### About
- **Description:** In the Gitlab utilities used for the Gitlab tool
there is no check to prevent pushing to the main branch, as this is
already done for Github (for example here:
5a2cfb49e0/libs/community/langchain_community/utilities/github.py (L587)).
This PR add this check as already done for Github.
- **Issue:** None
- **Dependencies:** None
**Description:** Add support for Writer chat models
**Issue:** N/A
**Dependencies:** Add `writer-sdk` to optional dependencies.
**Twitter handle:** Please tag `@samjulien` and `@Get_Writer`
**Tests and docs**
- [x] Unit test
- [x] Example notebook in `docs/docs/integrations` directory.
**Lint and test**
- [x] Run `make format`
- [x] Run `make lint`
- [x] Run `make test`
---------
Co-authored-by: Johannes <tolstoy.work@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
**Description:**
- Fix bug in Replicate LLM class, where it was looking for parameter
names in a place where they no longer exist in pydantic 2, resulting in
the "Field required" validation error described in the issue.
- Fix Replicate LLM integration tests to:
- Use active models on Replicate.
- Use the correct model parameter `max_new_tokens` as shown in the
[Replicate
docs](https://replicate.com/docs/guides/language-models/how-to-use#minimum-and-maximum-new-tokens).
- Use callbacks instead of deprecated callback_manager.
**Issue:** #26937
**Dependencies:** n/a
**Twitter handle:** n/a
---------
Signed-off-by: Fayvor Love <fayvor@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
`ChatDatabricks` added support for structured output and JSON mode in
the last release. This PR updates the feature table accordingly.
Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>
Thank you for contributing to LangChain!
**Description:** Added the model parameters to be passed in the OpenAI
Assistant. Enabled it at the `OpenAIAssistantV2Runnable` class.
**Issue:** NA
**Dependencies:** None
**Twitter handle:** luizf0992
Thank you for contributing to LangChain!
- **Description:** Add token_usage and model_name metadata to
ChatZhipuAI stream() and astream() response
- **Issue:** None
- **Dependencies:** None
- **Twitter handle:** None
- [ ] **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: jianfehuang <jianfehuang@tencent.com>
### Description/Issue:
I had problems filtering when setting up a local Milvus db and noticed
that the `filter` option in the `similarity_search` and
`similarity_search_with_score` appeared to do nothing. Instead, the
`expr` option should be used.
The `expr` option is correctly used in the retriever example further
down in the documentation.
The `expr` option seems to be correctly passed on, for example
[here](447c0dd2f0/libs/community/langchain_community/vectorstores/milvus.py (L701))
### Solution:
Update the documentation for the functions mentioned to show intended
behavior.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
**Description:**
- Add the `lora_request` parameter to the VLLM class to support LoRA
model configurations. This enhancement allows users to specify LoRA
requests directly when using VLLM, enabling more flexible and efficient
model customization.
**Issue:**
- No existing issue for `lora_adapter` in VLLM. This PR addresses the
need for configuring LoRA requests within the VLLM framework.
- Reference : [Using LoRA Adapters in
vLLM](https://docs.vllm.ai/en/stable/models/lora.html#using-lora-adapters)
**Example Code :**
Before this change, the `lora_request` parameter was not applied
correctly:
```python
ADAPTER_PATH = "/path/of/lora_adapter"
llm = VLLM(model="Bllossom/llama-3.2-Korean-Bllossom-3B",
max_new_tokens=512,
top_k=2,
top_p=0.90,
temperature=0.1,
vllm_kwargs={
"gpu_memory_utilization":0.5,
"enable_lora":True,
"max_model_len":1024,
}
)
print(llm.invoke(
["...prompt_content..."],
lora_request=LoRARequest("lora_adapter", 1, ADAPTER_PATH)
))
```
**Before Change Output:**
```bash
response was not applied lora_request
```
So, I attempted to apply the lora_adapter to
langchain_community.llms.vllm.VLLM.
**current output:**
```bash
response applied lora_request
```
**Dependencies:**
- None
**Lint and test:**
- All tests and lint checks have passed.
---------
Co-authored-by: Um Changyong <changyong.um@sfa.co.kr>
* **PR title**: "docs: Replaced langchain import with
langchain-nvidia-ai-endpoints in NVIDIA Endpoints Tab"
* **PR message**:
+ **Description:** Replaced the import of `langchain` with
`langchain-nvidia-ai-endpoints` in the NVIDIA Endpoints Tab to resolve
an error caused by the documentation attempting to import the generic
`langchain` module despite the targeted import.
+ **Issue:**
+ **Dependencies:** No additional dependencies introduced; simply
updated the existing import to a more specific module.
+ **Twitter handle:** https://x.com/nawaz0x1
* **Add tests and docs**:
+ **Applicability:** Not applicable in this case, as the change is a fix
to an existing integration rather than the addition of a new one.
+ **Rationale:** No new functionality or integrations are introduced,
only a corrective import change.
* **Lint and test**:
+ **Status:** Completed
+ **Outcome:**
- `make format`: **Passed**
- `make lint`: **Passed**
- `make test`: **Passed**
Thank you for contributing to LangChain!
Add notice of upcoming package consolidation of `langchain-databricks`
into `databricks-langchain`.
<img width="1047" alt="image"
src="https://github.com/user-attachments/assets/18eaa394-4e82-444b-85d5-7812be322674">
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.
Signed-off-by: Prithvi Kannan <prithvi.kannan@databricks.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Updated the documentation to fix some grammar errors
- **Description:** Some language errors exist in the documentation
- **Issue:** the issue # Changed the structure of some sentences
**PR Title**: `docs: fix typo in query analysis documentation`
**Description**: This PR corrects a typo on line 68 in the query
analysis documentation, changing **"pharsings"** to **"phrasings"** for
clarity and accuracy. Only one instance of the typo was fixed in the
last merge, and this PR fixes the second instance.
**Issue**: N/A
**Dependencies**: None
**Additional Notes**: No functional changes were made; this is a
documentation fix only.
Edited various notebooks in the tutorial section to fix:
* Grammatical Errors
* Improve Readability by changing the sentence structure or reducing
repeated words which bears the same meaning
* Edited a code block to follow the PEP 8 Standard
* Added more information in some sentences to make the concept more
clear and reduce ambiguity
---------
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
**Description:**
This PR fixes an issue where non-ASCII characters in Pydantic field
descriptions were being escaped to their Unicode representations when
using `JsonOutputParser`. The change allows non-ASCII characters to be
preserved in the output, which is especially important for multilingual
support and when working with non-English languages.
**Issue:** Fixes#27256
**Example Code:**
```python
from pydantic import BaseModel, Field
from langchain_core.output_parsers import JsonOutputParser
class Article(BaseModel):
title: str = Field(description="科学文章的标题")
output_data_structure = Article
parser = JsonOutputParser(pydantic_object=output_data_structure)
print(parser.get_format_instructions())
```
**Previous Output**:
```... "title": {"description": "\\u79d1\\u5b66\\u6587\\u7ae0\\u7684\\u6807\\u9898", "title": "Title", "type": "string"}} ...```
**Current Output**:
```... "title": {"description": "科学文章的标题", "title": "Title", "type":
"string"}} ...```
**Changes made**:
- Modified `json.dumps()` call in
`langchain_core/output_parsers/json.py` to use `ensure_ascii=False`
- Added a unit test to verify Unicode handling
Co-authored-by: Harsimran-19 <harsimran1869@gmail.com>
**PR Title**: `docs: fix typo in query analysis documentation`
**Description**: This PR corrects a typo on line 68 in the query
analysis documentation, changing **"pharsings"** to **"phrasings"** for
clarity and accuracy.
**Issue**: N/A
**Dependencies**: None
**Additional Notes**: No functional changes were made; this is a
documentation fix only.
**Description:**
When annotating a function with the @tool decorator, the symbol should
have type BaseTool. The previous type annotations did not convey that to
type checkers. This patch creates 4 overloads for the tool function for
the 4 different use cases.
1. @tool decorator with no arguments
2. @tool decorator with only keyword arguments
3. @tool decorator with a name argument (and possibly keyword arguments)
4. Invoking tool as function with a name and runnable positional
arguments
The main function is updated to match the overloads. The changes are
100% backwards compatible (all existing calls should continue to work,
just with better type annotations).
**Twitter handle:** @nvachhar
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
**Description:** Fixes None addition issues when an empty value is
passed on
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
**Description:**
The `aiohttp.ClientSession` is closed at the end of the with statement,
which causes an error during a second call.
The implemented fix is to define the session directly within the with
block, exactly like in the textembed code:
c6350d636e/libs/community/langchain_community/embeddings/textembed.py (L335-L346)
**Issue:** Fix#26932
Co-authored-by: ccurme <chester.curme@gmail.com>
**Description:** We improve the performance of the InMemoryVectorStore.
**Isue:** Originally, similarity was computed document by document:
```
for doc in self.store.values():
vector = doc["vector"]
similarity = float(cosine_similarity([embedding], [vector]).item(0))
```
This is inefficient and does not make use of numpy vectorization.
This PR computes the similarity in one vectorized go:
```
docs = list(self.store.values())
similarity = cosine_similarity([embedding], [doc["vector"] for doc in docs])
```
**Dependencies:** None
**Twitter handle:** @b12_consulting, @Vincent_Min
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
