Explore tweets tagged as #text2sql
@9hills
九原客
1 month
Google 推出的 MCP for 数据库,但是和直接开放SQL不同,而是自定义tools封装SQL,实际上更可靠,生产可用。. 不要开发所谓的AI问数(自由的Text2SQL)系统,以后找个机会说说里面的坑。.
Tweet media one
26
63
398
@withmartian
Martian
21 days
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. 🧵👇
Tweet media one
19
10
43
@akshay_pachaar
Akshay 🚀
14 days
Text2SQL + RAG over docs, hybrid agentic workflow:
@akshay_pachaar
Akshay 🚀
15 days
Let's build a (Text2SQL + RAG), hybrid agentic workflow:.
6
70
335
@Subhash_Peshwa
Subhash Peshwa
8 months
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. 🧵
Tweet media one
11
54
315
@lianapatel_
Liana
6 months
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
Tweet media one
3
24
91
@gregschoeninger
Greg Schoeninger
3 months
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 👑
Tweet media one
27
99
1K
@ashpreetbedi
Ashpreet Bedi
4 months
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
272
@DailyDoseOfDS_
Daily Dose of Data Science
15 days
Text2SQL + RAG, hybrid agentic workflow, powered by Qwen3:
@akshay_pachaar
Akshay 🚀
15 days
Let's build a (Text2SQL + RAG), hybrid agentic workflow:.
5
33
154
@mdancho84
🔥 Matt Dancho (Business Science) 🔥
5 months
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:
Tweet media one
5
89
392
@gregschoeninger
Greg Schoeninger
3 months
Evaluating Text2SQL is low key kind of hard
Tweet media one
1
0
15
@mdancho84
🔥 Matt Dancho (Business Science) 🔥
1 month
🔥 Text2SQL just got WILD. + Llama 3.1 turns your questions into SQL queries in Python for FREE. Here's how: 🧵
Tweet media one
3
52
163
@llama_index
LlamaIndex 🦙
5 days
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
Tweet media one
6
54
264
@oxen_ai
oxen.ai
1 year
Ever wish you could just talk to your data? With Oxen's new Text2SQL generator, you no longer have to go through the pain of writing your SQL queries. Here's a quick example 👇
1
0
5
@MeetHubble
Hubble AI 🦉✨🔭
29 days
🦉 Hubble AI Weekly Update.Another week of pushing on-chain analytics forward - here's what we've been building:. 🔹 Text2SQL Agent New Webpage Available to Clients.Query & visualize Solana data in plain language with our AI Assistant. 🔹 Enterprise Momentum.Deep-diving with
1
1
11
@itsSandraKublik
Sandra Kublik
8 months
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.
Tweet media one
2
11
60
@vysakh0
Vysakh Sreenivasan
1 year
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
@NirantK
Nirant
1 year
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!
Tweet media one
11
19
176
@gregschoeninger
Greg Schoeninger
1 year
Our Text2SQL engine makes me laugh at the ridiculous SQL it writes 😂 not wrong…LGTM, ship it.
Tweet media one
2
0
2
@Subhash_Peshwa
Subhash Peshwa
8 months
2024 State of LLMs for Text2SQL Tasks 🏆- Updated with Cohere R7B. @cohere Command R7B is a 7B param model that's out-performing the latest 14B models and the coming in very close to Claude-3.5 Haiku! . Whatever is going into making a model enterprise ready is working here.
Tweet media one
2
7
31