mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-06 21:43:44 +00:00
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)
Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
This commit is contained in:
@@ -0,0 +1,113 @@
|
||||
import importlib.util
|
||||
from typing import Any, Dict, List
|
||||
|
||||
from langchain_core.embeddings import Embeddings
|
||||
from langchain_core.pydantic_v1 import BaseModel, Extra, root_validator
|
||||
|
||||
|
||||
class SpacyEmbeddings(BaseModel, Embeddings):
|
||||
"""Embeddings by SpaCy models.
|
||||
|
||||
It only supports the 'en_core_web_sm' model.
|
||||
|
||||
Attributes:
|
||||
nlp (Any): The Spacy model loaded into memory.
|
||||
|
||||
Methods:
|
||||
embed_documents(texts: List[str]) -> List[List[float]]:
|
||||
Generates embeddings for a list of documents.
|
||||
embed_query(text: str) -> List[float]:
|
||||
Generates an embedding for a single piece of text.
|
||||
"""
|
||||
|
||||
nlp: Any # The Spacy model loaded into memory
|
||||
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
extra = Extra.forbid # Forbid extra attributes during model initialization
|
||||
|
||||
@root_validator(pre=True)
|
||||
def validate_environment(cls, values: Dict) -> Dict:
|
||||
"""
|
||||
Validates that the Spacy package and the 'en_core_web_sm' model are installed.
|
||||
|
||||
Args:
|
||||
values (Dict): The values provided to the class constructor.
|
||||
|
||||
Returns:
|
||||
The validated values.
|
||||
|
||||
Raises:
|
||||
ValueError: If the Spacy package or the 'en_core_web_sm'
|
||||
model are not installed.
|
||||
"""
|
||||
# Check if the Spacy package is installed
|
||||
if importlib.util.find_spec("spacy") is None:
|
||||
raise ValueError(
|
||||
"Spacy package not found. "
|
||||
"Please install it with `pip install spacy`."
|
||||
)
|
||||
try:
|
||||
# Try to load the 'en_core_web_sm' Spacy model
|
||||
import spacy
|
||||
|
||||
values["nlp"] = spacy.load("en_core_web_sm")
|
||||
except OSError:
|
||||
# If the model is not found, raise a ValueError
|
||||
raise ValueError(
|
||||
"Spacy model 'en_core_web_sm' not found. "
|
||||
"Please install it with"
|
||||
" `python -m spacy download en_core_web_sm`."
|
||||
)
|
||||
return values # Return the validated values
|
||||
|
||||
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
||||
"""
|
||||
Generates embeddings for a list of documents.
|
||||
|
||||
Args:
|
||||
texts (List[str]): The documents to generate embeddings for.
|
||||
|
||||
Returns:
|
||||
A list of embeddings, one for each document.
|
||||
"""
|
||||
return [self.nlp(text).vector.tolist() for text in texts]
|
||||
|
||||
def embed_query(self, text: str) -> List[float]:
|
||||
"""
|
||||
Generates an embedding for a single piece of text.
|
||||
|
||||
Args:
|
||||
text (str): The text to generate an embedding for.
|
||||
|
||||
Returns:
|
||||
The embedding for the text.
|
||||
"""
|
||||
return self.nlp(text).vector.tolist()
|
||||
|
||||
async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
|
||||
"""
|
||||
Asynchronously generates embeddings for a list of documents.
|
||||
This method is not implemented and raises a NotImplementedError.
|
||||
|
||||
Args:
|
||||
texts (List[str]): The documents to generate embeddings for.
|
||||
|
||||
Raises:
|
||||
NotImplementedError: This method is not implemented.
|
||||
"""
|
||||
raise NotImplementedError("Asynchronous embedding generation is not supported.")
|
||||
|
||||
async def aembed_query(self, text: str) -> List[float]:
|
||||
"""
|
||||
Asynchronously generates an embedding for a single piece of text.
|
||||
This method is not implemented and raises a NotImplementedError.
|
||||
|
||||
Args:
|
||||
text (str): The text to generate an embedding for.
|
||||
|
||||
Raises:
|
||||
NotImplementedError: This method is not implemented.
|
||||
"""
|
||||
raise NotImplementedError("Asynchronous embedding generation is not supported.")
|
Reference in New Issue
Block a user