PDF

Document Embedding

Generate vector representations of entire documents

520K runs

Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.

Input

Input Type

File URL string

Enter a URL to a pdf file

Upload pdf

Drag and drop a pdf file here, or click to browse

Select File

# model string

Embedding model to use. Default: document_encoder_v2

# chunk_size number

Size of text chunks for embedding. Default: 512

Output

{
  "embedding": [
    0.085,
    -0.031,
    0.142,
    0.073,
    "..."
  ],
  "dimensions": 1536,
  "model": "document_encoder_v2",
  "page_embeddings": [
    {
      "page": 1,
      "embedding": [
        0.091,
        -0.035,
        0.137,
        "..."
      ]
    },
    {
      "page": 2,
      "embedding": [
        0.079,
        -0.028,
        0.145,
        "..."
      ]
    }
  ],
  "section_embeddings": [
    {
      "section": "executive_summary",
      "embedding": [
        0.074,
        -0.042,
        0.156,
        "..."
      ]
    },
    {
      "section": "financial_results",
      "embedding": [
        0.096,
        -0.018,
        0.131,
        "..."
      ]
    }
  ]
}

Ready to run Document Embedding on your data? Spin it up in Studio — no infra to host.

Run this in Studio

Already have embeddings? Skip extraction — search your own vectors with MVS. First 1M vectors free.

Try MVS →