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>
Thank you for contributing to LangChain!
- [X] **PR title**: DOC: Added notes in ipynb file to advice user to
upgrade package langchain_openai.
- [X]
Added notes from the issue report: to advise the user to upgrade
langchain_openai
Issue:
https://github.com/langchain-ai/langchain/issues/26616
- [ ] **Add tests and docs**:
- [ ] **Lint and test**:
- [ ]
---------
Co-authored-by: Libby Lin <libbylin@Libbys-MacBook-Pro.local>
Co-authored-by: Erick Friis <erick@langchain.dev>
**Description:** Returns the document id along with the Vector Search
results
**Issue:** Fixes https://github.com/langchain-ai/langchain/issues/26860
for CouchbaseVectorStore
- [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.
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified.
Co-authored-by: Erick Friis <erick@langchain.dev>
This PR adds support to the how-to documentation for using AWS Bedrock
and Sagemaker Endpoints.
Because AWS services above dont presently use API keys to access LLMs
I've amended more of the source code than would normally be expected.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Reopened as a personal repo outside the organization.
## Description
- Naver HyperCLOVA X community package
- Add chat model & embeddings
- Add unit test & integration test
- Add chat model & embeddings docs
- I changed partner
package(https://github.com/langchain-ai/langchain/pull/24252) to
community package on this PR
- Could this
embeddings(https://github.com/langchain-ai/langchain/pull/21890) be
deprecated? We are trying to replace it with embedding
model(**ClovaXEmbeddings**) in this PR.
Twitter handle: None. (if needed, contact with
joonha.jeon@navercorp.com)
---
you can check our previous discussion below:
> one question on namespaces - would it make sense to have these in
.clova namespaces instead of .naver?
I would like to keep it as is, unless it is essential to unify the
package name.
(ClovaX is a branding for the model, and I plan to add other models and
components. They need to be managed as separate classes.)
> also, could you clarify the difference between ClovaEmbeddings and
ClovaXEmbeddings?
There are 3 models that are being serviced by embedding, and all are
supported in the current PR. In addition, all the functionality of CLOVA
Studio that serves actual models, such as distinguishing between test
apps and service apps, is supported. The existing PR does not support
this content because it is hard-coded.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Vadym Barda <vadym@langchain.dev>
## Description
I encountered an error while using the` gemma-2-2b-it model` with the
`HuggingFacePipeline` class and have implemented a fix to resolve this
issue.
### What is Problem
```python
model_id="google/gemma-2-2b-it"
gemma_2_model = AutoModelForCausalLM.from_pretrained(model_id)
gemma_2_tokenizer = AutoTokenizer.from_pretrained(model_id)
gen = pipeline(
task='text-generation',
model=gemma_2_model,
tokenizer=gemma_2_tokenizer,
max_new_tokens=1024,
device=0 if torch.cuda.is_available() else -1,
temperature=.5,
top_p=0.7,
repetition_penalty=1.1,
do_sample=True,
)
llm = HuggingFacePipeline(pipeline=gen)
for chunk in llm.stream("Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World."):
print(chunk, end="", flush=True)
```
This code outputs the following error message:
```
/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py:1258: UserWarning: Using the model-agnostic default `max_length` (=20) to control the generation length. We recommend setting `max_new_tokens` to control the maximum length of the generation.
warnings.warn(
Exception in thread Thread-19 (generate):
Traceback (most recent call last):
File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 1874, in generate
self._validate_generated_length(generation_config, input_ids_length, has_default_max_length)
File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 1266, in _validate_generated_length
raise ValueError(
ValueError: Input length of input_ids is 31, but `max_length` is set to 20. This can lead to unexpected behavior. You should consider increasing `max_length` or, better yet, setting `max_new_tokens`.
```
In addition, the following error occurs when the number of tokens is
reduced.
```python
for chunk in llm.stream("Hello World"):
print(chunk, end="", flush=True)
```
```
/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py:1258: UserWarning: Using the model-agnostic default `max_length` (=20) to control the generation length. We recommend setting `max_new_tokens` to control the maximum length of the generation.
warnings.warn(
/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py:1885: UserWarning: You are calling .generate() with the `input_ids` being on a device type different than your model's device. `input_ids` is on cpu, whereas the model is on cuda. You may experience unexpected behaviors or slower generation. Please make sure that you have put `input_ids` to the correct device by calling for example input_ids = input_ids.to('cuda') before running `.generate()`.
warnings.warn(
Exception in thread Thread-20 (generate):
Traceback (most recent call last):
File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 2024, in generate
result = self._sample(
File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 2982, in _sample
outputs = self(**model_inputs, return_dict=True)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/models/gemma2/modeling_gemma2.py", line 994, in forward
outputs = self.model(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/models/gemma2/modeling_gemma2.py", line 803, in forward
inputs_embeds = self.embed_tokens(input_ids)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/sparse.py", line 164, in forward
return F.embedding(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py", line 2267, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument index in method wrapper_CUDA__index_select)
```
On the other hand, in the case of invoke, the output is normal:
```
llm.invoke("Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World.")
```
```
'Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World. Hello World.\n\nThis is a simple program that prints the phrase "Hello World" to the console. \n\n**Here\'s how it works:**\n\n* **`print("Hello World")`**: This line of code uses the `print()` function, which is a built-in function in most programming languages (like Python). The `print()` function takes whatever you put inside its parentheses and displays it on the screen.\n* **`"Hello World"`**: The text within the double quotes (`"`) is called a string. It represents the message we want to print.\n\n\nLet me know if you\'d like to explore other programming concepts or see more examples! \n'
```
### Problem Analysis
- Apparently, I put kwargs in while generating pipelines and it applied
to `invoke()`, but it's not applied in the `stream()`.
- When using the stream, `inputs = self.pipeline.tokenizer (prompt,
return_tensors = "pt")` enters cpu.
- This can crash when the model is in gpu.
### Solution
Just use `self.pipeline` instead of `self.pipeline.model.generate`.
- **Original Code**
```python
stopping_criteria = StoppingCriteriaList([StopOnTokens()])
inputs = self.pipeline.tokenizer(prompt, return_tensors="pt")
streamer = TextIteratorStreamer(
self.pipeline.tokenizer,
timeout=60.0,
skip_prompt=skip_prompt,
skip_special_tokens=True,
)
generation_kwargs = dict(
inputs,
streamer=streamer,
stopping_criteria=stopping_criteria,
**pipeline_kwargs,
)
t1 = Thread(target=self.pipeline.model.generate, kwargs=generation_kwargs)
t1.start()
```
- **Updated Code**
```python
stopping_criteria = StoppingCriteriaList([StopOnTokens()])
streamer = TextIteratorStreamer(
self.pipeline.tokenizer,
timeout=60.0,
skip_prompt=skip_prompt,
skip_special_tokens=True,
)
generation_kwargs = dict(
text_inputs= prompt,
streamer=streamer,
stopping_criteria=stopping_criteria,
**pipeline_kwargs,
)
t1 = Thread(target=self.pipeline, kwargs=generation_kwargs)
t1.start()
```
By using the `pipeline` directly, the `kwargs` of the pipeline are
applied, and there is no need to consider the `device` of the `tensor`
made with the `tokenizer`.
> According to the change to use `pipeline`, it was modified to put
`text_inputs=prompts` directly into `generation_kwargs`.
## Issue
None
## Dependencies
None
## Twitter handle
None
---------
Co-authored-by: Vadym Barda <vadym@langchain.dev>
`strightforward` => `straightforward`
`adavanced` => `advanced`
`There a few challenges` => `There are a few challenges`
Documentation Correction:
*
[`docs/docs/concepts/structured_output.mdx`]:
Corrected several typos in the sentence directing users to the API
reference.
