Header: x-po-di-apikey: $POLARIS_DATAINSIGHT_API_KEY

export POLARIS_DATAINSIGHT_API_KEY="your-api-key-here"

POST https://datainsight-api.polarisoffice.com/api/v1/datainsight/doc-extract

import requests
import json
import zipfile
import io

def extract_document(file_path: str, api_key: str) -> dict:
    with open(file_path, "rb") as f:
        response = requests.post(
            "https://datainsight-api.polarisoffice.com/api/v1/datainsight/doc-extract",
            headers={"x-po-di-apikey": api_key},
            files={"file": f}
        )

    if response.status_code != 200:
        raise Exception(f"API error: {response.status_code} - {response.text}")

    # Response is a ZIP file
    zip_buffer = io.BytesIO(response.content)
    with zipfile.ZipFile(zip_buffer) as z:
        json_files = [name for name in z.namelist() if name.endswith('.json')]
        if json_files:
            with z.open(json_files[0]) as jf:
                return json.load(jf)

    raise Exception("No JSON found in ZIP")

# Example usage
import os
api_key = os.environ["POLARIS_DATAINSIGHT_API_KEY"]
schema = extract_document("report.docx", api_key)
print(f"Extracted {schema['totalPages']} pages")

curl -X POST "https://datainsight-api.polarisoffice.com/api/v1/datainsight/doc-extract" \
  -H "x-po-di-apikey: $POLARIS_DATAINSIGHT_API_KEY" \
  -F "file=@example.docx" \
  --output result.zip

unzip result.zip -d result/
cat result/*.json | python -m json.tool

{
  "docName": "sample.docx",
  "totalPages": 3,
  "pages": [ ... ]
}

{
  "pageNum": 1,
  "pageWidth": 595.3,
  "pageHeight": 842.0,
  "extractionSummary": {
    "text": 5, "image": 2, "table": 1, "chart": 1
  },
  "elements": [ ... ]
}

{
  "type": "text",
  "id": "te1",
  "boundaryBox": { "left": 40, "top": 80, "right": 300, "bottom": 120 },
  "content": { "text": "Body content here" }
}

{
  "content": {
    "html": "<table>...</table>",
    "csv": "Header1,Header2\nValue1,Value2",
    "json": [
      {
        "metrics": { "rowaddr": 0, "coladdr": 0, "rowspan": 1, "colspan": 1 },
        "para": [{ "content": [{ "text": "Cell content" }] }]
      }
    ]
  }
}

{
  "content": {
    "chart_type": "column",
    "title": "Annual Sales Comparison",
    "x_axis_labels": ["Q1", "Q2", "Q3", "Q4"],
    "series_names": ["2023", "2024"],
    "series_values": [[100, 200, 150, 300], [120, 220, 180, 320]],
    "csv": "Quarter,2023,2024\nQ1,100,120\nQ2,200,220"
  }
}

def get_all_text(schema: dict) -> str:
    texts = []
    for page in schema.get("pages", []):
        for el in page.get("elements", []):
            if el["type"] == "text" and el.get("content", {}).get("text"):
                texts.append(el["content"]["text"])
    return "\n".join(texts)

def get_tables_as_csv(schema: dict) -> list:
    tables = []
    for page in schema.get("pages", []):
        for el in page.get("elements", []):
            if el["type"] == "table":
                csv_data = el.get("content", {}).get("csv", "")
                if csv_data:
                    tables.append(csv_data)
    return tables

def make_rag_chunks(schema: dict) -> list:
    chunks = []
    doc_name = schema.get("docName", "")
    for page in schema.get("pages", []):
        for el in page.get("elements", []):
            text = el.get("content", {}).get("text") or el.get("content", {}).get("csv") or ""
            if text.strip():
                chunks.append({
                    "source": doc_name,
                    "page": page["pageNum"],
                    "type": el["type"],
                    "text": text.strip()
                })
    return chunks

import os
schema = extract_document("report.docx", os.environ["POLARIS_DATAINSIGHT_API_KEY"])
tables = get_tables_as_csv(schema)
for i, csv_data in enumerate(tables):
    print(f"=== Table {i+1} ===")
    print(csv_data)

=== Table 1 ===
Quarter,Revenue,Cost
Q1,1200,800
Q2,1500,900

=== Table 2 ===
Item,Amount
Labor,500
Operations,300