Load Jina AI data to DuckDB

Jina AI is a Search Foundation providing embeddings, rerankers, classifiers and multimodal models for semantic search and retrieval. Everything needed to build a working Jina AI → 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 Jina AI 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 Jina AI 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 Jina AI 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.

---

Jina AI API at a glance

These values come from the Jina AI API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Jina AI API?

All requests require the Authorization header with a Bearer token in the format 'Bearer jina_YOUR_API_KEY'. You must also include 'Content-Type: application/json' and 'Accept: application/json' headers for standard requests.

1. Get your credentials

To obtain your Jina AI API key, visit the official Jina AI API dashboard at https://jina.ai/api-dashboard/. You can generate a free API key there to access their services. New users typically receive a complimentary token allowance. You can manage, monitor usage, or top up your account balance directly within the 'API Key & Billing' or 'Manage API Key' sections of the dashboard.

2. Add them to .dlt/secrets.toml

Copy
[sources.jina_ai_source]
api_key = "jina_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 Jina AI data can I load into DuckDB?

These are the Jina AI endpoints dlt can load into DuckDB:

---

How do I load only new Jina AI records?

Jina AI exposes model_id on v1/models, so dlt can request only the records that changed since the last run. Set it as the cursor_path and dlt tracks the high-water mark for you between runs.

Copy
{"name": "models", "endpoint": {
    "path": "v1/models",
    "data_selector": "models",
    "incremental": {"cursor_path": "model_id", "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 Jina AI pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading https://api.jina.ai/v1/embeddings and https://r.jina.ai/ from the Jina AI API into DuckDB:

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

@dlt.source
def jina_ai_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.jina.ai",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "models", "endpoint": {"path": "v1/models", "data_selector": "models"}},
            {"name": "batch_status", "endpoint": {"path": "v1/batch/{batch_id}/status"}}
        ],
    }
    yield from rest_api_resources(config)


def load_jina_ai_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="jina_ai_pipeline",
        destination="duckdb",
        dataset_name="jina_ai_data",
    )
    load_info = pipeline.run(jina_ai_source())
    print(load_info)


if __name__ == "__main__":
    load_jina_ai_to_duckdb()

Run it with python jina_ai_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 Jina AI 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("jina_ai_pipeline").dataset()
df = data.models.df()
print(df.head())

SQL:

Copy
SELECT * FROM jina_ai_data.models LIMIT 10;

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

---

How do I deploy the Jina AI 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 Jina AI 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 Jina AI 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