⚙️ API Endpoints

1️⃣ Submit PDF for PageIndex Computation

Endpoint (POST): https://api.vectify.ai/pageindex
Description: Initiates the conversion of a PDF document into a structured hierarchical tree format. Immediately returns a task identifier (task_id).

Request Body:

Parameter	Type	Required	Description
file	binary	Yes	PDF file to be processed

Optional Parameters:

Parameter	Description	Default Value
`model`	OpenAI model to use	`"gpt-4o-2024-11-20"`
`toc_check_page_num`	Number of initial pages to check for table of contents	`20`
`max_page_num_each_node`	Max pages allowed for each node	`10`
`max_token_num_each_node`	Max tokens allowed for each node	`20000`
`if_add_node_id`	Include a node ID for each node (`yes` / `no`)	`"yes"`
`if_add_node_summary`	Include a summary for each node (`yes` / `no`)	`"no"`
`if_add_doc_description`	Include a description for the document (`yes` / `no`)	`"yes"`

Example Request:

with open('./2023-annual-report.pdf', 'rb') as file:
    response = requests.post(
        "https://api.vectify.ai/pageindex",
        headers={'api_key': 'YOUR_API_KEY_HERE'},
        files={'file': file}
    )

Example Request with Optional Parameters:

with open('./2023-annual-report.pdf', 'rb') as file:
    response = requests.post(
        "https://api.vectify.ai/pageindex",
        headers={'api_key': 'YOUR_API_KEY_HERE'},
        files={'file': file},
        data={
            "toc_check_pages": 15,
            "max_page_num_each_node": 8,
        }
    )

See here for the example PDF document.

Example Response:

{
  "task_id": "abc123def456"
}

2️⃣ Check Status and Retrieve Results

Endpoint (POST): https://api.vectify.ai/pageindex/status
Description: Checks computation status and retrieves results once processing is complete.

Request Body:

Parameter	Type	Required	Description
task_id	string	Yes	Task ID from submit response

Computation Status:

The status returned from the endpoint indicates the progress of PDF processing tasks:

Status	Description
`queued`	Task is queued and waiting to begin processing
`processing`	Task is currently being processed
`completed`	Task processing is complete; results are ready
`failed`	Task processing encountered an error

Example Request:

response = requests.post(
    "https://api.vectify.ai/pageindex/status",
    headers={'api_key': 'YOUR_API_KEY_HERE'},
    json={"task_id": "abc123def456"}
)

Example Response (Processing):

{
  "task_id": "abc123def456",
  "status": "processing"
}

Example Response (Completed):

{
  "task_id": "abc123def456",
  "status": "completed",
  "result": [
    ...
    {
        "title": "Financial Stability",
        "node_id": "0006",
        "start_index": 21,
        "end_index": 22,
        "summary": "The Federal Reserve maintains financial stability by...",
        "child_nodes": [
            {
                "title": "Monitoring Financial Vulnerabilities",
                "node_id": "0007",
                "start_index": 22,
                "end_index": 28,
                "summary": "The Federal Reserve's monitoring focuses on..."
            },
            {
                "title": "Domestic and International Cooperation and Coordination",
                "node_id": "0008",
                "start_index": 28,
                "end_index": 31,
                "summary": "In 2023, the Federal Reserve collaborated internationally..."
            }
        ]
    }
    ...
  ]
}

See here for a complete example output structure generated by PageIndex from the above example PDF document.

⚠️ API Response Codes

Status Code	Description	Resolution
`200`	Request successful	-
`400`	Bad request due to missing/invalid parameters	Check request parameters
`401`	Unauthorized; invalid or missing API key	Ensure API key is correct
`404`	Task or PDF file not found	Verify task_id and PDF path
`413`	File size too large	Use smaller file or contact support
`500`	Internal server error	Retry later; if persistent, contact support