github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-18 12:58:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix notebooks

Browse Source
This commit is contained in:
Philippe Prados 2025-04-15 11:50:52 +02:00
parent ada3ba2567
commit 028069ca42
2 changed files with 204 additions and 202 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

400
docs/docs/integrations/document_loaders/pdfplumber.ipynb
View File

@ -41,18 +41,18 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:32:31.030959Z", "end_time": "2025-04-15T09:32:31.030959Z",
"start_time": "2025-04-15T09:32:31.027427Z" "start_time": "2025-04-15T09:32:31.027427Z"
} }
}, },
"outputs": [],
"source": [ "source": [
"# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n", "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
"# os.environ[\"LANGSMITH_TRACING\"] = \"true\"" "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
], ]
"outputs": [],
"execution_count": 1
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -65,13 +65,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:32:34.953716Z", "end_time": "2025-04-15T09:32:34.953716Z",
"start_time": "2025-04-15T09:32:32.674410Z" "start_time": "2025-04-15T09:32:32.674410Z"
} }
}, },
"source": "%pip install -qU langchain_community pdfplumber",
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -82,7 +82,9 @@
] ]
} }
], ],
"execution_count": 2 "source": [
"%pip install -qU langchain_community pdfplumber"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -95,20 +97,20 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:32:55.327932Z", "end_time": "2025-04-15T09:32:55.327932Z",
"start_time": "2025-04-15T09:32:54.354899Z" "start_time": "2025-04-15T09:32:54.354899Z"
} }
}, },
"outputs": [],
"source": [ "source": [
"from langchain_community.document_loaders import PDFPlumberLoader\n", "from langchain_community.document_loaders import PDFPlumberLoader\n",
"\n", "\n",
"file_path = \"./example_data/layout-parser-paper.pdf\"\n", "file_path = \"./example_data/layout-parser-paper.pdf\"\n",
"loader = PDFPlumberLoader(file_path, metadata_format=\"standard\")" "loader = PDFPlumberLoader(file_path, metadata_format=\"standard\")"
], ]
"outputs": [],
"execution_count": 3
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -119,16 +121,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:32:59.036774Z", "end_time": "2025-04-15T09:32:59.036774Z",
"start_time": "2025-04-15T09:32:57.033035Z" "start_time": "2025-04-15T09:32:57.033035Z"
} }
}, },
"source": [
"docs = loader.load()\n",
"docs[0]"
],
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
@ -163,21 +162,20 @@
"output_type": "execute_result" "output_type": "execute_result"
} }
], ],
"execution_count": 4 "source": [
"docs = loader.load()\n",
"docs[0]"
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:32:59.047149Z", "end_time": "2025-04-15T09:32:59.047149Z",
"start_time": "2025-04-15T09:32:59.043526Z" "start_time": "2025-04-15T09:32:59.043526Z"
} }
}, },
"source": [
"import pprint\n",
"\n",
"pprint.pp(docs[0].metadata)"
],
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -201,7 +199,11 @@
] ]
} }
], ],
"execution_count": 5 "source": [
"import pprint\n",
"\n",
"pprint.pp(docs[0].metadata)"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -212,23 +214,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:33:03.931290Z", "end_time": "2025-04-15T09:33:03.931290Z",
"start_time": "2025-04-15T09:33:02.092848Z" "start_time": "2025-04-15T09:33:02.092848Z"
} }
}, },
"source": [
"pages = []\n",
"for doc in loader.lazy_load():\n",
" pages.append(doc)\n",
" if len(pages) >= 10:\n",
" # do some paged operation, e.g.\n",
" # index.upsert(page)\n",
"\n",
" pages = []\n",
"len(pages)"
],
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
@ -263,20 +255,27 @@
"output_type": "execute_result" "output_type": "execute_result"
} }
], ],
"execution_count": 6 "source": [
"pages = []\n",
"for doc in loader.lazy_load():\n",
" pages.append(doc)\n",
" if len(pages) >= 10:\n",
" # do some paged operation, e.g.\n",
" # index.upsert(page)\n",
"\n",
" pages = []\n",
"len(pages)"
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:33:05.116002Z", "end_time": "2025-04-15T09:33:05.116002Z",
"start_time": "2025-04-15T09:33:05.102235Z" "start_time": "2025-04-15T09:33:05.102235Z"
} }
}, },
"source": [
"print(pages[0].page_content[:100])\n",
"pprint.pp(pages[0].metadata)"
],
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -302,7 +301,10 @@
] ]
} }
], ],
"execution_count": 7 "source": [
"print(pages[0].page_content[:100])\n",
"pprint.pp(pages[0].metadata)"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -347,22 +349,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:33:13.625065Z", "end_time": "2025-04-15T09:33:13.625065Z",
"start_time": "2025-04-15T09:33:11.686326Z" "start_time": "2025-04-15T09:33:11.686326Z"
} }
}, },
"source": [
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"page\",\n",
")\n",
"docs = loader.load()\n",
"print(len(docs))\n",
"pprint.pp(docs[0].metadata)"
],
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
@ -409,7 +402,16 @@
] ]
} }
], ],
"execution_count": 8 "source": [
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"page\",\n",
")\n",
"docs = loader.load()\n",
"print(len(docs))\n",
"pprint.pp(docs[0].metadata)"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -427,22 +429,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:33:30.520801Z", "end_time": "2025-04-15T09:33:30.520801Z",
"start_time": "2025-04-15T09:33:28.785067Z" "start_time": "2025-04-15T09:33:28.785067Z"
} }
}, },
"source": [
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"single\",\n",
")\n",
"docs = loader.load()\n",
"print(len(docs))\n",
"pprint.pp(docs[0].metadata)"
],
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
@ -488,7 +481,16 @@
] ]
} }
], ],
"execution_count": 9 "source": [
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"single\",\n",
")\n",
"docs = loader.load()\n",
"print(len(docs))\n",
"pprint.pp(docs[0].metadata)"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -504,22 +506,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:33:34.209872Z", "end_time": "2025-04-15T09:33:34.209872Z",
"start_time": "2025-04-15T09:33:32.242569Z" "start_time": "2025-04-15T09:33:32.242569Z"
} }
}, },
"source": [
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"single\",\n",
" pages_delimiter=\"\\n-------THIS IS A CUSTOM END OF PAGE-------\\n\",\n",
")\n",
"docs = loader.load()\n",
"print(docs[0].page_content[:5780])"
],
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
@ -643,7 +636,16 @@
] ]
} }
], ],
"execution_count": 10 "source": [
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"single\",\n",
" pages_delimiter=\"\\n-------THIS IS A CUSTOM END OF PAGE-------\\n\",\n",
")\n",
"docs = loader.load()\n",
"print(docs[0].page_content[:5780])"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -682,15 +684,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:33:56.217580Z", "end_time": "2025-04-15T09:33:56.217580Z",
"start_time": "2025-04-15T09:33:42.788726Z" "start_time": "2025-04-15T09:33:42.788726Z"
} }
}, },
"source": [
"%pip install -qU rapidocr-onnxruntime"
],
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -701,30 +701,19 @@
] ]
} }
], ],
"execution_count": 11 "source": [
"%pip install -qU rapidocr-onnxruntime"
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:34:24.118706Z", "end_time": "2025-04-15T09:34:24.118706Z",
"start_time": "2025-04-15T09:33:56.230529Z" "start_time": "2025-04-15T09:33:56.230529Z"
} }
}, },
"source": [
"from langchain_community.document_loaders.parsers import RapidOCRBlobParser\n",
"\n",
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"page\",\n",
" images_inner_format=\"markdown-img\",\n",
" images_parser=RapidOCRBlobParser(),\n",
")\n",
"docs = loader.load()\n",
"\n",
"print(docs[5].page_content)"
],
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
@ -819,7 +808,20 @@
] ]
} }
], ],
"execution_count": 12 "source": [
"from langchain_community.document_loaders.parsers import RapidOCRBlobParser\n",
"\n",
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"page\",\n",
" images_inner_format=\"markdown-img\",\n",
" images_parser=RapidOCRBlobParser(),\n",
")\n",
"docs = loader.load()\n",
"\n",
"print(docs[5].page_content)"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -837,15 +839,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 13,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:35:29.381269Z", "end_time": "2025-04-15T09:35:29.381269Z",
"start_time": "2025-04-15T09:35:26.711980Z" "start_time": "2025-04-15T09:35:26.711980Z"
} }
}, },
"source": [
"%pip install -qU pytesseract"
],
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -856,29 +856,19 @@
] ]
} }
], ],
"execution_count": 13 "source": [
"%pip install -qU pytesseract"
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:35:45.154957Z", "end_time": "2025-04-15T09:35:45.154957Z",
"start_time": "2025-04-15T09:35:33.162485Z" "start_time": "2025-04-15T09:35:33.162485Z"
} }
}, },
"source": [
"from langchain_community.document_loaders.parsers import TesseractBlobParser\n",
"\n",
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"page\",\n",
" images_inner_format=\"html-img\",\n",
" images_parser=TesseractBlobParser(),\n",
")\n",
"docs = loader.load()\n",
"print(docs[5].page_content)"
],
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
@ -973,7 +963,19 @@
] ]
} }
], ],
"execution_count": 14 "source": [
"from langchain_community.document_loaders.parsers import TesseractBlobParser\n",
"\n",
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"page\",\n",
" images_inner_format=\"html-img\",\n",
" images_parser=TesseractBlobParser(),\n",
")\n",
"docs = loader.load()\n",
"print(docs[5].page_content)"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -984,15 +986,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 15,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:36:02.237828Z", "end_time": "2025-04-15T09:36:02.237828Z",
"start_time": "2025-04-15T09:35:57.078164Z" "start_time": "2025-04-15T09:35:57.078164Z"
} }
}, },
"source": [
"%pip install -qU langchain_openai"
],
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -1003,23 +1003,19 @@
] ]
} }
], ],
"execution_count": 15 "source": [
"%pip install -qU langchain_openai"
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 16,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:36:03.749164Z", "end_time": "2025-04-15T09:36:03.749164Z",
"start_time": "2025-04-15T09:36:03.558685Z" "start_time": "2025-04-15T09:36:03.558685Z"
} }
}, },
"source": [
"import os\n",
"\n",
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()"
],
"outputs": [ "outputs": [
{ {
"data": { "data": {
@ -1032,47 +1028,40 @@
"output_type": "execute_result" "output_type": "execute_result"
} }
], ],
"execution_count": 16 "source": [
"import os\n",
"\n",
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()"
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:36:04.863788Z", "end_time": "2025-04-15T09:36:04.863788Z",
"start_time": "2025-04-15T09:36:04.852010Z" "start_time": "2025-04-15T09:36:04.852010Z"
} }
}, },
"outputs": [],
"source": [ "source": [
"from getpass import getpass\n", "from getpass import getpass\n",
"\n", "\n",
"if not os.environ.get(\"OPENAI_API_KEY\"):\n", "if not os.environ.get(\"OPENAI_API_KEY\"):\n",
" os.environ[\"OPENAI_API_KEY\"] = getpass(\"OpenAI API key =\")" " os.environ[\"OPENAI_API_KEY\"] = getpass(\"OpenAI API key =\")"
], ]
"outputs": [],
"execution_count": 17
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 18,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:37:03.954718Z", "end_time": "2025-04-15T09:37:03.954718Z",
"start_time": "2025-04-15T09:36:09.023976Z" "start_time": "2025-04-15T09:36:09.023976Z"
} }
}, },
"source": [
"from langchain_community.document_loaders.parsers import LLMImageBlobParser\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"page\",\n",
" images_inner_format=\"markdown-img\",\n",
" images_parser=LLMImageBlobParser(model=ChatOpenAI(model=\"gpt-4o\", max_tokens=1024)),\n",
")\n",
"docs = loader.load()\n",
"print(docs[5].page_content)"
],
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
@ -1164,7 +1153,20 @@
] ]
} }
], ],
"execution_count": 18 "source": [
"from langchain_community.document_loaders.parsers import LLMImageBlobParser\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"loader = PDFPlumberLoader(\n",
" \"./example_data/layout-parser-paper.pdf\",\n",
" metadata_format=\"standard\",\n",
" mode=\"page\",\n",
" images_inner_format=\"markdown-img\",\n",
" images_parser=LLMImageBlobParser(model=ChatOpenAI(model=\"gpt-4o\", max_tokens=1024)),\n",
")\n",
"docs = loader.load()\n",
"print(docs[5].page_content)"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@ -1179,29 +1181,14 @@
] ]
}, },
{ {
"cell_type": "code",
"execution_count": 20,
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-04-15T09:39:00.809544Z", "end_time": "2025-04-15T09:39:00.809544Z",
"start_time": "2025-04-15T09:38:58.847574Z" "start_time": "2025-04-15T09:38:58.847574Z"
} }
}, },
"cell_type": "code",
"source": [
"from langchain_community.document_loaders import FileSystemBlobLoader\n",
"from langchain_community.document_loaders.generic import GenericLoader\n",
"from langchain_community.document_loaders.parsers import PDFPlumberParser\n",
"\n",
"loader = GenericLoader(\n",
" blob_loader=FileSystemBlobLoader(\n",
" path=\"./example_data/\",\n",
" glob=\"*.pdf\",\n",
" ),\n",
" blob_parser=PDFPlumberParser(),\n",
")\n",
"docs = loader.load()\n",
"print(docs[0].page_content)\n",
"pprint.pp(docs[0].metadata)"
],
"outputs": [ "outputs": [
{ {
"name": "stderr", "name": "stderr",
@ -1294,49 +1281,6 @@
] ]
} }
], ],
"execution_count": 20
},
{
"cell_type": "markdown",
"metadata": {},
"source": "It is possible to work with files from cloud storage."
},
{
"cell_type": "code",
"metadata": {},
"source": [
"from langchain_community.document_loaders import CloudBlobLoader\n",
"from langchain_community.document_loaders.generic import GenericLoader\n",
"from langchain_community.document_loaders.parsers import PDFPlumberParser\n",
"\n",
"loader = GenericLoader(\n",
" blob_loader=CloudBlobLoader(\n",
" url=\"s3://mybucket\", # Supports s3://, az://, gs://, file:// schemes.\n",
" glob=\"*.pdf\",\n",
" ),\n",
" blob_parser=PDFPlumberParser(\n",
" metadata_format=\"standard\",\n",
" ),\n",
")\n",
"docs = loader.load()\n",
"print(docs[0].page_content)\n",
"pprint.pp(docs[0].metadata)"
],
"outputs": [],
"execution_count": null
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `PDFMinerLoader` features and configurations head to the API reference: https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.pdf.PDFPlumberLoader.html"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [ "source": [
"from langchain_community.document_loaders import FileSystemBlobLoader\n", "from langchain_community.document_loaders import FileSystemBlobLoader\n",
"from langchain_community.document_loaders.generic import GenericLoader\n", "from langchain_community.document_loaders.generic import GenericLoader\n",
@ -1354,9 +1298,69 @@
"docs = loader.load()\n", "docs = loader.load()\n",
"print(docs[0].page_content)\n", "print(docs[0].page_content)\n",
"pprint.pp(docs[0].metadata)" "pprint.pp(docs[0].metadata)"
], ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": "It is possible to work with files from cloud storage."
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [], "outputs": [],
"execution_count": null "source": [
"from langchain_community.document_loaders import CloudBlobLoader\n",
"from langchain_community.document_loaders.generic import GenericLoader\n",
"from langchain_community.document_loaders.parsers import PDFPlumberParser\n",
"\n",
"loader = GenericLoader(\n",
" blob_loader=CloudBlobLoader(\n",
" url=\"s3://mybucket\", # Supports s3://, az://, gs://, file:// schemes.\n",
" glob=\"*.pdf\",\n",
" ),\n",
" blob_parser=PDFPlumberParser(\n",
" metadata_format=\"standard\",\n",
" ),\n",
")\n",
"docs = loader.load()\n",
"print(docs[0].page_content)\n",
"pprint.pp(docs[0].metadata)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `PDFMinerLoader` features and configurations head to the API reference: https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.pdf.PDFPlumberLoader.html"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.document_loaders import FileSystemBlobLoader\n",
"from langchain_community.document_loaders.generic import GenericLoader\n",
"from langchain_community.document_loaders.parsers import PDFPlumberParser\n",
"\n",
"loader = GenericLoader(\n",
" blob_loader=FileSystemBlobLoader(\n",
" path=\"./example_data/\",\n",
" glob=\"*.pdf\",\n",
" ),\n",
" blob_parser=PDFPlumberParser(\n",
" metadata_format=\"standard\",\n",
" ),\n",
")\n",
"docs = loader.load()\n",
"print(docs[0].page_content)\n",
"pprint.pp(docs[0].metadata)"
]
} }
], ],
"metadata": { "metadata": {

6
libs/community/langchain_community/document_loaders/parsers/pdf.py
View File

@ -1607,7 +1607,7 @@ class PDFPlumberParser(BaseBlobParser):
mime_type="application/x-npy", mime_type="application/x-npy",
) )
text_from_image = next( text_from_image = next(
self.images_parser.lazy_parse(blob) # type: ignore self.images_parser.lazy_parse(blob)
).page_content ).page_content
extras.append( extras.append(
_format_inner_image( _format_inner_image(
@ -1764,9 +1764,7 @@ class PDFPlumberParser(BaseBlobParser):
) )
elif img["stream"]["Filter"].name in _PDF_FILTER_WITH_LOSS: elif img["stream"]["Filter"].name in _PDF_FILTER_WITH_LOSS:
buf = np.frombuffer(img["stream"].get_data(), dtype=np.uint8) buf = np.frombuffer(img["stream"].get_data(), dtype=np.uint8)
images.append( images.append(np.array(Image.open(io.BytesIO(buf.tobytes()))))
np.array(Image.open(io.BytesIO(buf.tobytes()))) # type: ignore
)
else: else:
logger.warning("Unknown PDF Filter!") logger.warning("Unknown PDF Filter!")