github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-05 20:58:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: fix pdf docs hierarchy and formatting (#4593)

Browse Source 
# Fix pdf loader docs page


![image](https://github.com/hwchase17/langchain/assets/707699/4a11f379-00ed-4f7a-9870-71f74e0cadc6)

Using h1's messes with hierarchy, this fixes that, and moves the
PyPDFium2 loader out of the middle of PDFMiner docs
This commit is contained in:
Tim Asp 2023-05-12 12:03:01 -07:00 committed by GitHub
parent 36f9e9a0ba
commit ed0d557ede
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 44 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
docs/modules/indexes/document_loaders/examples/pdf.ipynb
View File

@ -335,56 +335,12 @@
"print(data)" "print(data)"
] ]
}, },
{
"cell_type": "markdown",
"id": "05187b33",
"metadata": {},
"source": []
},
{
"cell_type": "markdown",
"id": "21998d18",
"metadata": {},
"source": [
"## Using PDFMiner"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "2f0cc9ff",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import PDFMinerLoader"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "42b531e8",
"metadata": {},
"outputs": [],
"source": [
"loader = PDFMinerLoader(\"example_data/layout-parser-paper.pdf\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "483720b5",
"metadata": {},
"outputs": [],
"source": [
"data = loader.load()"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "96351714", "id": "96351714",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Using PyPDFium2" "## Using PyPDFium2"
] ]
}, },
{ {
@ -407,6 +363,48 @@
"loader = PyPDFium2Loader(\"example_data/layout-parser-paper.pdf\")" "loader = PyPDFium2Loader(\"example_data/layout-parser-paper.pdf\")"
] ]
}, },
{
"cell_type": "code",
"execution_count": 9,
"outputs": [],
"source": [
"data = loader.load()"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "markdown",
"source": [
"## Using PDFMiner"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": 7,
"outputs": [],
"source": [
"from langchain.document_loaders import PDFMinerLoader"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": 8,
"outputs": [],
"source": [
"loader = PDFMinerLoader(\"example_data/layout-parser-paper.pdf\")"
],
"metadata": {
"collapsed": false
}
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 4,
@ -422,7 +420,7 @@
"id": "c90a5fe8", "id": "c90a5fe8",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Using PDFMiner to generate HTML text" "### Using PDFMiner to generate HTML text"
] ]
}, },
{ {