Load Alibaba Cloud OCR SDK data to DuckDB

Alibaba Cloud OCR API provides optical character recognition services to extract text from images and documents. Everything needed to build a working Alibaba Cloud OCR SDK → 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 Alibaba Cloud OCR SDK 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 Alibaba Cloud OCR SDK 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 Alibaba Cloud OCR SDK 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.

---

Alibaba Cloud OCR SDK API at a glance

These values come from the Alibaba Cloud OCR SDK API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Alibaba Cloud OCR SDK API?

Requests are authenticated using Alibaba Cloud AccessKey ID and AccessKey Secret, which are used to generate an Authorization header. The SDK automates this process by signing requests using HMAC-SHA256 (V3 signature).

1. Get your credentials

To obtain credentials for Alibaba Cloud services, log in to the Alibaba Cloud console. Navigate to the Resource Access Management (RAM) service. In the side navigation pane, select Users to find your specific user or select your primary account profile. Navigate to the Authentication or AccessKey tab, and click Create AccessKey. Ensure you save the AccessKey ID and AccessKey Secret immediately, as the secret cannot be retrieved after the creation dialog is closed. For production, it is recommended to use a RAM user with restricted permissions (e.g., AliyunOCRFullAccess) rather than the root account AccessKey.

2. Add them to .dlt/secrets.toml

Copy
[sources.alibaba_cloud_ocr_sdk_source]
ALIBABA_CLOUD_ACCESS_KEY_ID = "your_access_key_id_here"
ALIBABA_CLOUD_ACCESS_KEY_SECRET = "your_access_key_secret_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 Alibaba Cloud OCR SDK data can I load into DuckDB?

These are the Alibaba Cloud OCR SDK endpoints dlt can load into DuckDB:

---

How do I load only new Alibaba Cloud OCR SDK records?

The Alibaba Cloud OCR SDK 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": "recognize_all_text", "endpoint": {
    "path": "RecognizeAllText",
    # 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 Alibaba Cloud OCR SDK pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading ocr-api.cn-hangzhou.aliyuncs.com and ocr-api-vpc.cn-hangzhou.aliyuncs.com from the Alibaba Cloud OCR SDK API into DuckDB:

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

@dlt.source
def alibaba_cloud_ocr_sdk_source(alibaba_cloud_access_key_id_alibaba_cloud_access_key_secret=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "ocr-api.cn-hangzhou.aliyuncs.com",
            "auth": {"type": "bearer", "token": alibaba_cloud_access_key_id_alibaba_cloud_access_key_secret},
        },
        "resources": [
            {"name": "recognize_all_text", "endpoint": {"path": "RecognizeAllText"}},
            {"name": "recognize_table_ocr", "endpoint": {"path": "RecognizeTableOcr"}}
        ],
    }
    yield from rest_api_resources(config)


def load_alibaba_cloud_ocr_sdk_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="alibaba_cloud_ocr_sdk_pipeline",
        destination="duckdb",
        dataset_name="alibaba_cloud_ocr_sdk_data",
    )
    load_info = pipeline.run(alibaba_cloud_ocr_sdk_source())
    print(load_info)


if __name__ == "__main__":
    load_alibaba_cloud_ocr_sdk_to_duckdb()

Run it with python alibaba_cloud_ocr_sdk_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 Alibaba Cloud OCR SDK 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("alibaba_cloud_ocr_sdk_pipeline").dataset()
df = data.recognize_all_text.df()
print(df.head())

SQL:

Copy
SELECT * FROM alibaba_cloud_ocr_sdk_data.recognize_all_text LIMIT 10;

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

---

How do I deploy the Alibaba Cloud OCR SDK 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 Alibaba Cloud OCR SDK 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 Alibaba Cloud OCR SDK 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