​
Getting Started

vlm-1 can extract structured markdown from long documents and reports. Here’s a rough breakdown of the steps involved in parsing a document:

1

Upload Document

Use the /v1/files endpoint to upload the document you want to parse.

from vlmrun.client import VLMRun
from vlmrun.client.types import FileResponse

# Initialize the client
client = VLMRun(api_key="<your-api-key>")

# Upload the file
response: FileResponse = client.files.upload(
    file=Path("<path/to/test.pdf>")
)
print(f"Uploaded file:\n {response.model_dump()}")

You should see a response like this:

Uploaded file:
{
  'id': '1e76cfd9-ba99-49b2-a8fe-2c8efaad2649',
  'filename': 'file-20240815-7UvOUQ-earnings_single_table.pdf',
  'bytes': 62430,
  'purpose': 'assistants',
  'created_at': '2024-08-15T02:22:06.716130',
  'object': 'file'
}
2

Submit the Document AI Job

Submit the uploaded file (via its file_id) to the /v1/document/generate endpoint to start the document parsing job. For long documents, you should set batch=True to submit the job to a queue for processing.

from vlmrun.client.types import PredictionResponse

# Submit the document for parsing
# Note: In this case, we are using the `document.markdown` domain
# which is optimized for extracting structured markdown from documents
response: PredictionResponse = client.document.generate(
    file=response.id,
    domain="document.markdown",
    batch=True,
)
print(f"Document submitted [id={response.id}]")
print(response.model_dump_json(indent=2))

You should see a response like this:

Document parsing job submitted:
{
  "id": "052cf2a8-2b84-45f5-a385-ccac2aae13bb",
  "created_at": "2024-08-15T02:22:09.157788",
  "response": null,
  "status": "pending"
}
3

Fetch the Results

Use the /v1/document/{request_id} endpoint to fetch the results of the document parsing job. The results of the extraction job will be in JSON format under the response field.

# Fetch the results
response: PredictionResponse = client.document.get(request_id)
print(f"Document parsing job results:\n {response.model_dump()}")

You should see a response like this:

{
  "id": "052cf2a8-2b84-45f5-a385-ccac2aae13bb",
  "created_at": "2024-08-15T02:22:09.157788",
  "status": "completed",
  "response": {
    "pages: [
      {
        "title": "Reducing Our Environmental Impact: Go Zero",
        "page_number": 30,
        "description": "...",
        "lines": [...]
        "paragraphs": [...]
        "tables": null,
        "charts": [...]
      },
      ...
    ]
  }
}

​
Notebook Example

If you want to simply look at the code, skip to the colab notebook link directly here.

​
Illustrative Examples

Here are some examples of the structured JSON output that vlm-1 can extract from long documents and reports:

Document AI with `vlm-1` - Example 1.

Document AI with `vlm-1` - Example 2.

Document AI with `vlm-1` - Example 3.

Document AI with `vlm-1` - Example 4.

​
Try our Document -> JSON API today

Head over to our Document -> JSON to start building your own document processing pipeline with VLM Run. Sign-up for access on our platform.