Documents

Retrieve and manage documents stored in a corpus for administrative tasks.

📄️ List the documents in the corpus

The List Documents API enables you to retrieve a list of documents stored in a specific corpus. This endpoint provides an overview of document metadata, including document IDs, tables (if table extraction is enabled), and pagination details.

📄️ Delete a document

Permanently delete a document identified by its unique `document_id` from a specific corpus. This operation cannot be undone, so use it with caution.

📄️ Retrieve a document

The Retrieve Document API enables you to fetch the content and metadata of a specific document from a corpus, identified by its unique `document_id` from a specific corpus. Use this endpoint to view the full details of a document, including its text, metadata, and associated tables, if table extraction is enabled.

📄️ Summarize a document

Organizations often struggle with extracting relevant insights from extensive documentation, such as vendor quotes, financial statements, and technical reports. Manually reviewing these documents is both time-consuming and prone to errors.

📄️ Retrieve an image from a document

Returns a specific image that is embedded within a document. The `image_id` uniquely identifies the image within the document. Use this endpoint to fetch the raw image data and associated metadata.