Email integration

Integrate with the Email document loader using LangChain Python.

This notebook shows how to load email (.eml) or Microsoft Outlook (.msg) files.

Please see Unstructured for more instructions on setting up Unstructured locally, including setting up required system dependencies.

Using unstructured

pip install -qU unstructured

from langchain_community.document_loaders import UnstructuredEmailLoader

loader = UnstructuredEmailLoader("./example_data/fake-email.eml")

data = loader.load()

data

[Document(page_content='This is a test email to use for unit tests.\n\nImportant points:\n\nRoses are red\n\nViolets are blue', metadata={'source': './example_data/fake-email.eml'})]

Retain elements

Under the hood, Unstructured creates different “elements” for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying mode="elements".

loader = UnstructuredEmailLoader("example_data/fake-email.eml", mode="elements")

data = loader.load()

data[0]

Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'file_directory': 'example_data', 'filename': 'fake-email.eml', 'last_modified': '2022-12-16T17:04:16-05:00', 'sent_from': ['Matthew Robinson [[e-mail]](mailto:[e-mail])'], 'sent_to': ['Matthew Robinson [[e-mail]](mailto:[e-mail])'], 'subject': 'Test Email', 'languages': ['eng'], 'filetype': 'message/rfc822', 'category': 'NarrativeText'})

Processing attachments

You can process attachments with UnstructuredEmailLoader by setting process_attachments=True in the constructor. By default, attachments will be partitioned using the partition function from unstructured. You can use a different partitioning function by passing the function to the attachment_partitioner kwarg.

loader = UnstructuredEmailLoader(
    "example_data/fake-email.eml",
    mode="elements",
    process_attachments=True,
)

data = loader.load()

data[0]

Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'file_directory': 'example_data', 'filename': 'fake-email.eml', 'last_modified': '2022-12-16T17:04:16-05:00', 'sent_from': ['Matthew Robinson [[e-mail]](mailto:[e-mail])'], 'sent_to': ['Matthew Robinson [[e-mail]](mailto:[e-mail])'], 'subject': 'Test Email', 'languages': ['eng'], 'filetype': 'message/rfc822', 'category': 'NarrativeText'})

Using OutlookMessageLoader

pip install -qU extract_msg

from langchain_community.document_loaders import OutlookMessageLoader

loader = OutlookMessageLoader("example_data/fake-email.msg")

data = loader.load()

data[0]

Document(page_content='This is a test email to experiment with the MS Outlook MSG Extractor\r\n\r\n\r\n-- \r\n\r\n\r\nKind regards\r\n\r\n\r\n\r\n\r\nBrian Zhou\r\n\r\n', metadata={'source': 'example_data/fake-email.msg', 'subject': 'Test for TIF files', 'sender': 'Brian Zhou [[e-mail]](mailto:[e-mail])', 'date': datetime.datetime(2013, 11, 18, 0, 26, 24, tzinfo=zoneinfo.ZoneInfo(key='America/Los_Angeles'))})

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.