mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-02 13:08:57 +00:00
641efcf41c
This PR enables changing the behaviour of huggingface pipeline between
different calls. For example, before this PR there's no way of changing
maximum generation length between different invocations of the chain.
This is desirable in cases, such as when we want to scale the maximum
output size depending on a dynamic prompt size.
Usage example:
```python
from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_id = "gpt2"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
hf = HuggingFacePipeline(pipeline=pipe)
hf("Say foo:", pipeline_kwargs={"max_new_tokens": 42})
```
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
|
||
|---|---|---|
| .. | ||
| langchain_community | ||
| scripts | ||
| tests | ||
| Makefile | ||
| poetry.lock | ||
| pyproject.toml | ||
| README.md | ||
🦜️🧑🤝🧑 LangChain Community
Quick Install
pip install langchain-community
What is it?
LangChain Community contains third-party integrations that implement the base interfaces defined in LangChain Core, making them ready-to-use in any LangChain application.
For full documentation see the API reference.
📕 Releases & Versioning
langchain-community is currently on version 0.0.x
All changes will be accompanied by a patch version increase.
💁 Contributing
As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
For detailed information on how to contribute, see the Contributing Guide.