kreneskyp / ix

Autonomous GPT-4 agent platform
MIT License
1.01k stars 121 forks source link

Unstructured IO #373

Closed kreneskyp closed 10 months ago

kreneskyp commented 10 months ago

Description

More complete implementation of Unstructured IO. Adds classes for all known loaders upstream in LangChain community:

    UNSTRUCTURED_API_FILE_LOADER,
    UNSTRUCTURED_WORD_DOCUMENT_LOADER,
    UNSTRUCTURED_ODT_LOADER,
    UNSTRUCTURED_PDF_LOADER,
    UNSTRUCTURED_HTML_LOADER,
    UNSTRUCTURED_CSV_LOADER,
    UNSTRUCTURED_MARKDOWN_LOADER,
    UNSTRUCTURED_RST_LOADER,
    UNSTRUCTURED_EPUB_LOADER,
    UNSTRUCTURED_XML_LOADER,
    UNSTRUCTURED_IMAGE_LOADER,
    UNSTRUCTURED_EMAIL_LOADER,
    UNSTRUCTURED_RTF_LOADER,
    UNSTRUCTURED_ORG_MODE_LOADER,
    UNSTRUCTURED_POWERPOINT_LOADER,
    UNSTRUCTURED_EXCEL_LOADER,
    UNSTRUCTURED_TSV_LOADER,

Changes

[List out the changes you've made in this pull request. Be as specific as possible.]

How Tested

[Explain how you tested this pull request. Include any relevant steps or scripts.]

TODOs