mirror of
https://github.com/hwchase17/langchain
synced 2024-11-02 09:40:22 +00:00
af8c5c185b
Adds: * methods `aload()` and `alazy_load()` to interface `BaseLoader` * implementation for class `MergedDataLoader ` * support for class `BaseLoader` in async function `aindex()` with unit tests Note: this is compatible with existing `aload()` methods that some loaders already had. **Twitter handle:** @cbornet_ --------- Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
from typing import AsyncIterator, Iterator, List
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
|
|
|
|
class MergedDataLoader(BaseLoader):
|
|
"""Merge documents from a list of loaders"""
|
|
|
|
def __init__(self, loaders: List):
|
|
"""Initialize with a list of loaders"""
|
|
self.loaders = loaders
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
"""Lazy load docs from each individual loader."""
|
|
for loader in self.loaders:
|
|
# Check if lazy_load is implemented
|
|
try:
|
|
data = loader.lazy_load()
|
|
except NotImplementedError:
|
|
data = loader.load()
|
|
for document in data:
|
|
yield document
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load docs."""
|
|
return list(self.lazy_load())
|
|
|
|
async def alazy_load(self) -> AsyncIterator[Document]:
|
|
"""Lazy load docs from each individual loader."""
|
|
for loader in self.loaders:
|
|
async for document in loader.alazy_load():
|
|
yield document
|