gopidesupavan opened a new pull request, #62640: URL: https://github.com/apache/airflow/pull/62640
### Summary This PR extends `LLMSQLQueryOperator` https://github.com/apache/airflow/pull/62599 to support querying data stored in object storage (S3, local filesystem, etc.) by integrating with the DataFusion engine. The operator can now introspect schemas from both traditional databases **and** object storage sources, enabling the LLM to generate SQL that spans across both. Additionally, the generated SQL can be executed directly against object storage data using `AnalyticsOperator`, creating a complete natural-language-to-results pipeline over data lakes. ### Usage Example ``` from airflow.providers.common.ai.operators.llm_sql import LLMSQLQueryOperator from airflow.providers.common.sql.config import DataSourceConfig from airflow.providers.common.sql.operators.analytics import AnalyticsOperator datasource_config = DataSourceConfig( conn_id="aws_default", table_name="sales_data", uri="s3://my-bucket/data/sales/", format="parquet", ) # Step 1: Generate SQL from natural language generate_sql = LLMSQLQueryOperator( task_id="generate_sql", prompt="Find the top 5 products by total sales amount", llm_conn_id="pydantic_ai_default", datasource_config=datasource_config, ) # Step 2: Execute the generated SQL against object storage run_query = AnalyticsOperator( task_id="run_query", datasource_configs=[datasource_config], queries=["{{ ti.xcom_pull(task_ids='generate_sql') }}"], ) generate_sql >> run_query ``` <!-- SPDX-License-Identifier: Apache-2.0 https://www.apache.org/licenses/LICENSE-2.0 --> <!-- Thank you for contributing! Please provide above a brief description of the changes made in this pull request. Write a good git commit message following this guide: http://chris.beams.io/posts/git-commit/ Please make sure that your code changes are covered with tests. And in case of new features or big changes remember to adjust the documentation. Feel free to ping (in general) for the review if you do not see reaction for a few days (72 Hours is the minimum reaction time you can expect from volunteers) - we sometimes miss notifications. In case of an existing issue, reference it using one of the following: * closes: #ISSUE * related: #ISSUE --> --- ##### Was generative AI tooling used to co-author this PR? <!-- If generative AI tooling has been used in the process of authoring this PR, please change below checkbox to `[X]` followed by the name of the tool, uncomment the "Generated-by". --> - [ ] Yes (please specify the tool below) <!-- Generated-by: [Tool Name] following [the guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#gen-ai-assisted-contributions) --> --- * Read the **[Pull Request Guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#pull-request-guidelines)** for more information. Note: commit author/co-author name and email in commits become permanently public when merged. * For fundamental code changes, an Airflow Improvement Proposal ([AIP](https://cwiki.apache.org/confluence/display/AIRFLOW/Airflow+Improvement+Proposals)) is needed. * When adding dependency, check compliance with the [ASF 3rd Party License Policy](https://www.apache.org/legal/resolved.html#category-x). * For significant user-facing changes create newsfragment: `{pr_number}.significant.rst` or `{issue_number}.significant.rst`, in [airflow-core/newsfragments](https://github.com/apache/airflow/tree/main/airflow-core/newsfragments). -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
