mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 13:06:03 +00:00
pdfminer (#1003)
This commit is contained in:
@@ -167,10 +167,48 @@
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "21998d18",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using PDFMiner"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "2f0cc9ff",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import PDFMinerLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "42b531e8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = PDFMinerLoader(\"example_data/layout-parser-paper.pdf\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "010d5cdd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "54fb6b62",
|
||||
"id": "7301c473",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
|
Reference in New Issue
Block a user