directory loader improvements (#1162)

This commit is contained in:
Harrison Chase
2023-02-19 20:47:08 -08:00
committed by GitHub
parent 05a05bcb04
commit 65cc81c479
2 changed files with 100 additions and 10 deletions

View File

@@ -6,7 +6,7 @@
"metadata": {},
"source": [
"# Directory Loader\n",
"This covers how to use the DirectoryLoader to load all documents in a directory. Under the hood, this uses the [UnstructuredLoader](./unstructured_file.ipynb)"
"This covers how to use the DirectoryLoader to load all documents in a directory. Under the hood, by default this uses the [UnstructuredLoader](./unstructured_file.ipynb)"
]
},
{
@@ -29,7 +29,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 2,
"id": "891fe56f",
"metadata": {},
"outputs": [],
@@ -39,7 +39,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 3,
"id": "addfe9cf",
"metadata": {},
"outputs": [],
@@ -49,7 +49,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 4,
"id": "b042086d",
"metadata": {},
"outputs": [
@@ -59,7 +59,67 @@
"1"
]
},
"execution_count": 9,
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(docs)"
]
},
{
"cell_type": "markdown",
"id": "c5652850",
"metadata": {},
"source": [
"## Change loader class\n",
"By default this uses the UnstructuredLoader class. However, you can change up the type of loader pretty easily."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "81c92da3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "ab38ee36",
"metadata": {},
"outputs": [],
"source": [
"loader = DirectoryLoader('../', glob=\"**/*.md\", loader_cls=TextLoader)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "25c8740f",
"metadata": {},
"outputs": [],
"source": [
"docs = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "38337763",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -71,7 +131,7 @@
{
"cell_type": "code",
"execution_count": null,
"id": "cbc8256b",
"id": "984c8429",
"metadata": {},
"outputs": [],
"source": []