Tool-calling tests started intermittently failing with
> groq.APIError: Failed to call a function. Please adjust your prompt.
See 'failed_generation' for more details.
**Description:** The error message was supposed to display the missing
vector name, but instead, it includes only the existing collection
configs.
This simple PR just includes the correct variable name, so that the user
knows the requested vector does not exist in the collection.
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
Signed-off-by: Tin Lai <tin@tinyiu.com>
Perplexity's importance in the space has been growing, so we think it's
time to add an official integration!
Note: following the release of `langchain-perplexity` to `pypi`, we
should be able to add `perplexity` as an extra in
`libs/langchain/pyproject.toml`, but we're blocked by a circular import
for now.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Related to https://github.com/langchain-ai/langchain/issues/30344https://github.com/langchain-ai/langchain/pull/30542 introduced an
erroneous test for token counts for o-series models. tiktoken==0.8 does
not support o-series models in
`tiktoken.encoding_for_model(model_name)`, and this is the version of
tiktoken we had in the lock file. So we would default to `cl100k_base`
for o-series, which is the wrong encoding model. The test tested against
this wrong encoding (so it passed with tiktoken 0.8).
Here we update tiktoken to 0.9 in the lock file, and fix the expected
counts in the test. Verified that we are pulling
[o200k_base](https://github.com/openai/tiktoken/blob/main/tiktoken/model.py#L8),
as expected.
**partners: Enable max_retries in ChatMistralAI**
**Description**
- This pull request reactivates the retry logic in the
completion_with_retry method of the ChatMistralAI class, restoring the
intended functionality of the previously ineffective max_retries
parameter. New unit test that mocks failed/successful retry calls and an
integration test to confirm end-to-end functionality.
**Issue**
- Closes#30362
**Dependencies**
- No additional dependencies required
Co-authored-by: andrasfe <andrasf94@gmail.com>
When OpenAI originally released `stream_options` to enable token usage
during streaming, it was not supported in AzureOpenAI. It is now
supported.
Like the [OpenAI
SDK](f66d2e6fdc/src/openai/resources/completions.py (L68)),
ChatOpenAI does not return usage metadata during streaming by default
(which adds an extra chunk to the stream). The OpenAI SDK requires users
to pass `stream_options={"include_usage": True}`. ChatOpenAI implements
a convenience argument `stream_usage: Optional[bool]`, and an attribute
`stream_usage: bool = False`.
Here we extend this to AzureChatOpenAI by moving the `stream_usage`
attribute and `stream_usage` kwarg (on `_(a)stream`) from ChatOpenAI to
BaseChatOpenAI.
---
Additional consideration: we must be sensitive to the number of users
using BaseChatOpenAI to interact with other APIs that do not support the
`stream_options` parameter.
Suppose OpenAI in the future updates the default behavior to stream
token usage. Currently, BaseChatOpenAI only passes `stream_options` if
`stream_usage` is True, so there would be no way to disable this new
default behavior.
To address this, we could update the `stream_usage` attribute to
`Optional[bool] = None`, but this is technically a breaking change (as
currently values of False are not passed to the client). IMO: if / when
this change happens, we could accompany it with this update in a minor
bump.
---
Related previous PRs:
- https://github.com/langchain-ai/langchain/pull/22628
- https://github.com/langchain-ai/langchain/pull/22854
- https://github.com/langchain-ai/langchain/pull/23552
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
We are implementing a token-counting callback handler in
`langchain-core` that is intended to work with all chat models
supporting usage metadata. The callback will aggregate usage metadata by
model. This requires responses to include the model name in its
metadata.
To support this, if a model `returns_usage_metadata`, we check that it
includes a string model name in its `response_metadata` in the
`"model_name"` key.
More context: https://github.com/langchain-ai/langchain/pull/30487
Deepseek model does not return reasoning when hosted on openrouter
(Issue [30067](https://github.com/langchain-ai/langchain/issues/30067))
the following code did not return reasoning:
```python
llm = ChatDeepSeek( model = 'deepseek/deepseek-r1:nitro', api_base="https://openrouter.ai/api/v1", api_key=os.getenv("OPENROUTER_API_KEY"))
messages = [
{"role": "system", "content": "You are an assistant."},
{"role": "user", "content": "9.11 and 9.8, which is greater? Explain the reasoning behind this decision."}
]
response = llm.invoke(messages, extra_body={"include_reasoning": True})
print(response.content)
print(f"REASONING: {response.additional_kwargs.get('reasoning_content', '')}")
print(response)
```
The fix is to extract reasoning from
response.choices[0].message["model_extra"] and from
choices[0].delta["reasoning"]. and place in response additional_kwargs.
Change is really just the addition of a couple one-sentence if
statements.
---------
Co-authored-by: andrasfe <andrasf94@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
# Description
This PR adds reasoning model support for `langchain-ollama` by
extracting reasoning token blocks, like those used in deepseek. It was
inspired by
[ollama-deep-researcher](https://github.com/langchain-ai/ollama-deep-researcher),
specifically the parsing of [thinking
blocks](6d1aaf2139/src/assistant/graph.py (L91)):
```python
# TODO: This is a hack to remove the <think> tags w/ Deepseek models
# It appears very challenging to prompt them out of the responses
while "<think>" in running_summary and "</think>" in running_summary:
start = running_summary.find("<think>")
end = running_summary.find("</think>") + len("</think>")
running_summary = running_summary[:start] + running_summary[end:]
```
This notes that it is very hard to remove the reasoning block from
prompting, but we actually want the model to reason in order to increase
model performance. This implementation extracts the thinking block, so
the client can still expect a proper message to be returned by
`ChatOllama` (and use the reasoning content separately when desired).
This implementation takes the same approach as
[ChatDeepseek](5d581ba22c/libs/partners/deepseek/langchain_deepseek/chat_models.py (L215)),
which adds the reasoning content to
chunk.additional_kwargs.reasoning_content;
```python
if hasattr(response.choices[0].message, "reasoning_content"): # type: ignore
rtn.generations[0].message.additional_kwargs["reasoning_content"] = (
response.choices[0].message.reasoning_content # type: ignore
)
```
This should probably be handled upstream in ollama + ollama-python, but
this seems like a reasonably effective solution. This is a standalone
example of what is happening;
```python
async def deepseek_message_astream(
llm: BaseChatModel,
messages: list[BaseMessage],
config: RunnableConfig | None = None,
*,
model_target: str = "deepseek-r1",
**kwargs: Any,
) -> AsyncIterator[BaseMessageChunk]:
"""Stream responses from Deepseek models, filtering out <think> tags.
Args:
llm: The language model to stream from
messages: The messages to send to the model
Yields:
Filtered chunks from the model response
"""
# check if the model is deepseek based
if (llm.name and model_target not in llm.name) or (hasattr(llm, "model") and model_target not in llm.model):
async for chunk in llm.astream(messages, config=config, **kwargs):
yield chunk
return
# Yield with a buffer, upon completing the <think></think> tags, move them to the reasoning content and start over
buffer = ""
async for chunk in llm.astream(messages, config=config, **kwargs):
# start or append
if not buffer:
buffer = chunk.content
else:
buffer += chunk.content if hasattr(chunk, "content") else chunk
# Process buffer to remove <think> tags
if "<think>" in buffer or "</think>" in buffer:
if hasattr(chunk, "tool_calls") and chunk.tool_calls:
raise NotImplementedError("tool calls during reasoning should be removed?")
if "<think>" in chunk.content or "</think>" in chunk.content:
continue
chunk.additional_kwargs["reasoning_content"] = chunk.content
chunk.content = ""
# upon block completion, reset the buffer
if "<think>" in buffer and "</think>" in buffer:
buffer = ""
yield chunk
```
# Issue
Integrating reasoning models (e.g. deepseek-r1) into existing LangChain
based workflows is hard due to the thinking blocks that are included in
the message contents. To avoid this, we could match the `ChatOllama`
integration with `ChatDeepseek` to return the reasoning content inside
`message.additional_arguments.reasoning_content` instead.
# Dependenices
None
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- Test if models support forcing tool calls via `tool_choice`. If they
do, they should support
- `"any"` to specify any tool
- the tool name as a string to force calling a particular tool
- Add `tool_choice` to signature of `BaseChatModel.bind_tools` in core
- Deprecate `tool_choice_value` in standard tests in favor of a boolean
`has_tool_choice`
Will follow up with PRs in external repos (tested in AWS and Google
already).
**Description:**
This PR fixes a minor typo in the comments within
`libs/partners/openai/langchain_openai/chat_models/base.py`. The word
"ben" has been corrected to "be" for clarity and professionalism.
**Issue:**
N/A
**Dependencies:**
None
From function calling to Ollama's [dedicated structured output
feature](https://ollama.com/blog/structured-outputs).
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
The default model for `ChatGroq`, `"mixtral-8x7b-32768"`, is being
retired on March 20, 2025. Here we remove the default, such that model
names must be explicitly specified (being explicit is a good practice
here, and avoids the need for breaking changes down the line). This
change will be released in a minor version bump to 0.3.
This follows https://github.com/langchain-ai/langchain/pull/30161
(released in version 0.2.5), where we began generating warnings to this
effect.
- Support features from recent update:
https://www.anthropic.com/news/token-saving-updates (mostly adding
support for built-in tools in `bind_tools`
- Add documentation around prompt caching, token-efficient tool use, and
built-in tools.
Groq is retiring `mixtral-8x7b-32768`, which is currently the default
model for ChatGroq, on March 20. Here we emit a warning if the model is
not specified explicitly.
A version 0.3.0 will be released ahead of March 20 that removes the
default altogether.
- Support thinking blocks in core's `convert_to_openai_messages` (pass
through instead of error)
- Ignore thinking blocks in ChatOpenAI (instead of error)
- Support Anthropic-style image blocks in ChatOpenAI
---
Standard integration tests include a `supports_anthropic_inputs`
property which is currently enabled only for tests on `ChatAnthropic`.
This test enforces compatibility with message histories of the form:
```
- system message
- human message
- AI message with tool calls specified only through `tool_use` content blocks
- human message containing `tool_result` and an additional `text` block
```
It additionally checks support for Anthropic-style image inputs if
`supports_image_inputs` is enabled.
Here we change this test, such that if you enable
`supports_anthropic_inputs`:
- You support AI messages with text and `tool_use` content blocks
- You support Anthropic-style image inputs (if `supports_image_inputs`
is enabled)
- You support thinking content blocks.
That is, we add a test case for thinking content blocks, but we also
remove the requirement of handling tool results within HumanMessages
(motivated by existing agent abstractions, which should all return
ToolMessage). We move that requirement to a ChatAnthropic-specific test.
- **Description:** Fix typo in code samples for max_tokens_for_prompt.
Code blocks had singular "token" but the method has plural "tokens".
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** N/A
Structured output will currently always raise a BadRequestError when
Claude 3.7 Sonnet's `thinking` is enabled, because we rely on forced
tool use for structured output and this feature is not supported when
`thinking` is enabled.
Here we:
- Emit a warning if `with_structured_output` is called when `thinking`
is enabled.
- Raise `OutputParserException` if no tool calls are generated.
This is arguably preferable to raising an error in all cases.
```python
from langchain_anthropic import ChatAnthropic
from pydantic import BaseModel
class Person(BaseModel):
name: str
age: int
llm = ChatAnthropic(
model="claude-3-7-sonnet-latest",
max_tokens=5_000,
thinking={"type": "enabled", "budget_tokens": 2_000},
)
structured_llm = llm.with_structured_output(Person) # <-- this generates a warning
```
```python
structured_llm.invoke("Alice is 30.") # <-- works
```
```python
structured_llm.invoke("Hello!") # <-- raises OutputParserException
```
Took a "census" of models supported by init_chat_model-- of those that
return model names in response metadata, these were the only two that
had it keyed under `"model"` instead of `"model_name"`.
Resolves https://github.com/langchain-ai/langchain/issues/29003,
https://github.com/langchain-ai/langchain/issues/27264
Related: https://github.com/langchain-ai/langchain-redis/issues/52
```python
from langchain.chat_models import init_chat_model
from langchain.globals import set_llm_cache
from langchain_community.cache import SQLiteCache
from pydantic import BaseModel
cache = SQLiteCache()
set_llm_cache(cache)
class Temperature(BaseModel):
value: int
city: str
llm = init_chat_model("openai:gpt-4o-mini")
structured_llm = llm.with_structured_output(Temperature)
```
```python
# 681 ms
response = structured_llm.invoke("What is the average temperature of Rome in May?")
```
```python
# 6.98 ms
response = structured_llm.invoke("What is the average temperature of Rome in May?")
```
Some o-series models will raise a 400 error for `"role": "system"`
(`o1-mini` and `o1-preview` will raise, `o1` and `o3-mini` will not).
Here we update `ChatOpenAI` to update the role to `"developer"` for all
model names matching `^o\d`.
We only make this change on the ChatOpenAI class (not BaseChatOpenAI).
For Context please check #29626
The Deepseek is using langchain_openai. The error happens that it show
`json decode error`.
I added a handler for this to give a more sensible error message which
is DeepSeek API returned empty/invalid json.
Reproducing the issue is a bit challenging as it is inconsistent,
sometimes DeepSeek returns valid data and in other times it returns
invalid data which triggers the JSON Decode Error.
This PR is an exception handling, but not an ultimate fix for the issue.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
**Description:** Update docstring for `reasoning_effort` argument to
specify that it applies to reasoning models only (e.g., OpenAI o1 and
o3-mini), clarifying its supported models.
**Issue:** None
**Dependencies:** None
https://docs.x.ai/docs/guides/structured-outputs
Interface appears identical to OpenAI's.
```python
from langchain.chat_models import init_chat_model
from pydantic import BaseModel
class Joke(BaseModel):
setup: str
punchline: str
llm = init_chat_model("xai:grok-2").with_structured_output(
Joke, method="json_schema"
)
llm.invoke("Tell me a joke about cats.")
```
- **Description:** Small fix in `add_texts` to make embedding
nullability is checked properly.
- **Issue:** #29765
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
This fix ensures that the chunk size is correctly determined when
processing text embeddings. Previously, the code did not properly handle
cases where chunk_size was None, potentially leading to incorrect
chunking behavior.
Now, chunk_size_ is explicitly set to either the provided chunk_size or
the default self.chunk_size, ensuring consistent chunking. This update
improves reliability when processing large text inputs in batches and
prevents unintended behavior when chunk_size is not specified.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
1. Make `_convert_chunk_to_generation_chunk` an instance method on
BaseChatOpenAI
2. Override on ChatDeepSeek to add `"reasoning_content"` to message
additional_kwargs.
Resolves https://github.com/langchain-ai/langchain/issues/29513
- This pull request includes various changes to add a `user_agent`
parameter to Azure OpenAI, Azure Search and Whisper in the Community and
Partner packages. This helps in identifying the source of API requests
so we can better track usage and help support the community better. I
will also be adding the user_agent to the new `langchain-azure` repo as
well.
- No issue connected or updated dependencies.
- Utilises existing tests and docs
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
ONNX and OpenVINO models are available by specifying the `backend`
argument (the model is loaded using `optimum`
https://github.com/huggingface/optimum)
```python
from langchain_huggingface import HuggingFaceEmbeddings
embedding = HuggingFaceEmbeddings(
model_name=model_id,
model_kwargs={"backend": "onnx"},
)
```
With this PR we also enable the IPEX backend
```python
from langchain_huggingface import HuggingFaceEmbeddings
embedding = HuggingFaceEmbeddings(
model_name=model_id,
model_kwargs={"backend": "ipex"},
)
```
- **Description:** Before sending a completion chunk at the end of an
OpenAI stream, removing the tool_calls as those have already been sent
as chunks.
- **Issue:** -
- **Dependencies:** -
- **Twitter handle:** -
@ccurme as mentioned in another PR
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Added `similarity_search_with_score_by_vector()` function to the
`QdrantVectorStore` class.
It is required when we want to query multiple time with the same
embeddings. It was present in the now deprecated original `Qdrant`
vectorstore implementation, but was absent from the new one. It is also
implemented in a number of others `VectorStore` implementations
I have added tests for this new function
Note that I also argued in this discussion that it should be part of the
general `VectorStore`
https://github.com/langchain-ai/langchain/discussions/29638
Co-authored-by: Erick Friis <erick@langchain.dev>
These are set in Github workflows, but forgot to add them to most
makefiles for convenience when developing locally.
`uv run` will automatically sync the lock file. Because many of our
development dependencies are local installs, it will pick up version
changes and update the lock file. Passing `--frozen` or setting this
environment variable disables the behavior.
- **Description:** Add to check pad_token_id and eos_token_id of model
config. It seems that this is the same bug as the HuggingFace TGI bug.
It's same bug as #29434
- **Issue:** #29431
- **Dependencies:** none
- **Twitter handle:** tell14
Example code is followings:
```python
from langchain_huggingface.llms import HuggingFacePipeline
hf = HuggingFacePipeline.from_model_id(
model_id="meta-llama/Llama-3.2-3B-Instruct",
task="text-generation",
pipeline_kwargs={"max_new_tokens": 10},
)
from langchain_core.prompts import PromptTemplate
template = """Question: {question}
Answer: Let's think step by step."""
prompt = PromptTemplate.from_template(template)
chain = prompt | hf
question = "What is electroencephalography?"
print(chain.invoke({"question": question}))
```
Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core, etc. is
being modified. Use "docs: ..." for purely docs changes, "infra: ..."
for CI changes.
- Example: "community: add foobar LLM"
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [x] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
We currently return string (and therefore no content blocks / citations)
if the response is of the form
```
[
{"text": "a claim", "citations": [...]},
]
```
There are other cases where we do return citations as-is:
```
[
{"text": "a claim", "citations": [...]},
{"text": "some other text"},
{"text": "another claim", "citations": [...]},
]
```
Here we update to return content blocks including citations in the first
case as well.
- **Description:** The ValueError raised on certain structured-outputs
parsing errors, in langchain openai community integration, was missing a
f-string modifier and so didn't produce useful outputs. This is a
2-line, 2-character change.
- **Issue:** None open that this fixes
- **Dependencies:** Nothing changed
- **Twitter handle:** None
- [X] **Add tests and docs**: There's nothing to add for.
- [-] **Lint and test**: Happy to run this if you deem it necessary.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- [feat] **Added backwards compatibility for OllamaEmbeddings
initialization (migration from `langchain_community.embeddings` to
`langchain_ollama.embeddings`**: "langchain_ollama"
- **Description:** Given that `OllamaEmbeddings` from
`langchain_community.embeddings` is deprecated, code is being shifted to
``langchain_ollama.embeddings`. However, this does not offer backward
compatibility of initializing the parameters and `OllamaEmbeddings`
object.
- **Issue:** #29294
- **Dependencies:** None
- **Twitter handle:** @BaqarAbbas2001
## Additional Information
Previously, `OllamaEmbeddings` from `langchain_community.embeddings`
used to support the following options:
e9abe583b2/libs/community/langchain_community/embeddings/ollama.py (L125-L139)
However, in the new package `from langchain_ollama import
OllamaEmbeddings`, there is no method to set these options. I have added
these parameters to resolve this issue.
This issue was also discussed in
https://github.com/langchain-ai/langchain/discussions/29113
The tokens I get are:
```
['', '\n\n', 'The', ' sun', ' was', ' setting', ' over', ' the', ' horizon', ',', ' casting', '']
```
so possibly an extra empty token is included in the output.
lmk @efriis if we should look into this further.
