# HKUSTDial/NL2SQL_Handbook

This is a continuously updated handbook for readers to easily track the latest Text-to-SQL techniques in the literature and provide practical guidance for researchers and practitioners.

Repository: https://github.com/HKUSTDial/NL2SQL_Handbook
Canonical: https://ross.abutalabs.com/products/nl2sql_handbook
Homepage: https://arxiv.org/abs/2408.05109
Language: Python
License Family: other
Topics: llms, nl2sql, nlp, text-to-sql, awesome, nl-to-code, text2sql, ai4db, text-to-code, db, nl-to-sql, awesome-agents, awesome-nl2sql, awesome-text-to-sql, awesome-text2sql
Last push: 2026-07-28T08:54:04+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 35, longevity 59
- inputs: {"age_days": 834, "days_push": 36, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1575, forks 97 (observed 2026-08-28T04:05:05.742560+00:00)

## What it is
A continuously updated handbook and survey repository tracking the latest Text-to-SQL (NL2SQL) techniques, accompanying TKDE'25 and VLDB'24 survey papers. It curates research papers, benchmarks, evaluation methods, and practical guidance for translating natural language into SQL using LLMs.

## Use cases
- track the latest text-to-sql research papers
- find benchmarks for evaluating nl2sql systems
- learn how llms translate natural language to sql
- choose a text-to-sql approach for my application
- survey of text-to-sql in the era of llms
- find datasets for training text-to-sql models
- understand error analysis in nl2sql systems

## When to choose
- you need a curated, continuously updated overview of Text-to-SQL research and benchmarks
- you are a researcher surveying LLM-based NL2SQL techniques
- you are a practitioner deciding which Text-to-SQL solution fits your scenario

## When to avoid
- you need a runnable Text-to-SQL tool or library rather than a reading list
- you need production NL2SQL code - use the companion NL2SQL360 repo or a framework instead

## Facets
- artifact type: learning-resource
- maturity: active
- function: nlp, database, documentation, benchmarking
- domain: databases, large-language-models, tutorials, awesome-lists
- platform: python
- tags: text-to-sql, nl2sql, survey, handbook, llm, awesome-list, research-papers, benchmarks, natural-language-processing

## Member repositories
- HKUSTDial/NL2SQL_Handbook (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.742560+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:57:34.590788+00:00, confidence not recorded.
  - readme: https://github.com/HKUSTDial/NL2SQL_Handbook (fetched 2026-08-28T04:05:05.742560+00:00, sha dd24310a0733)
  - homepage: https://arxiv.org/abs/2408.05109 (fetched 2026-08-29T11:27:48.568319+00:00, sha faa70b90ca3c)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:27:48.577373+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:27:48.581128+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:27:48.583051+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:27:48.579283+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.