Azure AI Python API Docs | dltHub

Azure AI Search is a fully managed cloud search service that provides indexing, querying, and AI enrichment over user-owned content. The REST API base URL is https://{search_service_name}.search.windows.net and All data-plane requests require an api-key header or a Bearer token (Microsoft Entra ID)..

dlt is an open-source Python library that handles authentication, pagination, and schema evolution automatically. dlthub provides AI context files that enable code assistants to generate production-ready pipelines. Install with uv pip install "dlt[workspace]" and start loading Azure AI data in under 10 minutes.

---

What data can I load from Azure AI?

Here are some of the endpoints you can load from Azure AI:

---

How do I authenticate with the Azure AI API?

Use key-based auth by sending the api-key header with an Admin key (read/write) or Query key (read-only). Alternatively, use Microsoft Entra ID bearer tokens in the Authorization header when role-based access is enabled. Requests must include api-version query parameter.

1. Get your credentials

1. Sign in to the Azure Portal (https://portal.azure.com). 2) Create or open your Search/Cognitive Search (Azure AI Search) resource. 3) Go to Settings -> Keys (or "Keys and Endpoint") to view primary/secondary Admin keys and Query keys. 4) Optionally create query keys via the portal or the Management REST API. 5) For role-based auth, configure Azure AD roles and obtain an access token using OAuth2 (client credentials) to use in Authorization: Bearer .

2. Add them to .dlt/secrets.toml

Copy
[sources.azure_ai_source]
api_key = "YOUR_SEARCH_API_KEY_HERE"

dlt reads this automatically at runtime — never hardcode tokens in your pipeline script. For production environments, see setting up credentials with dlt for environment variable and vault-based options.

---

How do I set up and run the pipeline?

Set up a virtual environment and install dlt:

Copy
uv venv && source .venv/bin/activate
uv pip install "dlt[workspace]"

1. Install the dlt AI Workbench:

Copy
dlt ai init --agent <your-agent> # <agent>: claude | cursor | codex

This installs project rules, a secrets management skill, appropriate ignore files, and configures the dlt MCP server for your agent. Learn more →

2. Install the rest-api-pipeline toolkit:

Copy
dlt ai toolkit rest-api-pipeline install

This loads the skills and context about dlt the agent uses to build the pipeline iteratively, efficiently, and safely. The agent uses MCP tools to inspect credentials — it never needs to read your secrets.toml directly. Learn more →

3. Start LLM-assisted coding:

Use /find-source to load data from the Azure AI API into DuckDB.

The rest-api-pipeline toolkit takes over from here — it reads relevant API documentation, presents you with options for which endpoints to load, and follows a structured workflow to scaffold, debug, and validate the pipeline step by step.

4. Run the pipeline:

Copy
python azure_ai_pipeline.py

If everything is configured correctly, you'll see output like this:

Copy
Pipeline azure_ai_pipeline load step completed in 0.26 seconds
1 load package(s) were loaded to destination duckdb and into dataset azure_ai_data
The duckdb destination used duckdb:/azure_ai.duckdb location to store data
Load package 1749667187.541553 is LOADED and contains no failed jobs

Inspect your pipeline and data:

Copy
dlt pipeline azure_ai_pipeline show

This opens the Pipeline Dashboard where you can verify pipeline state, load metrics, schema (tables, columns, types), and query the loaded data directly.

---

Python pipeline example

This example loads indexes and docs_search from the Azure AI API into DuckDB. It mirrors the endpoint and data selector configuration from the table above:

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

@dlt.source
def azure_ai_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://{search_service_name}.search.windows.net",
            "auth": {
                "type": "api_key",
                "api_key": api_key,
            },
        },
        "resources": [
            {"name": "indexes", "endpoint": {"path": "indexes?api-version={api-version}", "data_selector": "value"}},
            {"name": "docs_search", "endpoint": {"path": "indexes/{indexName}/docs?api-version={api-version}&search={query}", "data_selector": "value"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="azure_ai_pipeline",
        destination="duckdb",
        dataset_name="azure_ai_data",
    )
    load_info = pipeline.run(azure_ai_source())
    print(load_info)

To add more endpoints, append entries from the resource table to the "resources" list using the same name, path, and data_selector pattern.

---

How do I query the loaded data?

Once the pipeline runs, dlt creates one table per resource. You can query with Python or SQL.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("azure_ai_pipeline").dataset()
sessions_df = data.docs_search.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM azure_ai_data.docs_search LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("azure_ai_pipeline").dataset()
data.docs_search.df().head()

See how to explore your data in marimo Notebooks and how to query your data in Python with dataset.

---

What destinations can I load Azure AI data to?

dlt supports loading into any of these destinations — only the destination parameter changes:

Change the destination in dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. See the full destinations list.

---

Troubleshooting

Authentication failures

If you receive 401/403, check that you're sending the api-key header (api-key: ) for key-based auth or Authorization: Bearer for Azure AD. Admin operations require an Admin key; query operations can use a Query key. Regenerating both admin keys simultaneously will cause 403 until a valid key is restored.

Rate limits and throttling

Service may return 429 Too Many Requests when throttled. Implement exponential backoff and respect retry headers. Monitor request volumes and scale replica/partition counts as needed.

Pagination and result selectors

Most listing and search responses return arrays under the value key. Use the 'value' array as the records selector. For document search, each item may include system fields like '@search.score'. Use $skip/$top or continuation tokens per API version for pagination where applicable.

Ensure that the API key is valid to avoid 401 Unauthorized errors. Also, verify endpoint paths and parameters to avoid 404 Not Found errors.

---

Next steps

Continue your data engineering journey with the other toolkits of the dltHub AI Workbench:

• data-exploration — Build custom notebooks, charts, and dashboards for deeper analysis with marimo notebooks.
• dlthub-runtime — Deploy, schedule, and monitor your pipeline in production.

Copy
dlt ai toolkit data-exploration install
dlt ai toolkit dlthub-runtime install

• How to deploy a pipeline
• How to explore your data in marimo Notebooks
• How to query your data in Python with dataset
• Join the dlt community on Slack