Multiple models were
[retired](https://docs.anthropic.com/en/docs/about-claude/model-deprecations#model-status)
yesterday.
Tests remain broken until we figure out what to do with the legacy
Anthropic LLM integration— currently uses their (legacy) text
completions API, for which there appear to be no remaining supported
models.
* Adding support for more Chroma client options (`HttpClient` and
`CloundClient`). This includes adding arguments necessary for
instantiating these clients.
* Adding support for Chroma's new persisted collection configuration (we
moved index configuration into this new construct).
* Delegate `Settings` configuration to Chroma's client constructors.
## Problem
When using `ChatOllama` with `create_react_agent`, agents would
sometimes terminate prematurely with empty responses when Ollama
returned `done_reason: 'load'` responses with no content. This caused
agents to return empty `AIMessage` objects instead of actual generated
text.
```python
from langchain_ollama import ChatOllama
from langgraph.prebuilt import create_react_agent
from langchain_core.messages import HumanMessage
llm = ChatOllama(model='qwen2.5:7b', temperature=0)
agent = create_react_agent(model=llm, tools=[])
result = agent.invoke(HumanMessage('Hello'), {"configurable": {"thread_id": "1"}})
# Before fix: AIMessage(content='', response_metadata={'done_reason': 'load'})
# Expected: AIMessage with actual generated content
```
## Root Cause
The `_iterate_over_stream` and `_aiterate_over_stream` methods treated
any response with `done: True` as final, regardless of `done_reason`.
When Ollama returns `done_reason: 'load'` with empty content, it
indicates the model was loaded but no actual generation occurred - this
should not be considered a complete response.
## Solution
Modified the streaming logic to skip responses when:
- `done: True`
- `done_reason: 'load'`
- Content is empty or contains only whitespace
This ensures agents only receive actual generated content while
preserving backward compatibility for load responses that do contain
content.
## Changes
- **`_iterate_over_stream`**: Skip empty load responses instead of
yielding them
- **`_aiterate_over_stream`**: Apply same fix to async streaming
- **Tests**: Added comprehensive test cases covering all edge cases
## Testing
All scenarios now work correctly:
- ✅ Empty load responses are skipped (fixes original issue)
- ✅ Load responses with actual content are preserved (backward
compatibility)
- ✅ Normal stop responses work unchanged
- ✅ Streaming behavior preserved
- ✅ `create_react_agent` integration fixed
Fixes#31482.
<!-- START COPILOT CODING AGENT TIPS -->
---
💡 You can make Copilot smarter by setting up custom instructions,
customizing its development environment and configuring Model Context
Protocol (MCP) servers. Learn more [Copilot coding agent
tips](https://gh.io/copilot-coding-agent-tips) in the docs.
---------
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>
This PR addresses deprecation warnings users encounter when using
LangChain tools with Pydantic v2:
```
PydanticDeprecatedSince20: The `schema` method is deprecated; use `model_json_schema` instead.
Deprecated in Pydantic V2.0 to be removed in V3.0.
```
## Root Cause
Several LangChain components were still using the deprecated `.schema()`
method directly instead of the Pydantic v1/v2 compatible approach. While
users calling `.schema()` on returned models will still see warnings
(which is correct), LangChain's internal code should not generate these
warnings.
## Changes Made
Updated 3 files to use the standard compatibility pattern:
```python
# Before (deprecated)
schema = model.schema()
# After (compatible with both v1 and v2)
if hasattr(model, "model_json_schema"):
schema = model.model_json_schema() # Pydantic v2
else:
schema = model.schema() # Pydantic v1
```
### Files Updated:
- **`evaluation/parsing/json_schema.py`**: Fixed `_parse_json()` method
to handle Pydantic models correctly
- **`output_parsers/yaml.py`**: Fixed `get_format_instructions()` to use
compatible schema access
- **`chains/openai_functions/citation_fuzzy_match.py`**: Fixed direct
`.schema()` call on QuestionAnswer model
## Verification
✅ **Zero breaking changes** - all existing functionality preserved
✅ **No deprecation warnings** from LangChain internal code
✅ **Backward compatible** with Pydantic v1
✅ **Forward compatible** with Pydantic v2
✅ **Edge cases handled** (strings, plain objects, etc.)
## User Impact
LangChain users will no longer see deprecation warnings from internal
LangChain code. Users who directly call `.schema()` on schemas returned
by LangChain should adopt the same compatibility pattern:
```python
# User code should use this pattern
input_schema = tool.get_input_schema()
if hasattr(input_schema, "model_json_schema"):
schema_result = input_schema.model_json_schema()
else:
schema_result = input_schema.schema()
```
Fixes#31458.
<!-- 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>
This PR fixes the PostgreSQL NUL byte issue that causes
`psycopg.DataError` when inserting documents containing `\x00` bytes
into PostgreSQL-based vector stores.
## Problem
PostgreSQL text fields cannot contain NUL (0x00) bytes. When documents
with such characters are processed by PGVector or langchain-postgres
implementations, they fail with:
```
(psycopg.DataError) PostgreSQL text fields cannot contain NUL (0x00) bytes
```
This commonly occurs when processing PDFs, documents from various
loaders, or text extracted by libraries like unstructured that may
contain embedded NUL bytes.
## Solution
Added `sanitize_for_postgres()` utility function to
`langchain_core.utils.strings` that removes or replaces NUL bytes from
text content.
### Key Features
- **Simple API**: `sanitize_for_postgres(text, replacement="")`
- **Configurable**: Replace NUL bytes with empty string (default) or
space for readability
- **Comprehensive**: Handles all problematic examples from the original
issue
- **Well-tested**: Complete unit tests with real-world examples
- **Backward compatible**: No breaking changes, purely additive
### Usage Example
```python
from langchain_core.utils import sanitize_for_postgres
from langchain_core.documents import Document
# Before: This would fail with DataError
problematic_content = "Getting\x00Started with embeddings"
# After: Clean the content before database insertion
clean_content = sanitize_for_postgres(problematic_content)
# Result: "GettingStarted with embeddings"
# Or preserve readability with spaces
readable_content = sanitize_for_postgres(problematic_content, " ")
# Result: "Getting Started with embeddings"
# Use in Document processing
doc = Document(page_content=clean_content, metadata={...})
```
### Integration Pattern
PostgreSQL vector store implementations should sanitize content before
insertion:
```python
def add_documents(self, documents: List[Document]) -> List[str]:
# Sanitize documents before insertion
sanitized_docs = []
for doc in documents:
sanitized_content = sanitize_for_postgres(doc.page_content, " ")
sanitized_doc = Document(
page_content=sanitized_content,
metadata=doc.metadata,
id=doc.id
)
sanitized_docs.append(sanitized_doc)
return self._insert_documents_to_db(sanitized_docs)
```
## Changes Made
- Added `sanitize_for_postgres()` function in
`langchain_core/utils/strings.py`
- Updated `langchain_core/utils/__init__.py` to export the new function
- Added comprehensive unit tests in
`tests/unit_tests/utils/test_strings.py`
- Validated against all examples from the original issue report
## Testing
All tests pass, including:
- Basic NUL byte removal and replacement
- Multiple consecutive NUL bytes
- Empty string handling
- Real examples from the GitHub issue
- Backward compatibility with existing string utilities
This utility enables PostgreSQL integrations in both langchain-community
and langchain-postgres packages to handle documents with NUL bytes
reliably.
Fixes#26033.
<!-- 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>
See https://docs.astral.sh/ruff/rules/#tryceratops-try
* TRY004 (replace by TypeError) in main code is escaped with `noqa` to
not break backward compatibility. The rule is still interesting for new
code.
* TRY301 ignored at the moment. This one is quite hard to fix and I'm
not sure it's very interesting to activate it.
Co-authored-by: Mason Daugherty <mason@langchain.dev>
* **Description:** Updated `parse_result` logic to handle cases where
`self.first_tool_only` is `True` and multiple matching keys share the
same function name. Instead of returning the first match prematurely,
the method now prioritizes filtering results by the specified key to
ensure correct selection.
* **Issue:** #32100
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
**Description:**
This PR makes argument parsing for Ollama tool calls more robust. Some
LLMs—including Ollama—may return arguments as Python-style dictionaries
with single quotes (e.g., `{'a': 1}`), which are not valid JSON and
previously caused parsing to fail.
The updated `_parse_json_string` method in
`langchain_ollama.chat_models` now attempts standard JSON parsing and,
if that fails, falls back to `ast.literal_eval` for safe evaluation of
Python-style dictionaries. This improves interoperability with LLMs and
fixes a common usability issue for tool-based agents.
**Issue:**
Closes#30910
**Dependencies:**
None
**Tests:**
- Added new unit tests for double-quoted JSON, single-quoted dicts,
mixed quoting, and malformed/failure cases.
- All tests pass locally, including new coverage for single-quoted
inputs.
**Notes:**
- No breaking changes.
- No new dependencies introduced.
- Code is formatted and linted (`ruff format`, `ruff check`).
- If maintainers have suggestions for further improvements, I’m happy to
revise!
Thank you for maintaining LangChain! Looking forward to your feedback.
Previously, we hit an index out of range error with empty variable names
(accessing tag[0]), now we through a slightly nicer error
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Fixes#32042
## Summary
Fixes a critical bug in JSON Schema reference resolution that prevented
correctly dereferencing numeric components in JSON pointer paths,
specifically for list indices in `anyOf`, `oneOf`, and `allOf` arrays.
## Changes
- Fixed `_retrieve_ref` function in
`libs/core/langchain_core/utils/json_schema.py` to properly handle
numeric components
- Added comprehensive test function `test_dereference_refs_list_index()`
in `libs/core/tests/unit_tests/utils/test_json_schema.py`
- Resolved line length formatting issues
- Improved type checking and index validation for list and dictionary
references
## Key Improvements
- Correctly handles list index references in JSON pointer paths
- Maintains backward compatibility with existing dictionary numeric key
functionality
- Adds robust error handling for out-of-bounds and invalid indices
- Passes all test cases covering various reference scenarios
## Test Coverage
- Verified fix for `#/properties/payload/anyOf/1/properties/startDate`
reference
- Tested edge cases including out-of-bounds and negative indices
- Ensured no regression in existing reference resolution functionality
Resolves the reported issue with JSON Schema reference dereferencing for
list indices.
---------
Co-authored-by: open-swe-dev[bot] <open-swe-dev@users.noreply.github.com>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Since #29963 BaseCache and Callbacks are imported in BaseLanguageModel
so there's no need to import them and rebuild the models.
Note: fix is available since `langchain-core==0.3.39` and the current
langchain dependency on core is `>=0.3.66` so the fix will always be
there.
The `num_gpu` parameter in `OllamaEmbeddings` was not being passed to
the Ollama client in the async embedding method, causing GPU
acceleration settings to be ignored when using async operations.
## Problem
The issue was in the `aembed_documents` method where the `options`
parameter (containing `num_gpu` and other configuration) was missing:
```python
# Sync method (working correctly)
return self._client.embed(
self.model, texts, options=self._default_params, keep_alive=self.keep_alive
)["embeddings"]
# Async method (missing options parameter)
return (
await self._async_client.embed(
self.model, texts, keep_alive=self.keep_alive # ❌ No options!
)
)["embeddings"]
```
This meant that when users specified `num_gpu=4` (or any other GPU
configuration), it would work with sync calls but be ignored with async
calls.
## Solution
Added the missing `options=self._default_params` parameter to the async
embed call to match the sync version:
```python
# Fixed async method
return (
await self._async_client.embed(
self.model,
texts,
options=self._default_params, # ✅ Now includes num_gpu!
keep_alive=self.keep_alive,
)
)["embeddings"]
```
## Validation
- ✅ Added unit test to verify options are correctly passed in both sync
and async methods
- ✅ All existing tests continue to pass
- ✅ Manual testing confirms `num_gpu` parameter now works correctly
- ✅ Code passes linting and formatting checks
The fix ensures that GPU configuration works consistently across both
synchronous and asynchronous embedding operations.
Fixes#32059.
<!-- START COPILOT CODING AGENT TIPS -->
---
💡 You can make Copilot smarter by setting up custom instructions,
customizing its development environment and configuring Model Context
Protocol (MCP) servers. Learn more [Copilot coding agent
tips](https://gh.io/copilot-coding-agent-tips) in the docs.
---------
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>
Description
The Perplexity chat model already returns a search_results field, but
LangChain dropped it when mapping Perplexity responses to
additional_kwargs.
This patch adds "search_results" to the allowed attribute lists in both
_stream and _generate, so downstream code can access it just like
images, citations, or related_questions.
Dependencies
None. The change is purely internal; no new imports or optional
dependencies required.
https://community.perplexity.ai/t/new-feature-search-results-field-with-richer-metadata/398
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
## Description
When ChatDeepSeek invokes a tool that returns a list, it results in an
openai.UnprocessableEntityError due to a failure in deserializing the
JSON body.
The root of the problem is that ChatDeepSeek uses BaseChatOpenAI
internally, but the APIs are not identical: OpenAI v1/chat/completions
accepts arrays as tool results, but Deepseek API does not.
As a solution added `_get_request_payload` method to ChatDeepSeek, which
inherits the behavior from BaseChatOpenAI but adds a step to stringify
tool message content in case the content is an array. I also add a unit
test for this.
From the linked issue you can find the full reproducible example the
reporter of the issue provided. After the changes it works as expected.
Source: [Deepseek
docs](https://api-docs.deepseek.com/api/create-chat-completion/)
Source: [OpenAI
docs](https://platform.openai.com/docs/api-reference/chat/create)
## Issue
Fixes#31394
## Dependencies:
No new dependencies.
## Twitter handle:
Don't have one.
---------
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
- **Description:** Ensure that the tool description is an empty string
when creating a Structured Tool from a Pydantic class in case no
description is provided
- **Issue:** Fixes#31606
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
- **Description**: issues a warning if inf and nan are passed as inputs
to langchain_core.vectorstores.utils._cosine_similarity
- **Issue**: Fixes#31496
- **Dependencies**: no external dependencies added, only warnings module
imported
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
