Latest posts tagged with #TextToSql on Bluesky
WrenAI turns natural language into SQL queries, charts, and business insights in seconds - no more h
WrenAI turns natural language into SQL queries, charts, and business insights in seconds - no more hunting down that one person who knows how to write JOINs
🔗 https://github.com/Canner/WrenAI
#GenBI #TextToSQL #BusinessIntelligence
Graph-Reward-SQL Improves Text-to-SQL RL without Execution Overhead
Graph-Reward‑SQL replaces execution‑based rewards with a graph‑matching model, cutting latency and GPU memory while boosting accuracy on Spider and BIRD benchmarks. getnews.me/graph-reward-sql-improve... #graphrewardsql #texttosql
Framework Improves LLM Text-to-SQL Parsing Using Knowledge
Researchers evaluated a framework on eleven real‑world schemas from finance, healthcare and e‑commerce, using five LLMs, and reported exact‑match SQL accuracy via simple sub‑string knowledge retrieval. getnews.me/framework-improves-llm-t... #texttosql #llm
LLMSQL: A Refreshed Benchmark for Text-to-SQL in the LLM Era
LLMSQL refreshes WikiSQL with clean natural‑language questions and plain‑text SQL queries, fixing case and syntax errors. Gemma 3 and OpenAI o4‑mini achieved the highest exact‑match scores. getnews.me/llmsql-a-refreshed-bench... #llmsql #texttosql #llm
Agentar-Scale-SQL Enhances Text-to-SQL via Orchestrated Scaling
The new Agentar‑Scale‑SQL framework boosts text‑to‑SQL accuracy to 81.67% execution accuracy on the BIRD benchmark, taking the top spot on the official leaderboard. Read more: getnews.me/agentar-scale-sql-enhanc... #texttosql #bird #agentsql
Multilingual Text-to-SQL Benchmark Shows AI Gap with MultiSpider 2.0
The new MultiSpider 2.0 benchmark adds eight languages—including Japanese and Vietnamese—to the Spider 2.0 suite, and top LLMs saw execution accuracy fall to just 4%. getnews.me/multilingual-text-to-sql... #multispider2 #texttosql #multilingual
Agentar-Scale-SQL Improves Text-to-SQL with Orchestrated Scaling
Agentar-Scale-SQL achieved an 81.67 % execution accuracy on the BIRD benchmark, claiming first place, with the study submitted in September 2025 using three coordinated scaling techniques. getnews.me/agentar-scale-sql-improv... #texttosql #birdbenchmark
ScenarioBench: Traceable Benchmark for Text‑to‑SQL and RAG
ScenarioBench, a new Text‑to‑SQL and RAG compliance benchmark, was accepted for presentation at the LLMs Meet Databases workshop of the 35th IEEE International Conference. 29 Sep 2025. getnews.me/scenariobench-traceable-... #scenariobench #texttosql #rag
BiomedSQL Benchmark Challenges AI Text-to-SQL for Biomedical Research
BiomedSQL, a benchmark with 68,000 question‑SQL pairs for biomedical data, shows GPT‑o3‑mini at 59.0% execution accuracy, well below the 90% expert baseline. Read more: getnews.me/biomedsql-benchmark-chal... #biomedsql #texttosql
SteinerSQL Boosts Text-to‑SQL Accuracy with Graph‑Guided Reasoning
SteinerSQL's graph‑guided framework boosted text‑to‑SQL execution accuracy to 36.10% on LogicCat and 40.04% on Spider2.0‑Lite, outperforming prior methods. Read more: getnews.me/steinersql-boosts-text-t... #texttosql #graphoptimization
JOLT‑SQL Boosts Text‑to‑SQL with Confusion‑Aware Schema Sampling
JOLT‑SQL unifies schema linking and SQL generation, achieving state‑of‑the‑art accuracy on Spider and BIRD Text‑to‑SQL benchmarks. Code is open on GitHub. Read more: getnews.me/jolt-sql-boosts-text-to-... #joltsql #texttosql #nlp
GBV‑SQL Boosts Text‑to‑SQL Accuracy via Guided Generation
GBV‑SQL adds a back‑translation validation step, raising execution accuracy on the BIRD benchmark to 63.23% (a 5.8‑point gain) and reaching 96.5%/97.6% on Spider after removing Gold Errors. Read more: getnews.me/gbv-sql-boosts-text-to-s... #texttosql #gbvsql
Also, if you know of a good #TextToSQL package in #Node (#Javascript/#Typescript), can you let me know? :)
I'm on the hunt for a #TextToSql package for #Node. That is, an #npm package that takes an #SQL database, analyzes its structure, and can then transform natural language input into a query, run it, and bring me back the results.
Although it's #Python and so […]
[Original post on mastodon.online]
Just fine-tuned a text-to-SQL Gemma model using NVIDIA NIMs after days of chasing A100s across cloud providers 😅 and made a Chrome plugin. Check it out here - www.linkedin.com/posts/gbenga...
#AI #LLM #TextToSQL #Gemma #MLOps
📊📰 Build an AI-powered text-to-SQL chatbot using Amazon Bedrock, Amazon MemoryDB, and Amazon RDS
ift.tt/LD8Xz5b
#aws #DataDriven #SQL #AmazonRDS #GenerativeAI #TextToSQL
🚀📝 Dynamic text-to-SQL for enterprise workloads with Amazon Bedrock Agents
#GenerativeAI #TextToSQL #AmazonBedrock #DataInsights #CloudComputing
XiYan-SQL Revolutionizes NL2SQL Tasks with State-of-the-Art Framework 🚀📊✨ www.azoai.com/news/2024112... #AI #SQL #NaturalLanguage #MachineLearning #DatabaseInnovation #TextToSQL #DataAnalytics #TechResearch #FutureTech #NL2SQL
Meta Llama 3 Enhances Text-to-SQL Accuracy With Advanced Prompt Engineering and AWS Integration 🔍💡📊 www.azoai.com/news/2024090... #MetaLlama3 #TextToSQL #AIInnovation #PromptEngineering #ChromaDB #AWS #GenerativeAI #SQLQueries #MachineLearning #DataAccess
