Microsoft Excel 集成

pip install -qU langchain-community unstructured openpyxl

from langchain_community.document_loaders import UnstructuredExcelLoader

loader = UnstructuredExcelLoader("./example_data/stanley-cups.xlsx", mode="elements")
docs = loader.load()

print(len(docs))

docs

4

[Document(page_content='Stanley Cups', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups', 'page_number': 1, 'languages': ['eng'], 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Title'}),
 Document(page_content='\n\n\nTeam\nLocation\nStanley Cups\n\n\nBlues\nSTL\n1\n\n\nFlyers\nPHI\n2\n\n\nMaple Leafs\nTOR\n13\n\n\n', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups', 'page_number': 1, 'text_as_html': '<table border="1" class="dataframe">\n  <tbody>\n    <tr>\n      <td>Team</td>\n      <td>Location</td>\n      <td>Stanley Cups</td>\n    </tr>\n    <tr>\n      <td>Blues</td>\n      <td>STL</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <td>Flyers</td>\n      <td>PHI</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <td>Maple Leafs</td>\n      <td>TOR</td>\n      <td>13</td>\n    </tr>\n  </tbody>\n</table>', 'languages': ['eng'], 'parent_id': '17e9a90f9616f2abed8cf32b5bd3810d', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Table'}),
 Document(page_content='Stanley Cups Since 67', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups Since 67', 'page_number': 2, 'languages': ['eng'], 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Title'}),
 Document(page_content='\n\n\nTeam\nLocation\nStanley Cups\n\n\nBlues\nSTL\n1\n\n\nFlyers\nPHI\n2\n\n\nMaple Leafs\nTOR\n0\n\n\n', metadata={'source': './example_data/stanley-cups.xlsx', 'file_directory': './example_data', 'filename': 'stanley-cups.xlsx', 'last_modified': '2023-12-19T13:42:18', 'page_name': 'Stanley Cups Since 67', 'page_number': 2, 'text_as_html': '<table border="1" class="dataframe">\n  <tbody>\n    <tr>\n      <td>Team</td>\n      <td>Location</td>\n      <td>Stanley Cups</td>\n    </tr>\n    <tr>\n      <td>Blues</td>\n      <td>STL</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <td>Flyers</td>\n      <td>PHI</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <td>Maple Leafs</td>\n      <td>TOR</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>', 'languages': ['eng'], 'parent_id': 'ee34bd8c186b57e3530d5443ffa58122', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'category': 'Table'})]

pip install -qU langchain langchain-community azure-ai-documentintelligence

from langchain_community.document_loaders import AzureAIDocumentIntelligenceLoader

file_path = "<filepath>"
endpoint = "<endpoint>"
key = "<key>"
loader = AzureAIDocumentIntelligenceLoader(
    api_endpoint=endpoint, api_key=key, file_path=file_path, api_model="prebuilt-layout"
)

documents = loader.load()