Spaces:
Runtime error
Runtime error
"""Wrapper around HuggingFace embedding models.""" | |
from typing import Any, List | |
from pydantic import BaseModel, Extra | |
from langchain.embeddings.base import Embeddings | |
DEFAULT_MODEL_NAME = "sentence-transformers/all-mpnet-base-v2" | |
DEFAULT_INSTRUCT_MODEL = "hkunlp/instructor-large" | |
DEFAULT_EMBED_INSTRUCTION = "Represent the document for retrieval: " | |
DEFAULT_QUERY_INSTRUCTION = ( | |
"Represent the question for retrieving supporting documents: " | |
) | |
class HuggingFaceEmbeddings(BaseModel, Embeddings): | |
"""Wrapper around sentence_transformers embedding models. | |
To use, you should have the ``sentence_transformers`` python package installed. | |
Example: | |
.. code-block:: python | |
from langchain.embeddings import HuggingFaceEmbeddings | |
model_name = "sentence-transformers/all-mpnet-base-v2" | |
hf = HuggingFaceEmbeddings(model_name=model_name) | |
""" | |
client: Any #: :meta private: | |
model_name: str = DEFAULT_MODEL_NAME | |
"""Model name to use.""" | |
def __init__(self, **kwargs: Any): | |
"""Initialize the sentence_transformer.""" | |
super().__init__(**kwargs) | |
try: | |
import sentence_transformers | |
self.client = sentence_transformers.SentenceTransformer(self.model_name) | |
except ImportError: | |
raise ValueError( | |
"Could not import sentence_transformers python package. " | |
"Please install it with `pip install sentence_transformers`." | |
) | |
class Config: | |
"""Configuration for this pydantic object.""" | |
extra = Extra.forbid | |
def embed_documents(self, texts: List[str]) -> List[List[float]]: | |
"""Compute doc embeddings using a HuggingFace transformer model. | |
Args: | |
texts: The list of texts to embed. | |
Returns: | |
List of embeddings, one for each text. | |
""" | |
texts = list(map(lambda x: x.replace("\n", " "), texts)) | |
embeddings = self.client.encode(texts) | |
return embeddings.tolist() | |
def embed_query(self, text: str) -> List[float]: | |
"""Compute query embeddings using a HuggingFace transformer model. | |
Args: | |
text: The text to embed. | |
Returns: | |
Embeddings for the text. | |
""" | |
text = text.replace("\n", " ") | |
embedding = self.client.encode(text) | |
return embedding.tolist() | |
class HuggingFaceInstructEmbeddings(BaseModel, Embeddings): | |
"""Wrapper around sentence_transformers embedding models. | |
To use, you should have the ``sentence_transformers`` | |
and ``InstructorEmbedding`` python package installed. | |
Example: | |
.. code-block:: python | |
from langchain.embeddings import HuggingFaceInstructEmbeddings | |
model_name = "hkunlp/instructor-large" | |
hf = HuggingFaceInstructEmbeddings(model_name=model_name) | |
""" | |
client: Any #: :meta private: | |
model_name: str = DEFAULT_INSTRUCT_MODEL | |
"""Model name to use.""" | |
embed_instruction: str = DEFAULT_EMBED_INSTRUCTION | |
"""Instruction to use for embedding documents.""" | |
query_instruction: str = DEFAULT_QUERY_INSTRUCTION | |
"""Instruction to use for embedding query.""" | |
def __init__(self, **kwargs: Any): | |
"""Initialize the sentence_transformer.""" | |
super().__init__(**kwargs) | |
try: | |
from InstructorEmbedding import INSTRUCTOR | |
self.client = INSTRUCTOR(self.model_name) | |
except ImportError as e: | |
raise ValueError("Dependencies for InstructorEmbedding not found.") from e | |
class Config: | |
"""Configuration for this pydantic object.""" | |
extra = Extra.forbid | |
def embed_documents(self, texts: List[str]) -> List[List[float]]: | |
"""Compute doc embeddings using a HuggingFace instruct model. | |
Args: | |
texts: The list of texts to embed. | |
Returns: | |
List of embeddings, one for each text. | |
""" | |
instruction_pairs = [[self.embed_instruction, text] for text in texts] | |
embeddings = self.client.encode(instruction_pairs) | |
return embeddings.tolist() | |
def embed_query(self, text: str) -> List[float]: | |
"""Compute query embeddings using a HuggingFace instruct model. | |
Args: | |
text: The text to embed. | |
Returns: | |
Embeddings for the text. | |
""" | |
instruction_pair = [self.query_instruction, text] | |
embedding = self.client.encode([instruction_pair])[0] | |
return embedding.tolist() | |