations with model providers, tools, vector stores, retrievers, and more.
- **Model interoperability**. Swap models in and out as your engineering team experiments to find the best choice for your application’s needs. As the industry frontier evolves, adapt quickly — LangChain’s abstractions keep you moving without losing momentum.
- **Real-time data augmentation**. Easily connect LLMs to diverse data sources and external/internal systems, drawing from LangChain's vast library of integrations with model providers, tools, vector stores, retrievers, and more.
- **Model interoperability**. Swap models in and out as your engineering team experiments to find the best choice for your application's needs. As the industry frontier evolves, adapt quickly – LangChain's abstractions keep you moving without losing momentum.
- **Rapid prototyping**. Quickly build and iterate on LLM applications with LangChain's modular, component-based architecture. Test different approaches and workflows without rebuilding from scratch, accelerating your development cycle.
- **Production-ready features**. Deploy reliable applications with built-in support for monitoring, evaluation, and debugging through integrations like LangSmith. Scale with confidence using battle-tested patterns and best practices.
- **Vibrant community and ecosystem**. Leverage a rich ecosystem of integrations, templates, and community-contributed components. Benefit from continuous improvements and stay up-to-date with the latest AI developments through an active open-source community.
- **Flexible abstraction layers**. Work at the level of abstraction that suits your needs - from high-level chains for quick starts to low-level components for fine-grained control. LangChain grows with your application's complexity.
## LangChain’s ecosystem
## LangChain ecosystem
While the LangChain framework can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools when building LLM applications.
To improve your LLM application development, pair LangChain with:
- [LangSmith](https://www.langchain.com/langsmith) - Helpful for agent evals and observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain visibility in production, and improve performance over time.
- [LangGraph](https://langchain-ai.github.io/langgraph/) - Build agents that can reliably handle complex tasks with LangGraph, our low-level agent orchestration framework. LangGraph offers customizable architecture, long-term memory, and human-in-the-loop workflows — and is trusted in production by companies like LinkedIn, Uber, Klarna, and GitLab.
- [LangGraph Platform](https://docs.langchain.com/langgraph-platform) - Deploy and scale agents effortlessly with a purpose-built deployment platform for long-running, stateful workflows. Discover, reuse, configure, and share agents across teams — and iterate quickly with visual prototyping in [LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/).
- [Deep Agents](https://github.com/langchain-ai/deepagents) *(new!)*– Build agents that can plan, use subagents, and leverage file systems for complex tasks
- [LangGraph](https://docs.langchain.com/oss/python/langgraph/overview) – Build agents that can reliably handle complex tasks with LangGraph, our low-level agent orchestration framework. LangGraph offers customizable architecture, long-term memory, and human-in-the-loop workflows – and is trusted in production by companies like LinkedIn, Uber, Klarna, and GitLab.
- [Integrations](https://docs.langchain.com/oss/python/integrations/providers/overview) – List of LangChain integrations, includingchat & embedding models, tools & toolkits, and more
- [LangSmith](https://www.langchain.com/langsmith) – Helpful for agent evals and observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain visibility in production, and improve performance over time.
- [LangSmith Deployment](https://docs.langchain.com/langsmith/deployments) – Deploy and scale agents effortlessly with a purpose-built deployment platform for long-running, stateful workflows. Discover, reuse, configure, and share agents across teams – and iterate quickly with visual prototyping in [LangSmith Studio](https://docs.langchain.com/langsmith/studio).
## Additional resources
- [Conceptual Guides](https://docs.langchain.com/oss/python/langchain/overview): Explanations of key
concepts behind the LangChain framework.
- [Tutorials](https://docs.langchain.com/oss/python/learn): Simple walkthroughs with
guided examples on getting started with LangChain.
- [API Reference](https://reference.langchain.com/python/): Detailed reference on
navigating base packages and integrations for LangChain.
- [LangChain Forum](https://forum.langchain.com/): Connect with the community and share all of your technical questions, ideas, and feedback.
- [Chat LangChain](https://chat.langchain.com/): Ask questions & chat with our documentation.
- [API Reference](https://reference.langchain.com/python) – Detailed reference on navigating base packages and integrations for LangChain.
- [Contributing Guide](https://docs.langchain.com/oss/python/contributing/overview) – Learn how to contribute to LangChain projects and find good first issues.
- [Code of Conduct](https://github.com/langchain-ai/langchain/?tab=coc-ov-file) – Our community guidelines and standards for participation.
- [LangChain Academy](https://academy.langchain.com/) – Comprehensive, free courses on LangChain libraries and products, made by the LangChain team.
LangChain has a large ecosystem of integrations with various external resources like local and remote file systems, APIs and databases. These integrations allow developers to create versatile applications that combine the power of LLMs with the ability to access, interact with and manipulate external resources.
## Best practices
When building such applications, developers should remember to follow good security practices:
* [**Limit Permissions**](https://en.wikipedia.org/wiki/Principle_of_least_privilege): Scope permissions specifically to the application's need. Granting broad or excessive permissions can introduce significant security vulnerabilities. To avoid such vulnerabilities, consider using read-only credentials, disallowing access to sensitive resources, using sandboxing techniques (such as running inside a container), specifying proxy configurations to control external requests, etc., as appropriate for your application.
* **Anticipate Potential Misuse**: Just as humans can err, so can Large Language Models (LLMs). Always assume that any system access or credentials may be used in any way allowed by the permissions they are assigned. For example, if a pair of database credentials allows deleting data, it's safest to assume that any LLM able to use those credentials may in fact delete data.
* [**Defense in Depth**](https://en.wikipedia.org/wiki/Defense_in_depth_(computing)): No security technique is perfect. Fine-tuning and good chain design can reduce, but not eliminate, the odds that a Large Language Model (LLM) may make a mistake. It's best to combine multiple layered security approaches rather than relying on any single layer of defense to ensure security. For example: use both read-only permissions and sandboxing to ensure that LLMs are only able to access data that is explicitly meant for them to use.
Risks of not doing so include, but are not limited to:
* Data corruption or loss.
* Unauthorized access to confidential information.
* Compromised performance or availability of critical resources.
Example scenarios with mitigation strategies:
* A user may ask an agent with access to the file system to delete files that should not be deleted or read the content of files that contain sensitive information. To mitigate, limit the agent to only use a specific directory and only allow it to read or write files that are safe to read or write. Consider further sandboxing the agent by running it in a container.
* A user may ask an agent with write access to an external API to write malicious data to the API, or delete data from that API. To mitigate, give the agent read-only API keys, or limit it to only use endpoints that are already resistant to such misuse.
* A user may ask an agent with access to a database to drop a table or mutate the schema. To mitigate, scope the credentials to only the tables that the agent needs to access and consider issuing READ-ONLY credentials.
If you're building applications that access external resources like file systems, APIs or databases, consider speaking with your company's security team to determine how to best design and secure your applications.
## Reporting OSS Vulnerabilities
LangChain is partnered with [huntr by Protect AI](https://huntr.com/) to provide
a bounty program for our open source projects.
Please report security vulnerabilities associated with the LangChain
open source projects at [huntr](https://huntr.com/bounties/disclose/?target=https%3A%2F%2Fgithub.com%2Flangchain-ai%2Flangchain&validSearch=true).
Before reporting a vulnerability, please review:
1) In-Scope Targets and Out-of-Scope Targets below.
2) The [langchain-ai/langchain](https://docs.langchain.com/oss/python/contributing/code#repository-structure) monorepo structure.
3) The [Best Practices](#best-practices) above to understand what we consider to be a security vulnerability vs. developer responsibility.
### In-Scope Targets
The following packages and repositories are eligible for bug bounties:
* langchain-core
* langchain (see exceptions)
* langchain-community (see exceptions)
* langgraph
* langserve
### Out of Scope Targets
All out of scope targets defined by huntr as well as:
* **langchain-experimental**: This repository is for experimental code and is not
eligible for bug bounties (see [package warning](https://pypi.org/project/langchain-experimental/)), bug reports to it will be marked as interesting or waste of
time and published with no bounty attached.
***tools**: Tools in either langchain or langchain-community are not eligible for bug
bounties. This includes the following directories
* libs/langchain/langchain/tools
* libs/community/langchain_community/tools
* Please review the [Best Practices](#best-practices)
for more details, but generally tools interact with the real world. Developers are
expected to understand the security implications of their code and are responsible
for the security of their tools.
* Code documented with security notices. This will be decided on a case-by-case basis, but likely will not be eligible for a bounty as the code is already
documented with guidelines for developers that should be followed for making their
application secure.
* Any LangSmith related repositories or APIs (see [Reporting LangSmith Vulnerabilities](#reporting-langsmith-vulnerabilities)).
## Reporting LangSmith Vulnerabilities
Please report security vulnerabilities associated with LangSmith by email to `security@langchain.dev`.
"- TODO: Make sure API reference link is correct.\n",
"\n",
"This will help you get started with __ModuleName__ [chat models](/docs/concepts/chat_models). For detailed documentation of all Chat__ModuleName__ features and configurations head to the [API reference](https://python.langchain.com/api_reference/__package_name_short_snake__/chat_models/__module_name__.chat_models.Chat__ModuleName__.html).\n",
"\n",
"- TODO: Add any other relevant links, like information about models, prices, context windows, etc. See https://python.langchain.com/docs/integrations/chat/openai/ for an example.\n",
"\n",
"## Overview\n",
"### Integration details\n",
"\n",
"- TODO: Fill in table features.\n",
"- TODO: Remove JS support link if not relevant, otherwise ensure link is correct.\n",
"- TODO: Make sure API reference links are correct.\n",
"\n",
"| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/__package_name_short_snake__) | Package downloads | Package latest |\n",
"To access __ModuleName__ models you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package.\n",
"\n",
"### Credentials\n",
"\n",
"- TODO: Update with relevant info.\n",
"\n",
"Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
"metadata": {},
"outputs": [],
"source": [
"import getpass\n",
"import os\n",
"\n",
"if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
" \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
" ),\n",
" (\"human\", \"{input}\"),\n",
" ]\n",
")\n",
"\n",
"chain = prompt | llm\n",
"chain.invoke(\n",
" {\n",
" \"input_language\": \"English\",\n",
" \"output_language\": \"German\",\n",
" \"input\": \"I love programming.\",\n",
" }\n",
")"
]
},
{
"cell_type": "markdown",
"id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
"metadata": {},
"source": [
"## TODO: Any functionality specific to this model provider\n",
"\n",
"E.g. creating/using finetuned models via this provider. Delete if not relevant."
]
},
{
"cell_type": "markdown",
"id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all Chat__ModuleName__ features and configurations head to the [API reference](https://python.langchain.com/api_reference/__package_name_short_snake__/chat_models/__module_name__.chat_models.Chat__ModuleName__.html)"
"- TODO: Make sure API reference link is correct.\n",
"\n",
"This notebook provides a quick overview for getting started with __ModuleName__ [document loader](https://python.langchain.com/docs/concepts/document_loaders). For detailed documentation of all __ModuleName__Loader features and configurations head to the [API reference](https://python.langchain.com/v0.2/api_reference/community/document_loaders/langchain_community.document_loaders.__module_name___loader.__ModuleName__Loader.html).\n",
"\n",
"- TODO: Add any other relevant links, like information about underlying API, etc.\n",
"\n",
"## Overview\n",
"### Integration details\n",
"\n",
"- TODO: Fill in table features.\n",
"- TODO: Remove JS support link if not relevant, otherwise ensure link is correct.\n",
"- TODO: Make sure API reference links are correct.\n",
"\n",
"| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/document_loaders/web_loaders/__module_name___loader)|\n",
"To access __ModuleName__ document loader you'll need to install the `__package_name__` integration package, and create a **ModuleName** account and get an API key.\n",
"\n",
"### Credentials\n",
"\n",
"- TODO: Update with relevant info.\n",
"\n",
"Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
"- TODO: Run cells to show lazy loading capabilities. Delete if lazy loading is not implemented."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"page = []\n",
"for doc in loader.lazy_load():\n",
" page.append(doc)\n",
" if len(page) >= 10:\n",
" # do some paged operation, e.g.\n",
" # index.upsert(page)\n",
"\n",
" page = []"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## TODO: Any functionality specific to this document loader\n",
"\n",
"E.g. using specific configs for different loading behavior. Delete if not relevant."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all __ModuleName__Loader features and configurations head to the API reference: https://python.langchain.com/v0.2/api_reference/community/document_loaders/langchain_community.document_loaders.__module_name___loader.__ModuleName__Loader.html"
"- [ ] TODO: Make sure API reference link is correct\n",
"\n",
"This will help you get started with __ModuleName__ completion models (LLMs) using LangChain. For detailed documentation on `__ModuleName__LLM` features and configuration options, please refer to the [API reference](https://api.python.langchain.com/en/latest/llms/__module_name__.llms.__ModuleName__LLM.html).\n",
"\n",
"## Overview\n",
"### Integration details\n",
"\n",
"- TODO: Fill in table features.\n",
"- TODO: Remove JS support link if not relevant, otherwise ensure link is correct.\n",
"- TODO: Make sure API reference links are correct.\n",
"\n",
"| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/llms/__package_name_short_snake__) | Package downloads | Package latest |\n",
"To access __ModuleName__ models you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package.\n",
"\n",
"### Credentials\n",
"\n",
"- TODO: Update with relevant info.\n",
"\n",
"Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bc51e756",
"metadata": {},
"outputs": [],
"source": [
"import getpass\n",
"import os\n",
"\n",
"if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
"prompt = PromptTemplate(\"How to say {input} in {output_language}:\\n\")\n",
"\n",
"chain = prompt | llm\n",
"chain.invoke(\n",
" {\n",
" \"output_language\": \"German\",\n",
" \"input\": \"I love programming.\",\n",
" }\n",
")"
]
},
{
"cell_type": "markdown",
"id": "e99eef30",
"metadata": {},
"source": [
"## TODO: Any functionality specific to this model provider\n",
"\n",
"E.g. creating/using finetuned models via this provider. Delete if not relevant"
]
},
{
"cell_type": "markdown",
"id": "e9bdfcef",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `__ModuleName__LLM` features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/__module_name__.llms.__ModuleName__LLM.html"
"- TODO: Make sure API reference link is correct.\n",
"\n",
"This will help you get started with the __ModuleName__ [retriever](/docs/concepts/retrievers). For detailed documentation of all __ModuleName__Retriever features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/__module_name__.retrievers.__ModuleName__.__ModuleName__Retriever.html).\n",
"\n",
"### Integration details\n",
"\n",
"TODO: Select one of the tables below, as appropriate.\n",
"\n",
"1: Bring-your-own data (i.e., index and search a custom corpus of documents):\n",
"If you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
"metadata": {},
"outputs": [],
"source": [
"# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
"# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
]
},
{
"cell_type": "markdown",
"id": "0730d6a1-c893-4840-9817-5e5251676d5d",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"This retriever lives in the `__package_name__` package:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "652d6238-1f87-422a-b135-f5abbb8652fc",
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU __package_name__"
]
},
{
"cell_type": "markdown",
"id": "a38cde65-254d-4219-a441-068766c0d4b5",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"Now we can instantiate our retriever:\n",
"\n",
"- TODO: Update model instantiation with relevant params."
"## TODO: Any functionality or considerations specific to this retriever\n",
"\n",
"Fill in or delete if not relevant."
]
},
{
"cell_type": "markdown",
"id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all __ModuleName__Retriever features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/__module_name__.retrievers.__ModuleName__.__ModuleName__Retriever.html)."
"- TODO: Make sure API reference link is correct.\n",
"\n",
"This will help you get started with __ModuleName__ [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all __ModuleName__ByteStore features and configurations head to the [API reference](https://python.langchain.com/v0.2/api_reference/core/stores/langchain_core.stores.__module_name__ByteStore.html).\n",
"\n",
"- TODO: Add any other relevant links, like information about models, prices, context windows, etc. See https://python.langchain.com/docs/integrations/stores/in_memory/ for an example.\n",
"\n",
"## Overview\n",
"\n",
"- TODO: (Optional) A short introduction to the underlying technology/API.\n",
"\n",
"### Integration details\n",
"\n",
"- TODO: Fill in table features.\n",
"- TODO: Remove JS support link if not relevant, otherwise ensure link is correct.\n",
"- TODO: Make sure API reference links are correct.\n",
"\n",
"| Class | Package | Local | [JS support](https://js.langchain.com/docs/integrations/stores/_package_name_) | Package downloads | Package latest |\n",
"To create a __ModuleName__ byte store, you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package.\n",
"\n",
"### Credentials\n",
"\n",
"- TODO: Update with relevant info, or omit if the service does not require any credentials.\n",
"\n",
"Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import getpass\n",
"import os\n",
"\n",
"if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
"You can set data under keys like this using the `mset` method:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"kv_store.mset(\n",
" [\n",
" [\"key1\", b\"value1\"],\n",
" [\"key2\", b\"value2\"],\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"And you can delete data using the `mdelete` method:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"kv_store.mdelete(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## TODO: Any functionality specific to this key-value store provider\n",
"\n",
"E.g. extra initialization. Delete if not relevant."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all __ModuleName__ByteStore features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/stores/__module_name__.stores.__ModuleName__ByteStore.html"
"- [ ] TODO: Make sure API reference link is correct\n",
"\n",
"This will help you get started with __ModuleName__ embedding models using LangChain. For detailed documentation on `__ModuleName__Embeddings` features and configuration options, please refer to the [API reference](https://python.langchain.com/v0.2/api_reference/__package_name_short__/embeddings/__module_name__.embeddings__ModuleName__Embeddings.html).\n",
"To access __ModuleName__ embedding models you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package.\n",
"\n",
"### Credentials\n",
"\n",
"- TODO: Update with relevant info.\n",
"\n",
"Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "36521c2a",
"metadata": {},
"outputs": [],
"source": [
"import getpass\n",
"import os\n",
"\n",
"if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
"Embedding models are often used in retrieval-augmented generation (RAG) flows, both as part of indexing data as well as later retrieving it. For more detailed instructions, please see our [RAG tutorials](/docs/tutorials/).\n",
"\n",
"Below, see how to index and retrieve data using the `embeddings` object we initialized above. In this example, we will index and retrieve a sample document in the `InMemoryVectorStore`."
"retrieved_documents = retriever.invoke(\"What is LangChain?\")\n",
"\n",
"# show the retrieved document's content\n",
"retrieved_documents[0].page_content"
]
},
{
"cell_type": "markdown",
"id": "e02b9855",
"metadata": {},
"source": [
"## Direct Usage\n",
"\n",
"Under the hood, the vectorstore and retriever implementations are calling `embeddings.embed_documents(...)` and `embeddings.embed_query(...)` to create embeddings for the text(s) used in `from_texts` and retrieval `invoke` operations, respectively.\n",
"\n",
"You can directly call these methods to get embeddings for your own use cases.\n",
"\n",
"### Embed single texts\n",
"\n",
"You can embed single texts or documents with `embed_query`:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0d2befcd",
"metadata": {},
"outputs": [],
"source": [
"single_vector = embeddings.embed_query(text)\n",
"print(str(single_vector)[:100]) # Show the first 100 characters of the vector"
]
},
{
"cell_type": "markdown",
"id": "1b5a7d03",
"metadata": {},
"source": [
"### Embed multiple texts\n",
"\n",
"You can embed multiple texts with `embed_documents`:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2f4d6e97",
"metadata": {},
"outputs": [],
"source": [
"text2 = (\n",
" \"LangGraph is a library for building stateful, multi-actor applications with LLMs\"\n",
" print(str(vector)[:100]) # Show the first 100 characters of the vector"
]
},
{
"cell_type": "markdown",
"id": "98785c12",
"metadata": {},
"source": [
"## API Reference\n",
"\n",
"For detailed documentation on `__ModuleName__Embeddings` features and configuration options, please refer to the [API reference](https://api.python.langchain.com/en/latest/embeddings/__module_name__.embeddings.__ModuleName__Embeddings.html).\n"
"- TODO: Make sure API reference link is correct.\n",
"\n",
"This will help you get started with the __ModuleName__ [toolkit](/docs/concepts/tools/#toolkits). For detailed documentation of all __ModuleName__Toolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/__module_name__.agent_toolkits.__ModuleName__.toolkit.__ModuleName__Toolkit.html).\n",
"\n",
"## Setup\n",
"\n",
"- TODO: Update with relevant info."
]
},
{
"cell_type": "markdown",
"id": "72ee0c4b-9764-423a-9dbf-95129e185210",
"metadata": {},
"source": "To enable automated tracing of individual tools, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
},
{
"cell_type": "code",
"execution_count": null,
"id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
"metadata": {},
"outputs": [],
"source": [
"# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
"# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
]
},
{
"cell_type": "markdown",
"id": "0730d6a1-c893-4840-9817-5e5251676d5d",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"This toolkit lives in the `__package_name__` package:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "652d6238-1f87-422a-b135-f5abbb8652fc",
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU __package_name__"
]
},
{
"cell_type": "markdown",
"id": "a38cde65-254d-4219-a441-068766c0d4b5",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"Now we can instantiate our toolkit:\n",
"\n",
"- TODO: Update model instantiation with relevant params."
"## TODO: Any functionality or considerations specific to this toolkit\n",
"\n",
"Fill in or delete if not relevant."
]
},
{
"cell_type": "markdown",
"id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all __ModuleName__Toolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/__module_name__.agent_toolkits.__ModuleName__.toolkit.__ModuleName__Toolkit.html)."
"- TODO: Make sure API reference link is correct.\n",
"\n",
"This notebook provides a quick overview for getting started with __ModuleName__ [tool](/docs/integrations/tools/). For detailed documentation of all __ModuleName__ features and configurations head to the [API reference](https://python.langchain.com/v0.2/api_reference/community/tools/langchain_community.tools.__module_name__.tool.__ModuleName__.html).\n",
"\n",
"- TODO: Add any other relevant links, like information about underlying API, etc.\n",
"\n",
"## Overview\n",
"\n",
"### Integration details\n",
"\n",
"- TODO: Make sure links and features are correct\n",
"### [Invoke directly with args](/docs/concepts/tools/#use-the-tool-directly)\n",
"\n",
"- TODO: Describe what the tool args are, fill them in, run cell"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "65310a8b-eb0c-4d9e-a618-4f4abe2414fc",
"metadata": {},
"outputs": [],
"source": [
"tool.invoke({...})"
]
},
{
"cell_type": "markdown",
"id": "d6e73897",
"metadata": {},
"source": [
"### [Invoke with ToolCall](/docs/concepts/tool_calling/#tool-execution)\n",
"\n",
"We can also invoke the tool with a model-generated ToolCall, in which case a ToolMessage will be returned:\n",
"\n",
"- TODO: Fill in tool args and run cell"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f90e33a7",
"metadata": {},
"outputs": [],
"source": [
"# This is usually generated by a model, but we'll create a tool call directly for demo purposes.\n",
"model_generated_tool_call = {\n",
" \"args\": {...}, # TODO: FILL IN\n",
" \"id\": \"1\",\n",
" \"name\": tool.name,\n",
" \"type\": \"tool_call\",\n",
"}\n",
"tool.invoke(model_generated_tool_call)"
]
},
{
"cell_type": "markdown",
"id": "659f9fbd-6fcf-445f-aa8c-72d8e60154bd",
"metadata": {},
"source": [
"## Use within an agent\n",
"\n",
"- TODO: Add user question and run cells\n",
"\n",
"We can use our tool in an [agent](/docs/concepts/agents/). For this we will need a LLM with [tool-calling](/docs/how_to/tool_calling/) capabilities:\n",
"\n",
"import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
"For detailed documentation of all __ModuleName__ features and configurations head to the API reference: https://python.langchain.com/v0.2/api_reference/community/tools/langchain_community.tools.__module_name__.tool.__ModuleName__.html"
"This notebook covers how to get started with the __ModuleName__ vector store."
]
},
{
"cell_type": "markdown",
"id": "36fdc060",
"metadata": {},
"source": [
"## Setup\n",
"\n",
"- TODO: Update with relevant info.\n",
"- TODO: Update minimum version to be correct.\n",
"\n",
"To access __ModuleName__ vector stores you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package."
"Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "894c30e4",
"metadata": {},
"outputs": [],
"source": [
"import getpass\n",
"import os\n",
"\n",
"if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
"- TODO: Edit and then run code cell to generate output"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ef61e188",
"metadata": {},
"outputs": [],
"source": [
"vector_store.delete(ids=[\"3\"])"
]
},
{
"cell_type": "markdown",
"id": "c3620501",
"metadata": {},
"source": [
"## Query vector store\n",
"\n",
"Once your vector store has been created and the relevant documents have been added you will most likely wish to query it during the running of your chain or agent.\n",
"\n",
"### Query directly\n",
"\n",
"Performing a simple similarity search can be done as follows:\n",
"\n",
"- TODO: Edit and then run code cell to generate output"
"## TODO: Any functionality specific to this vector store\n",
"\n",
"E.g. creating a persisten database to save to your disk, etc."
]
},
{
"cell_type": "markdown",
"id": "8a27244f",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all __ModuleName__VectorStore features and configurations head to the API reference: https://api.python.langchain.com/en/latest/vectorstores/__module_name__.vectorstores.__ModuleName__VectorStore.html"
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
