Load Free OLM OCR data to DuckDB

Free OLM OCR is an AI-powered document understanding service that extracts text, images, tables, and formulas from PDFs and images. Everything needed to build a working Free OLM OCR → 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 Free OLM OCR 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 Free OLM OCR 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 Free OLM OCR 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.

---

Free OLM OCR API at a glance

These values come from the Free OLM OCR API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Free OLM OCR API?

The API supports authentication via an 'x-api-key' header or an 'Authorization: Bearer ' header.

1. Get your credentials

To obtain API credentials for Free OLM OCR, navigate to the official website (freeolmocr.com), create or sign in to your user account, and locate the settings or dashboard page where you can generate a new API key.

2. Add them to .dlt/secrets.toml

Copy
[sources.free_olm_ocr_source]
api_key = "your_api_key_here"

dlt reads this file automatically at runtime. With the harness, the setup-secrets skill prompts you for the values and never handles the raw credential in chat. For production, see setting up credentials with dlt.

---

What Free OLM OCR data can I load into DuckDB?

These are the Free OLM OCR endpoints dlt can load into DuckDB:

---

How do I load only new Free OLM OCR records?

The Free OLM OCR 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": "ocr_process", "endpoint": {
    "path": "ocr/process",
    # 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 Free OLM OCR pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading mcp and ocr/process from the Free OLM OCR API into DuckDB:

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

@dlt.source
def free_olm_ocr_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://www.freeolmocr.com/api",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "ocr_process", "endpoint": {"path": "ocr/process"}},
            {"name": "mcp_tools_list", "endpoint": {"path": "mcp"}}
        ],
    }
    yield from rest_api_resources(config)


def load_free_olm_ocr_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="free_olm_ocr_pipeline",
        destination="duckdb",
        dataset_name="free_olm_ocr_data",
    )
    load_info = pipeline.run(free_olm_ocr_source())
    print(load_info)


if __name__ == "__main__":
    load_free_olm_ocr_to_duckdb()

Run it with python free_olm_ocr_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 Free OLM OCR 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("free_olm_ocr_pipeline").dataset()
df = data.ocr_process.df()
print(df.head())

SQL:

Copy
SELECT * FROM free_olm_ocr_data.ocr_process LIMIT 10;

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

---

How do I deploy the Free OLM OCR 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 Free OLM OCR 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 Free OLM OCR 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