Load OCRmyPDF data to DuckDB

OCRmyPDF is a command-line tool and Python library that adds an optical character recognition (OCR) text layer to scanned PDF files. Everything needed to build a working OCRmyPDF → DuckDB pipeline is on this page: the API's base URL, authentication, endpoints, pagination and incremental field — plus a prompt that hands the whole job to your coding agent.

---

Build your OCRmyPDF to DuckDB pipeline

Paste this prompt into Claude, Codex, or Cursor. The agent does the rest.

PromptCopy prompt
Run uvx dlthub-init@latest to build a pipeline from OCRmyPDF to DuckDB and run it on dltHub

That scaffolds a dltHub workspace and installs the dltHub AI harness — the project rules, the secrets-management skill, and the dlt MCP server your agent needs to work safely. From there it reads the OCRmyPDF API, proposes the endpoints to load, then writes, runs and validates the pipeline while you review rather than type. Credentials are inspected through MCP tools, so your agent never reads secrets.toml itself. How the LLM-native workflow works →

Prefer to write it yourself? Every fact the agent uses is below.

---

OCRmyPDF API at a glance

These values come from the OCRmyPDF API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the OCRmyPDF API?

OCRmyPDF does not provide an official REST API for production use; the available web service wrapper is for demonstration purposes only and lacks authentication mechanisms.

No credentials required. The OCRmyPDF API is public, so there is nothing to obtain and nothing to add to .dlt/secrets.toml — the pipeline above runs as written.

---

What OCRmyPDF data can I load into DuckDB?

These are the OCRmyPDF endpoints dlt can load into DuckDB:

---

How do I load only new OCRmyPDF records?

The OCRmyPDF API reference does not document a timestamp or sequence field for these endpoints, so there is nothing to advertise here as verified. Pick a field from the endpoints table above that increases with every write, then set it as the cursor_path.

Copy
{"name": "records", "endpoint": {
    "path": "records",
    # Replace with a field that increases on every write.
    "incremental": {"cursor_path": "REPLACE_ME", "initial_value": "2024-01-01T00:00:00Z"},
}}

On the first run dlt loads everything from initial_value; on every run after that it requests only what changed and appends with write_disposition="merge" if you set a primary key. See incremental loading.

---

What does the generated OCRmyPDF pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading /ocr and /health from the OCRmyPDF API into DuckDB:

Copy
import dlt
from dlt.sources.rest_api import RESTAPIConfig, rest_api_resources

@dlt.source
def ocrmypdf_source():
    config: RESTAPIConfig = {
        "client": {
            "base_url": "N/A",
        },
        "resources": [
            
        ],
    }
    yield from rest_api_resources(config)


def load_ocrmypdf_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="ocrmypdf_pipeline",
        destination="duckdb",
        dataset_name="ocrmypdf_data",
    )
    load_info = pipeline.run(ocrmypdf_source())
    print(load_info)


if __name__ == "__main__":
    load_ocrmypdf_to_duckdb()

Run it with python ocrmypdf_pipeline.py. The agent iterates on this until it loads cleanly — you review and approve, rather than write it from scratch.

---

How do I query OCRmyPDF data in DuckDB?

dlt creates one table per resource. Query the loaded data with Python or SQL — or ask your agent to, through the MCP server's execute_sql_query tool.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("ocrmypdf_pipeline").dataset()
df = data.none.df()
print(df.head())

SQL:

Copy
SELECT * FROM ocrmypdf_data.none LIMIT 10;

See querying your data with dataset and exploring it in marimo notebooks.

---

How do I deploy the OCRmyPDF to DuckDB pipeline in production?

The pipeline runs locally, which is ideal for prototyping and one-off analysis. When you need it on a schedule, monitored on every load, and shared with your team, deploy the same dlt code on the dltHub platform — no infrastructure to maintain. The prompt above already ends with "run it on dltHub", so your agent can take it there directly.

• Deploy & schedule — run the pipeline as a managed job with automatic retries.
• Monitor — observable job queues, alerting, and load metrics for every run.
• Transform — promote raw OCRmyPDF loads into governed, documented models.
• Visualize & share — explore data in notebooks and publish live dashboards instead of static screenshots.

Book a demo →

---

What other destinations can I load OCRmyPDF data to?

dlt loads into any of these — only the destination argument changes:

Set dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. On the dltHub platform the same pipeline runs against a managed Iceberg lakehouse. See the full destinations list.

---

Next steps

• Ready for production? Book a demo of the dltHub platform →
• dlt LLM-native workflow docs
• REST API source reference
• Join the dlt community on Slack