langchain[minor],community[minor]: Add async methods in BaseLoader (#16634)

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>
This commit is contained in:
Christophe Bornet
2024-01-31 20:08:11 +01:00
committed by GitHub
parent c37ca45825
commit af8c5c185b
5 changed files with 71 additions and 52 deletions

View File

@@ -1,4 +1,4 @@
from typing import Iterator, List
from typing import AsyncIterator, Iterator, List
from langchain_core.documents import Document
@@ -26,3 +26,9 @@ class MergedDataLoader(BaseLoader):
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