**Description:**
`langchain_huggingface` has a very large installation size of around 600
MB (on a Mac with Python 3.11). This is due to its dependency on
`sentence-transformers`, which in turn depends on `torch`, which is 320
MB all by itself. Similarly, the depedency on `transformers` adds
another set of heavy dependencies. With those dependencies removed, the
installation of `langchain_huggingface` only takes up ~26 MB. This is
only 5 % of the full installation!
These libraries are not necessary to use `langchain_huggingface`'s API
wrapper classes, only for local inferences/embeddings. All import
statements for those two libraries already have import guards in place
(try/catch with a helpful "please install x" message).
This PR therefore moves those two libraries to an optional dependency
group `full`. So a `pip install langchain_huggingface` will only install
the lightweight version, and a `pip install
"langchain_huggingface[full]"` will install all dependencies.
I know this may break existing code, because `sentence-transformers` and
`transformers` are now no longer installed by default. Given that users
will see helpful error messages when that happens, and the major impact
of this small change, I hope that you will still consider this PR.
**Dependencies:** No new dependencies, but new optional grouping.
Hi there, I'm Célina from 🤗,
This PR introduces support for Hugging Face's serverless Inference
Providers (documentation
[here](https://huggingface.co/docs/inference-providers/index)), allowing
users to specify different providers for chat completion and text
generation tasks.
This PR also removes the usage of `InferenceClient.post()` method in
`HuggingFaceEndpoint`, in favor of the task-specific `text_generation`
method. `InferenceClient.post()` is deprecated and will be removed in
`huggingface_hub v0.31.0`.
---
## Changes made
- bumped the minimum required version of the `huggingface-hub` package
to ensure compatibility with the latest API usage.
- added a `provider` field to `HuggingFaceEndpoint`, enabling users to
select the inference provider (e.g., 'cerebras', 'together',
'fireworks-ai'). Defaults to `hf-inference` (HF Inference API).
- replaced the deprecated `InferenceClient.post()` call in
`HuggingFaceEndpoint` with the task-specific `text_generation` method
for future-proofing, `post()` will be removed in huggingface-hub
v0.31.0.
- updated the `ChatHuggingFace` component:
- added async and streaming support.
- added support for tool calling.
- exposed underlying chat completion parameters for more granular
control.
- Added integration tests for `ChatHuggingFace` and updated the
corresponding unit tests.
✅ All changes are backward compatible.
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
Follow up to https://github.com/langchain-ai/langsmith-sdk/pull/1696,
I've bumped the `langsmith` version where applicable in `uv.lock`.
Type checking problems here because deps have been updated in
`pyproject.toml` and `uv lock` hasn't been run - we should enforce that
in the future - goes with the other dependabot todos :).
Hi there, This is a complementary PR to #30733.
This PR introduces support for Hugging Face's serverless Inference
Providers (documentation
[here](https://huggingface.co/docs/inference-providers/index)), allowing
users to specify different providers
This PR also removes the usage of `InferenceClient.post()` method in
`HuggingFaceEndpointEmbeddings`, in favor of the task-specific
`feature_extraction` method. `InferenceClient.post()` is deprecated and
will be removed in `huggingface_hub` v0.31.0.
## Changes made
- bumped the minimum required version of the `huggingface_hub` package
to ensure compatibility with the latest API usage.
- added a provider field to `HuggingFaceEndpointEmbeddings`, enabling
users to select the inference provider.
- replaced the deprecated `InferenceClient.post()` call in
`HuggingFaceEndpointEmbeddings` with the task-specific
`feature_extraction` method for future-proofing, `post()` will be
removed in `huggingface-hub` v0.31.0.
✅ All changes are backward compatible.
---------
Co-authored-by: Lucain <lucainp@gmail.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Generally, this PR is CI performance focused + aims to clean up some
dependencies at the same time.
1. Unpins upper bounds for `numpy` in all `pyproject.toml` files where
`numpy` is specified
2. Requires `numpy >= 2.1.0` for Python 3.13 and `numpy > v1.26.0` for
Python 3.12, plus a `numpy` min version bump for `chroma`
3. Speeds up CI by minutes - linting on Python 3.13, installing `numpy <
2.1.0` was taking [~3
minutes](https://github.com/langchain-ai/langchain/actions/runs/14316342925/job/40123305868?pr=30713),
now the entire env setup takes a few seconds
4. Deleted the `numpy` test dependency from partners where that was not
used, specifically `huggingface`, `voyageai`, `xai`, and `nomic`.
It's a bit unfortunate that `langchain-community` depends on `numpy`, we
might want to try to fix that in the future...
Closes https://github.com/langchain-ai/langchain/issues/26026
Fixes https://github.com/langchain-ai/langchain/issues/30555
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"},
)
```
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}))
```
**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>
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>
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)
```
## 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>
- [ ] **Description:**
- pass the device_map into model_kwargs
- removing the unused device_map variable in the hf_pipeline function
call
- [ ] **Issue:** issue #13128
When using the from_model_id function to load a Hugging Face model for
text generation across multiple GPUs, the model defaults to loading on
the CPU despite multiple GPUs being available using the expected format
``` python
llm = HuggingFacePipeline.from_model_id(
model_id="model-id",
task="text-generation",
device_map="auto",
)
```
Currently, to enable multiple GPU , we have to pass in variable in this
format instead
``` python
llm = HuggingFacePipeline.from_model_id(
model_id="model-id",
task="text-generation",
device=None,
model_kwargs={
"device_map": "auto",
}
)
```
This issue arises due to improper handling of the device and device_map
parameters.
- [ ] **Explanation:**
1. In from_model_id, the model is created using model_kwargs and passed
as the model variable of the pipeline function. So at this moment, to
load the model with multiple GPUs, "device_map" needs to be set to
"auto" within model_kwargs. Otherwise, the model defaults to loading on
the CPU.
2. The device_map variable in from_model_id is not utilized correctly.
In the pipeline function's source code of tnansformer:
- The device_map variable is stored in the model_kwargs dictionary
(lines 867-878 of transformers/src/transformers/pipelines/\__init__.py).
```python
if device_map is not None:
......
model_kwargs["device_map"] = device_map
```
- The model is constructed with model_kwargs containing the device_map
value ONLY IF it is a string (lines 893-903 of
transformers/src/transformers/pipelines/\__init__.py).
```python
if isinstance(model, str) or framework is None:
model_classes = {"tf": targeted_task["tf"], "pt": targeted_task["pt"]}
framework, model = infer_framework_load_model( ... , **model_kwargs, )
```
- Consequently, since a model object is already passed to the pipeline
function, the device_map variable from from_model_id is never used.
3. The device_map variable in from_model_id not only appears unused but
also causes errors. Without explicitly setting device=None, attempting
to load the model on multiple GPUs may result in the following error:
```
Device has 2 GPUs available. Provide device={deviceId} to
`from_model_id` to use available GPUs for execution. deviceId is -1
(default) for CPU and can be a positive integer associated with CUDA
device id.
Traceback (most recent call last):
File "foo.py", line 15, in <module>
llm = HuggingFacePipeline.from_model_id(
File
"foo\site-packages\langchain_huggingface\llms\huggingface_pipeline.py",
line 217, in from_model_id
pipeline = hf_pipeline(
File "foo\lib\site-packages\transformers\pipelines\__init__.py", line
1108, in pipeline
return pipeline_class(model=model, framework=framework, task=task,
**kwargs)
File "foo\lib\site-packages\transformers\pipelines\text_generation.py",
line 96, in __init__
super().__init__(*args, **kwargs)
File "foo\lib\site-packages\transformers\pipelines\base.py", line 835,
in __init__
raise ValueError(
ValueError: The model has been loaded with `accelerate` and therefore
cannot be moved to a specific device. Please discard the `device`
argument when creating your pipeline object.
```
This error occurs because, in from_model_id, the default values in from_model_id for device and device_map are -1 and None, respectively. It would passes the statement (`device_map is not None and device < 0`) and keep the device as -1 so the pipeline function later raises an error when trying to move a GPU-loaded model back to the CPU.
19eb82e68b/libs/community/langchain_community/llms/huggingface_pipeline.py (L204-L213)
If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: vbarda <vadym@langchain.dev>
