Explore tweets tagged as #Text2SQL
Text2SQL + RAG, hybrid agentic workflow, powered by Qwen3:
Let's build a (Text2SQL + RAG), hybrid agentic workflow:.
5
33
156
Took me ~10 minutes to fine-tune Qwen-0.6B on Text2SQL and beat GPT-4.1 accuracy on the same task. Qwen is a smol but mighty king 👑
27
99
1K
Announcing a research preview and a new paper!. `martian/code` uses MI research to out-perform existing models on codegen: (openai-api compatible). One focus: text2sql. A peek behind the research preview: TinySQL, a paper on how models generate SQL. 🧵👇
18
10
42
基于大模型和RAG的一款智能text2sql系统：SQLBot，可以帮你用自然语言查询数据库. 它可以把问题转换成数据库能理解的SQL语句，再去数据库里执行查询，然后生成数据图表及分析. 获得基础图表结果后��支持进一步分析、解释、验证以及预测，也可以把多个问答对话构建成一个数据看板
3
41
171
Text2SQL + RAG over docs, hybrid agentic workflow:
Let's build a (Text2SQL + RAG), hybrid agentic workflow:.
6
70
334
Enterprise adoption of "vanilla" LLM use cases like Text2SQL requires good AI engineering. See this Prompt Journey diagram from @SwiggyTech — constrained environment with stable schemas, defined relationships, column names, and past queries — and still so much complexity!
11
19
176
2024 State of LLMs for Text2SQL Tasks 🏆- Full Report. 🥇 Overall Performance: @GoogleDeepMind Gemini-Exp-1206.🥇 Open Source Model: @Alibaba_Qwen 2.5-Coder:32b (Beats Sonnet 3.5 and on par with GPT-4o!). Disappointing performance by GPT-4o and 3.5 Sonnet on this task. 🧵
11
54
313
Build a hybrid agentic workflow combining RAG, Text2SQL and a system that intelligently routes between SQL databases and vector search based on the users query. This tutorial and example repository by @akshay_pachaar shows you how to:. · Implement query classification to route
6
52
265
Introducing SQrL - a Text2SQL Reasoning Agent built with GPT4.1 . It “thinks” before running SQL and "analyzes" the results of its queries to deliver the best possible answer to your questions. The video is 1x speed. Give it a try and let me know if you like it. Code below 👇
9
40
271
Opensource framework for you to build Data apps. Not a yet another text2sql thing. In this framework, there is framework to maintain your context layer. You get python SDK to integrate directly within your app and also REST APIs. To create customer facing chatbots or chat or
2
1
3
Our Text2SQL engine makes me laugh at the ridiculous SQL it writes 😂 not wrong…LGTM, ship it.
2
0
2
Some of the most exciting AI apps require LLM reasoning over large datasets at test time. For these types of NL questions, RAG or Text2SQL + your favorite LLM are simply not enough. Excited to announce our new leaderboard, from the TAG team at Stanford and Berkeley, to
3
24
92
Some of our interesting observations from working on multi-turn text2SQL: .- Data-efficient RL works pretty well: We did very typical GRPO settings; Just make sure to use "hard-enough" samples and no KL. KL can stabilize learning early on but will always bring down rewards.
1/N Introducing SkyRL-SQL, a simple, data-efficient RL pipeline for Text-to-SQL that trains LLMs to interactively probe, refine, and verify SQL queries with a real database. 🚀 Early Result: trained on just ~600 samples, SkyRL-SQL-7B outperforms GPT-4o, o4-mini, and SFT model
0
6
18
Command 7b is looking really strong among these bigger models in text2SQL 💪 Excited to see what new analytics agents the community will build in 2025.
2
12
61
2024 State of LLMs for Text2SQL Tasks 🏆- Sneak Peak. Can you guess who's come out on top? Is it @OpenAI , @AnthropicAI , @GoogleDeepMind. Bonus points for guessing where @Alibaba_Qwen is at!. Hint: All open source models are <= 14B 🤫
13
14
98
Move over Tableau and PowerBI. There's a new Python library that automates Business Intelligence with AI using Text2SQL. Let me introduce you to WrenAI:
5
90
392