Uploading Files to Trieve

​

Overview

We provide the ability for users to upload their files to Trieve and use our automatic chunking. When uploading a file to Trieve, we automatically group the chunks together to link them. This is done through our upload file route.

​

Uploading a File to Trieve

Our service supports various file types (e.g., HTML, DOCX, PDF). We use Apache Tika to convert these files to HTML to preserve formatting and then chunk them.

​

Important Parameters

• base64_file: To allow users to pass metadata with their file uploads, we require files to be base64 URL encoded. Convert + to -, / to _, and remove the ending = if present.
• file_name: The name of the file being uploaded, including the extension. This will become the name of the resulting group.
• group_tracking_id: This field allows you to assign an arbitrary ID to the group, aiding in coordination with your database system. You can search for this group using this ID.
• link, tag_set, and time_stamp: These fields are indexed to enable fast filtering of groups based on these attributes.
• metadata: This field allows you to include any arbitrary metadata in the form of a JSON object with the group.

​

Example Upload File Request

POST /api/file
Headers:
{
    "TR-Dataset": "<Your Dataset ID>",
    "Authorization": "<Your API Key>"
}
Body:
{
    "file_name": "text.docx",
    "base64_file": "SGVsbG8sIFdvcmxkIQ...",
    "metadata": {
        "todo": "add what seems useful"
    },
    "create_chunks": true,
    "group_tracking_id": "test-group-tracking-id"
}