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.
- **partner**: "Update Aiohttp for resolving vulnerability issue"
- **Description:** I have updated the upper limit of aiohttp from `3.10`
to `3.10.5` in the pyproject.toml file of langchain-pinecone. Hopefully
this will resolve#28771 . Please review this as I'm quite unsure.
---------
Co-authored-by: = <=>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
## Goal
Solve the following problems with `langchain-openai`:
- Structured output with `o1` [breaks out of the
box](https://langchain.slack.com/archives/C050X0VTN56/p1735232400232099).
- `with_structured_output` by default does not use OpenAI’s [structured
output
feature](https://platform.openai.com/docs/guides/structured-outputs).
- We override API defaults for temperature and other parameters.
## Breaking changes:
- Default method for structured output is changing to OpenAI’s dedicated
[structured output
feature](https://platform.openai.com/docs/guides/structured-outputs).
For schemas specified via TypedDict or JSON schema, strict schema
validation is disabled by default but can be enabled by specifying
`strict=True`.
- To recover previous default, pass `method="function_calling"` into
`with_structured_output`.
- Models that don’t support `method="json_schema"` (e.g., `gpt-4` and
`gpt-3.5-turbo`, currently the default model for ChatOpenAI) will raise
an error unless `method` is explicitly specified.
- To recover previous default, pass `method="function_calling"` into
`with_structured_output`.
- Schemas specified via Pydantic `BaseModel` that have fields with
non-null defaults or metadata (like min/max constraints) will raise an
error.
- To recover previous default, pass `method="function_calling"` into
`with_structured_output`.
- `strict` now defaults to False for `method="json_schema"` when schemas
are specified via TypedDict or JSON schema.
- To recover previous behavior, use `with_structured_output(schema,
strict=True)`
- Schemas specified via Pydantic V1 will raise a warning (and use
`method="function_calling"`) unless `method` is explicitly specified.
- To remove the warning, pass `method="function_calling"` into
`with_structured_output`.
- Streaming with default structured output method / Pydantic schema no
longer generates intermediate streamed chunks.
- To recover previous behavior, pass `method="function_calling"` into
`with_structured_output`.
- We no longer override default temperature (was 0.7 in LangChain, now
will follow OpenAI, currently 1.0).
- To recover previous behavior, initialize `ChatOpenAI` or
`AzureChatOpenAI` with `temperature=0.7`.
- Note: conceptually there is a difference between forcing a tool call
and forcing a response format. Tool calls may have more concise
arguments vs. generating content adhering to a schema. Prompts may need
to be adjusted to recover desired behavior.
---------
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Title: langchain-pinecone: improve test structure and async handling
Description: This PR improves the test infrastructure for the
langchain-pinecone package by:
1. Implementing LangChain's standard test patterns for embeddings
2. Adding comprehensive configuration testing
3. Improving async test coverage
4. Fixing integration test issues with namespaces and async markers
The changes make the tests more robust, maintainable, and aligned with
LangChain's testing standards while ensuring proper async behavior in
the embeddings implementation.
Key improvements:
- Added standard EmbeddingsTests implementation
- Split custom configuration tests into a separate test class
- Added proper async test coverage with pytest-asyncio
- Fixed namespace handling in vector store integration tests
- Improved test organization and documentation
Dependencies: None (uses existing test dependencies)
Tests and Documentation:
- ✅ Added standard test implementation following LangChain's patterns
- ✅ Added comprehensive unit tests for configuration and async behavior
- ✅ All tests passing locally
- No documentation changes needed (internal test improvements only)
Twitter handle: N/A
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:**
This PR addresses an issue with the `stop_sequences` field in the
`ChatGroq` class. Currently, the field is defined as:
```python
stop: Optional[Union[List[str], str]] = Field(None, alias="stop_sequences")
```
This causes the language server (LSP) to raise an error indicating that
the `stop_sequences` parameter must be implemented. The issue occurs
because `Field(None, alias="stop_sequences")` is different compared to
`Field(default=None, alias="stop_sequences")`.
To resolve the issue, the field is updated to:
```python
stop: Optional[Union[List[str], str]] = Field(default=None, alias="stop_sequences")
```
While this issue does not affect runtime behavior, it ensures
compatibility with LSPs and improves the development experience.
- **Issue:** N/A
- **Dependencies:** None
**Description:**
Added ability to set `prefix` attribute to prevent error :
```
httpx.HTTPStatusError: Error response 400 while fetching https://api.mistral.ai/v1/chat/completions: {"object":"error","message":"Expected last role User or Tool (or Assistant with prefix True) for serving but got assistant","type":"invalid_request_error","param":null,"code":null}
```
Co-authored-by: Sylvain DEPARTE <sylvain.departe@wizbii.com>
- Convert developer openai messages to SystemMessage
- store additional_kwargs={"__openai_role__": "developer"} so that the
correct role can be reconstructed if needed
- update ChatOpenAI to read in openai_role
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
…ent path given.
Thank you for contributing to LangChain!
- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
**Description:** This PR introduces a `model` alias for the embedding
classes that contain the attribute `model_name`, to ensure consistency
across the codebase, as suggested by a moderator in a previous PR. The
change aligns the usage of attribute names across the project (see for
example
[here](65deeddd5d/libs/partners/groq/langchain_groq/chat_models.py (L304))).
**Issue:** This PR addresses the suggestion from the review of issue
#28269.
**Dependencies:** None
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Currently `_convert_TGI_message_to_LC_message` replaces `'` in the tool
arguments, so an argument like "It's" will be converted to `It"s` and
could cause a json parser to fail.
---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Vadym Barda <vadym@langchain.dev>
- **Description:**: In the event of a Rate Limit Error from the
MistralAI server, the response JSON raises a KeyError. To address this,
a simple retry mechanism has been implemented to handle cases where the
request limit is exceeded.
- **Issue:** #27790
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
- **Description:** Streaming response from Mistral model using Vertex AI
raises KeyError when trying to access `choices` key, that the last chunk
doesn't have. The fix is to access the key safely using `get()`.
- **Issue:** https://github.com/langchain-ai/langchain/issues/27886
- **Dependencies:**
- **Twitter handle:**
- Description: Azure AI takes an issue with the safe_mode parameter
being set to False instead of None. Therefore, this PR changes the
default value of safe_mode from False to None. This results in it being
filtered out before the request is sent - avoind the extra-parameter
issue described below.
- Issue: #26029
- Dependencies: /
---------
Co-authored-by: blaufink <sebastian.brueckner@outlook.de>
Co-authored-by: Erick Friis <erick@langchain.dev>
- Run standard integration tests in Chroma
- Add `get_by_ids` method
- Fix bug in `add_texts`: if a list of `ids` is passed but any of them
are None, Chroma will raise an exception. Here we assign a uuid.
Description:
* Added internal `Document.id` support to Chroma VectorStore
Dependencies:
* https://github.com/langchain-ai/langchain/pull/27968 should be merged
first and this PR should be re-based on top of those changes.
Tests:
* Modified/Added tests for `Document.id` support. All tests are passing.
Note: I am not a member of the Chroma team.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
This PR updates the Pinecone client to `5.4.0`, as well as its
dependencies (`pinecone-plugin-inference` and
`pinecone-plugin-interface`).
Note: `pinecone-client` is now simply called `pinecone`.
**Question for reviewer(s):** should this PR also update the `pinecone`
dep in [the root dir's `poetry.lock`
file](https://github.com/langchain-ai/langchain/blob/master/poetry.lock#L6729)?
Was unsure. (I don't believe so b/c it seems pinned to a lower version
likely based on 3rd-party deps (e.g. Unstructured).)
--
TW: @audrey_sage_
---
- To see the specific tasks where the Asana app for GitHub is being
used, see below:
- https://app.asana.com/0/0/1208693659122374
This PR adds an additional method to `Chroma` to retrieve the embedding
vectors, besides the most relevant Documents. This is sometimes of use
when you need to run a postprocessing algorithm on the retrieved results
based on the vectors, which has been the case for me lately.
Example issue (discussion) requesting this change:
https://github.com/langchain-ai/langchain/discussions/20383
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
## Description
This PR addresses the following:
**Fixes Issue #25343:**
- Adds additional logic to parse shallowly nested JSON-encoded strings
in tool call arguments, allowing for proper parsing of responses like
that of Llama3.1 and 3.2 with nested schemas.
**Adds Integration Test for Fix:**
- Adds a Ollama specific integration test to ensure the issue is
resolved and to prevent regressions in the future.
**Fixes Failing Integration Tests:**
- Fixes failing integration tests (even prior to changes) caused by
`llama3-groq-tool-use` model. Previously,
tests`test_structured_output_async` and
`test_structured_output_optional_param` failed due to the model not
issuing a tool call in the response. Resolved by switching to
`llama3.1`.
## Issue
Fixes#25343.
## Dependencies
No dependencies.
____
Done in collaboration with @ishaan-upadhyay @mirajismail @ZackSteine.
v0.4 of the Python SDK is already installed via the lock file in CI, but
our current implementation is not compatible with it.
This also addresses an issue introduced in
https://github.com/langchain-ai/langchain/pull/28299. @RyanMagnuson
would you mind explaining the motivation for that change? From what I
can tell the Ollama SDK [does not support
kwargs](6c44bb2729/ollama/_client.py (L286)).
Previously, unsupported kwargs were ignored, but they currently raise
`TypeError`.
Some of LangChain's standard test suite expects `tool_choice` to be
supported, so here we catch it in `bind_tools` so it is ignored and not
passed through to the client.
From what I can tell response using SDK is not deterministic:
```python
import numpy as np
import openai
documents = ["disallowed special token '<|endoftext|>'"]
model = "text-embedding-ada-002"
direct_output_1 = (
openai.OpenAI()
.embeddings.create(input=documents, model=model)
.data[0]
.embedding
)
for i in range(10):
direct_output_2 = (
openai.OpenAI()
.embeddings.create(input=documents, model=model)
.data[0]
.embedding
)
print(f"{i}: {np.isclose(direct_output_1, direct_output_2).all()}")
```
```
0: True
1: True
2: True
3: True
4: False
5: True
6: True
7: True
8: True
9: True
```
See related discussion here:
https://community.openai.com/t/can-text-embedding-ada-002-be-made-deterministic/318054
Found the same result using `"text-embedding-3-small"`.
This change refines the handling of _model_kwargs in POST requests.
Instead of nesting _model_kwargs as a dictionary under the parameters
key, it is now directly unpacked and merged into the request's JSON
payload. This ensures that the model parameters are passed correctly and
avoids unnecessary nesting.E. g.:
```python
import asyncio
from langchain_huggingface.embeddings import HuggingFaceEndpointEmbeddings
embedding_input = ["This input will get multiplied" * 10000]
embeddings = HuggingFaceEndpointEmbeddings(
model="http://127.0.0.1:8081/embed",
model_kwargs={"truncate": True},
)
# Truncated parameters in synchronized methods are handled correctly
embeddings.embed_documents(texts=embedding_input)
# The truncate parameter is not handled correctly in the asynchronous method,
# and 413 Request Entity Too Large is returned.
asyncio.run(embeddings.aembed_documents(texts=embedding_input))
```
Co-authored-by: af su <saf@zjuici.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Description:
* I'm planning to add `Document.id` support to the Chroma VectorStore,
but first I wanted to make sure all the integration tests were passing
first. They weren't. This PR fixes the broken tests.
* I found 2 issues:
* This change (from a year ago, exactly :) ) for supporting multi-modal
embeddings:
https://docs.trychroma.com/deployment/migration#migration-to-0.4.16---november-7,-2023
* This change https://github.com/langchain-ai/langchain/pull/27827 due
to an update in the chroma client.
Also ran `format` and `lint` on the changes.
Note: I am not a member of the Chroma team.
**Description:** The issue concerns the unexpected behavior observed
using the bind_tools method in LangChain's ChatOllama. When tools are
not bound, the llm.stream() method works as expected, returning
incremental chunks of content, which is crucial for real-time
applications such as conversational agents and live feedback systems.
However, when bind_tools([]) is used, the streaming behavior changes,
causing the output to be delivered in full chunks rather than
incrementally. This change negatively impacts the user experience by
breaking the real-time nature of the streaming mechanism.
**Issue:** #26971
---------
Co-authored-by: 4meyDam1e <amey.damle@mail.utoronto.ca>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Last week Anthropic released version 0.39.0 of its python sdk, which
enabled support for Python 3.13. This release deleted a legacy
`client.count_tokens` method, which we currently access during init of
the `Anthropic` LLM. Anthropic has replaced this functionality with the
[client.beta.messages.count_tokens()
API](https://github.com/anthropics/anthropic-sdk-python/pull/726).
To enable support for `anthropic >= 0.39.0` and Python 3.13, here we
drop support for the legacy token counting method, and add support for
the new method via `ChatAnthropic.get_num_tokens_from_messages`.
To fully support the token counting API, we update the signature of
`get_num_tokens_from_message` to accept tools everywhere.
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Now `encode_kwargs` used for both for documents and queries and this
leads to wrong embeddings. E. g.:
```python
model_kwargs = {"device": "cuda", "trust_remote_code": True}
encode_kwargs = {"normalize_embeddings": False, "prompt_name": "s2p_query"}
model = HuggingFaceEmbeddings(
model_name="dunzhang/stella_en_400M_v5",
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs,
)
query_embedding = np.array(
model.embed_query("What are some ways to reduce stress?",)
)
document_embedding = np.array(
model.embed_documents(
[
"There are many effective ways to reduce stress. Some common techniques include deep breathing, meditation, and physical activity. Engaging in hobbies, spending time in nature, and connecting with loved ones can also help alleviate stress. Additionally, setting boundaries, practicing self-care, and learning to say no can prevent stress from building up.",
"Green tea has been consumed for centuries and is known for its potential health benefits. It contains antioxidants that may help protect the body against damage caused by free radicals. Regular consumption of green tea has been associated with improved heart health, enhanced cognitive function, and a reduced risk of certain types of cancer. The polyphenols in green tea may also have anti-inflammatory and weight loss properties.",
]
)
)
print(model._client.similarity(query_embedding, document_embedding)) # output: tensor([[0.8421, 0.3317]], dtype=torch.float64)
```
But from the [model
card](https://huggingface.co/dunzhang/stella_en_400M_v5#sentence-transformers)
expexted like this:
```python
model_kwargs = {"device": "cuda", "trust_remote_code": True}
encode_kwargs = {"normalize_embeddings": False}
query_encode_kwargs = {"normalize_embeddings": False, "prompt_name": "s2p_query"}
model = HuggingFaceEmbeddings(
model_name="dunzhang/stella_en_400M_v5",
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs,
query_encode_kwargs=query_encode_kwargs,
)
query_embedding = np.array(
model.embed_query("What are some ways to reduce stress?", )
)
document_embedding = np.array(
model.embed_documents(
[
"There are many effective ways to reduce stress. Some common techniques include deep breathing, meditation, and physical activity. Engaging in hobbies, spending time in nature, and connecting with loved ones can also help alleviate stress. Additionally, setting boundaries, practicing self-care, and learning to say no can prevent stress from building up.",
"Green tea has been consumed for centuries and is known for its potential health benefits. It contains antioxidants that may help protect the body against damage caused by free radicals. Regular consumption of green tea has been associated with improved heart health, enhanced cognitive function, and a reduced risk of certain types of cancer. The polyphenols in green tea may also have anti-inflammatory and weight loss properties.",
]
)
)
print(model._client.similarity(query_embedding, document_embedding)) # tensor([[0.8398, 0.2990]], dtype=torch.float64)
```
There was a change of attribute name which was "max_batch_size". It's
now "get_max_batch_size" method.
I want to use "create_batches" which is right down below.
Please check this PR link.
reference: https://github.com/chroma-core/chroma/pull/2305
---------
Signed-off-by: Prithvi Kannan <prithvi.kannan@databricks.com>
Co-authored-by: Prithvi Kannan <46332835+prithvikannan@users.noreply.github.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Jun Yamog <jkyamog@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: ono-hiroki <86904208+ono-hiroki@users.noreply.github.com>
Co-authored-by: Dobiichi-Origami <56953648+Dobiichi-Origami@users.noreply.github.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Co-authored-by: Duy Huynh <vndee.huynh@gmail.com>
Co-authored-by: Rashmi Pawar <168514198+raspawar@users.noreply.github.com>
Co-authored-by: sifatj <26035630+sifatj@users.noreply.github.com>
Co-authored-by: Eric Pinzur <2641606+epinzur@users.noreply.github.com>
Co-authored-by: Daniel Vu Dao <danielvdao@users.noreply.github.com>
Co-authored-by: Ofer Mendelevitch <ofermend@gmail.com>
Co-authored-by: Stéphane Philippart <wildagsx@gmail.com>
