Add a Document(s) to a Collection

Overview

A Collection can contain multiple Documents. Added documents are indexed and stored in a database. When you ask a question about the Document(s), h2oGPTe crawls through the indexed Document(s) in the Collection to find relevant content to answer the question while utilizing the H2O LLM to summarize a concise question response. You can add documents while creating a Collection or after creating a Collection.

note

To learn how to create a Collection, see Create a Collection.

Instructions

To add a Document(s) to a Collection, consider the following instructions:

1. In the Enterprise h2oGPTe navigation menu, click Collections.

2. In the Collections table, select the name of the Collection you want to add a Document(s) to.

3. Click + Add documents.

   info

   You can upload certain text, image, and audio file types to a Collection. To learn more, see Supported file types for a Collection.

4. In the Choose method list, select a method to import a Document(s).

   Methods

   Upload documents

   1. Click Browse....
   2. Upload documents.

   Import from file system

   1. In the Directory to import documents from box, enter a directory to import Documents from.
   2. In the Glob pattern to match files box, enter a global pattern to match the files (Documents).

   Import from URL

   1. In the URL to import box, enter a valid URL.

   Upload plain text

   1. In the Plain text to upload box, paste the text you copied from another source to create a document.

   Select a document

   1. In the Search for a document list, select a Document that is imported to another Collection.
      note

      The selected Document will be imported into this Collection.

   Select a Collection

   1. In the Search for a collection list, select an existing Collection.
      note

      All Documents from the selected Collection will be imported into the new Collection.

   Import from S3

   1. In the S3 Path box, enter the Document URL in the Amazon S3 bucket.
   2. Enter the Region Name.
   3. Optional: Enter the Access Key ID.
   4. Optional: Enter the Secret Access Key.
   5. Optional: Enter the Session Token.
   6. Click Add selected.

   Import from Azure Blob Storage

   1. In the Container box, enter the URI for the container.
   2. Optional: In the Path box, enter the URL of the blob.
   3. In the Account name box, enter the account name.
   4. Optional: In the Account Key box, enter the account key.
   5. Optional: In the SAS token box, enter the shared access signature (SAS) token.
   6. Click Add selected.

   Import from Google Cloud Storage

   1. In the Google Storage path box, enter the Google Cloud Storage resource path.
   2. Optional: In the Service Account Key box, enter the service account key.
   3. Click Add selected.
   note

   • Toggle the Create short document summaries button to auto-generate a summary of your document.
   • Toggle the Create sample questions for documents button to receive auto-suggested sample questions based on your document.
   • From the Spoken language in audio files dropdown list, select the language spoken in the uploaded audio files.
   • From the OCR model dropdown, select the OCR (Optical Character Recognition) model to identify and extract text from images and PDFs.

5. Click Add.

note

• If you try to add an empty Document, the indexing of the files will fail. Overall, the Job associated with the Collection will fail.
• To learn how to Chat with a Collection, see Chat with a Collection.

---

Feedback

• Submit and view feedback for this page
• Send feedback about Enterprise h2oGPTe to cloud-feedback@h2o.ai