Natural Language to SQL (NL2SQL) enables intuitive interactions with databases by transforming natural language queries into structured SQL statements. Despite recent advancements in enhancing human-c...

Previously on @thatjeffsmith... NL2SQL: Let’s put Opus 4.1 to task on my NETFLIX data

Learn why NL2SQL is useful for demos and development, but risky for production data. See how SQL MCP Server uses contracts, guardrails, and abstraction for safer agentic data access.

YouTube video by DataMonkey

Previously on @thatjeffsmith... NL2SQL: Let’s put Opus 4.1 to task on my NETFLIX data

Previously on @thatjeffsmith... NL2SQL: Let’s put Opus 4.1 to task on my NETFLIX data

Previously on @thatjeffsmith... NL2SQL is cool. Reports are trustworthy. You can have both!

Organizations struggle with AI agents processing both structured and unstructured data, as LLMs handle text well but falter with databases, while NL2SQL models can generate inaccurate queries. Gemini Enterprise offers a unified AI interface, now enhanced by Looker's governed semantic layer for trusted structured data. This integration allows Looker analysts to publish conversational agents directly into Gemini Enterprise via a secure A2A protocol. This empowers employees with real-time, natural language access to governed business intelligence, reducing friction and fostering a data-driven culture. Looker's semantic layer eliminates guesswork in data queries, preventing inconsistent metrics and AI hallucinations by providing codified context. When a Gemini Enterprise user requests a business KPI, a Looker agent generates precise SQL based on version-controlled business logic, ensuring deterministic and predictable results. This integration prioritizes robust governance and secure access, employing a zero-risk pass-through architecture that doesn't ingest or store user data. Data access is controlled through OAuth authorization and Looker's existing row- and column-level access policies, maintaining strict security isolation. Technical capabilities include rich visual interactivity with native charts and interoperability with other agents, enabling complex multi-agent workflows. A robust, identity-centric authentication model ensures every query is authenticated at the user level, enforcing existing permission structures. This integration brings trusted data analytics, visualizations, and data storytelling directly into users' daily workspaces, bringing operational metrics to life.

Contribute to Kurukshetran/nl2sql development by creating an account on GitHub.

Previously on @thatjeffsmith... NL2SQL: Let’s put Opus 4.1 to task on my NETFLIX data

The text discusses the advancement of text-to-SQL (NL2SQL) capabilities, where natural language translates into SQL queries, facilitating data access. Google Cloud achieved a state-of-the-art score on the BIRD benchmark, using a single model. The BIRD benchmark assesses NL2SQL solutions, focusing on execution-verified accuracy across diverse databases. This advancement, built upon a specialized Gemini model, improves customer experience in various data services. This includes enhanced natural language querying within AlloyDB AI and conversational analytics in BigQuery. Developers can use AI assistance, such as Google Code Assist, for efficient SQL code generation. The success stems from specialized model tuning including rigorous data filtering and multitask learning. Self-consistency at test time further boosted the model's accuracy. This improved model provides a strong foundation for future advancements in data services. It enables a more robust baseline for text-to-SQL capabilities. The improved model is now driving innovation in Google Data Cloud products, as exemplified by enhanced natural language querying within AlloyDB and BigQuery.

Researchers at Alibaba Group have developed XiYan-SQL, a cutting-edge framework combining multi-generator strategies and enhanced schema representation to achieve state-of-the-art performance in conve...

Learn how to build a governed natural-language query layer on top of an Apache Iceberg lakehouse using Amazon Bedrock, AWS Glue, Amazon Athena, and RAG. This architecture combines semantic metadata, NL2SQL, SQL validation, and data governance to let users interact with enterprise data using natural language while keeping the underlying data platform secure and auditable.

Better NL2SQL experiences with your AI Agents and your Oracle Databases are now available with better schema-information MCP Server tools with SQLcl.

Having an LLM generate SQL on your behalf is one of it's better party tricks. Let's see how it managed my family's online streaming historical data!

The integration of Large Language Models (LLMs) into enterprise database environments has fundamentally altered how users interact with structured data. This paper presents an imperative analysis of Oracle’s DBMS_CLOUD_AI package within the Autonomous Transaction Processing (ATP) ecosystem, evaluating its efficacy in Natural Language to SQL (NL2SQL) translation. By leveraging metadata-augmented prompts, the architecture mitigates hallucination risks inherent in zero-shot LLM queries. Furthermore, we examine the integration of these capabilities with Oracle Integration Cloud (OIC) to expose AI-driven data insights via RESTful services. We analyze the implementation methodology, execution modalities (showsql, runsql, narrate, explainsql), and critical data governance considerations when routing enterprise metadata to external AI providers such as Cohere and OpenAI.