mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
f98d7f7494
- **Description:** Support reranking based on cross encoder models
available from HuggingFace.
- Added `CrossEncoder` schema
- Implemented `HuggingFaceCrossEncoder` and
`SagemakerEndpointCrossEncoder`
- Implemented `CrossEncoderReranker` that performs similar functionality
to `CohereRerank`
- Added `cross-encoder-reranker.ipynb` to demonstrate how to use it.
Please let me know if anything else needs to be done to make it visible
on the table-of-contents navigation bar on the left, or on the card list
on [retrievers documentation
page](https://python.langchain.com/docs/integrations/retrievers).
- **Issue:** N/A
- **Dependencies:** None other than the existing ones.
---------
Co-authored-by: Kenny Choe <kchoe@amazon.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
64 lines
1.9 KiB
Python
64 lines
1.9 KiB
Python
from typing import Any, Dict, List, Tuple
|
|
|
|
from langchain_core.pydantic_v1 import BaseModel, Extra, Field
|
|
|
|
from langchain_community.cross_encoders.base import BaseCrossEncoder
|
|
|
|
DEFAULT_MODEL_NAME = "BAAI/bge-reranker-base"
|
|
|
|
|
|
class HuggingFaceCrossEncoder(BaseModel, BaseCrossEncoder):
|
|
"""HuggingFace cross encoder models.
|
|
|
|
Example:
|
|
.. code-block:: python
|
|
|
|
from langchain_community.cross_encoders import HuggingFaceCrossEncoder
|
|
|
|
model_name = "BAAI/bge-reranker-base"
|
|
model_kwargs = {'device': 'cpu'}
|
|
hf = HuggingFaceCrossEncoder(
|
|
model_name=model_name,
|
|
model_kwargs=model_kwargs
|
|
)
|
|
"""
|
|
|
|
client: Any #: :meta private:
|
|
model_name: str = DEFAULT_MODEL_NAME
|
|
"""Model name to use."""
|
|
model_kwargs: Dict[str, Any] = Field(default_factory=dict)
|
|
"""Keyword arguments to pass to the model."""
|
|
|
|
def __init__(self, **kwargs: Any):
|
|
"""Initialize the sentence_transformer."""
|
|
super().__init__(**kwargs)
|
|
try:
|
|
import sentence_transformers
|
|
|
|
except ImportError as exc:
|
|
raise ImportError(
|
|
"Could not import sentence_transformers python package. "
|
|
"Please install it with `pip install sentence-transformers`."
|
|
) from exc
|
|
|
|
self.client = sentence_transformers.CrossEncoder(
|
|
self.model_name, **self.model_kwargs
|
|
)
|
|
|
|
class Config:
|
|
"""Configuration for this pydantic object."""
|
|
|
|
extra = Extra.forbid
|
|
|
|
def score(self, text_pairs: List[Tuple[str, str]]) -> List[float]:
|
|
"""Compute similarity scores using a HuggingFace transformer model.
|
|
|
|
Args:
|
|
text_pairs: The list of text text_pairs to score the similarity.
|
|
|
|
Returns:
|
|
List of scores, one for each pair.
|
|
"""
|
|
scores = self.client.predict(text_pairs)
|
|
return scores
|