What is text-to-SQL? Natural language queries with LLMs
Text-to-SQL uses an LLM to turn a plain-English question into a SQL query for your database. How it works, the benchmarks, and the guardrails, with Python.
Tags
7 posts tagged
Text-to-SQL uses an LLM to turn a plain-English question into a SQL query for your database. How it works, the benchmarks, and the guardrails, with Python.
Synthetic data is training data written by a model, not people. How LLM labs generate and verify it, why model collapse happens, with a Python demo.
Apache Iceberg is an open table format that turns files in object storage into tables with snapshots, ACID commits and time travel. How it works, in Python.
DuckDB is an in-process SQL database built for analytics: no server, a columnar engine, and direct queries over Parquet and CSV. How it works, when to use it.
pgvector is a Postgres extension that stores embeddings and runs nearest-neighbor search in SQL. Types, operators, HNSW vs IVFFlat and the filtering trap.
A vector database stores embeddings and finds the nearest ones to a query fast. How ANN indexes trade recall for speed, with a runnable Python IVF demo.
A CRDT is a data type that copies can edit independently and always merge to the same state. How CRDTs work, why local-first apps use them, with Python code.