ๆญฃๅœจๅŠ ่ฝฝ่ง†้ข‘...

่ง†้ข‘ๅŠ ่ฝฝๅคฑ่ดฅ

่ฟ”ๅ›ž้ฆ–้กต

๐Ÿ†• Introducing PrismaGPT, a query helper built on GPT-4 ๐ŸŽ‰ * Drop in your Prisma schema * Ask for what you want * Get back a Prisma Client query and raw SQL Great for when you know what you need but aren't quite sure how to construct the query ๐Ÿ‘

ryanchenkie's profile picture

Ryan Chenkie

10,928 subscribers

94,182 ๆฌก่ง‚็œ‹ โ€ข 3 ๅนดๅ‰ โ€ขvia X (Twitter)

็ง‘ๅญฆๆŠ€ๆœฏๆ–ฐ้—ปๆ”ฟๆฒปๆ•™่‚ฒ
LIVE

Anya Rossiโ€ข Live Now

Private livecam show

10 ๆก่ฏ„่ฎบ

Matija Sosic ็š„ๅคดๅƒ
Matija Sosic3 ๅนดๅ‰

@prisma nice one! If you're looking for an OSS template to build sth similar, we just released one yesterday (React/Node/Prisma + GPT integration): It already got >100โญ๏ธ on gh!

Tim Petri ็š„ๅคดๅƒ
Tim Petri3 ๅนดๅ‰

@prisma This would be awesome as a vs code extension instead of a website where I have to upload (and reupload) my schema.

Ryan Chenkie ็š„ๅคดๅƒ
Ryan Chenkie3 ๅนดๅ‰

@prisma VS Code extension would be cool. I'll look into that. I'll also add something to keep the schema in local storage.

Manish Dalal ็š„ๅคดๅƒ
Manish Dalal3 ๅนดๅ‰

@prisma Have a look at use gpt to create schema, build query and generate CRUD query code!

Alex Ruheni ็š„ๅคดๅƒ
Alex Ruheni3 ๅนดๅ‰

@prisma This looks really awesome @ryanchenkie! ๐ŸŽ‰ Would you like to join us tomorrow on "What's New In Prisma" to showcase PrismaGPT?

Theral Moyo ็š„ๅคดๅƒ
Theral Moyo3 ๅนดๅ‰

@prisma This is so sick, will be featuring it in my AI newsletter tomorrow. Getting sent to 4000 people

Ryan Chenkie ็š„ๅคดๅƒ
Ryan Chenkie3 ๅนดๅ‰

@prisma Many thanks!

Jan Wilhelm ็š„ๅคดๅƒ
Jan Wilhelm3 ๅนดๅ‰

@prisma If you are using Metabase and want a similar SQL-generating feature, have a look at @AvantyApp

Mike @ HTML All The Things ๐Ÿ‡จ๐Ÿ‡ฆ ็š„ๅคดๅƒ
Mike @ HTML All The Things ๐Ÿ‡จ๐Ÿ‡ฆ3 ๅนดๅ‰

@prisma This is awesome! Love that it gives both Prisma client and SQL. Probably going to use that with planetscale's database.js lib.

Jens Neuse | Founder @ WunderGraph ็š„ๅคดๅƒ
Jens Neuse | Founder @ WunderGraph3 ๅนดๅ‰

@prisma The next step is to ask GPT to just generate code that does what you need, without an ORM. ๐Ÿ˜…

็›ธๅ…ณ่ง†้ข‘

Quick demo of Zeroโ€™s new background queries. Zeroโ€™s sync is query-based. Rather than specifying what data you want using rules or some other separate system, you just use queries. Right inside the client app, you do a query using a full sql-style language. You get filters, subqueries , limits, etc. Zero syncs the data backing these queries to the client. Itโ€™s important to realize Zero isnโ€™t really a cache. Itโ€™s a replica. Itโ€™s eagerly replicating a precise snapshot of a slice of your database - the slice covered by the queries you have open. So there is never stale data in Zero. When you close a query we delete the rows uniquely returned by that query because we can no longer keep them up to date. Of course that kind of sucks for the common case of doing a query, navigating, then pressing โ€œbackโ€. Ideally we want that back nav to be fast. To address this Zero 0.17 adds background queries. You can add a ttl to a query and it will keep running and syncing in the background. This is much different than normal caching because this data stays up to date. If you make the same query again, the results will be *instantly* available *and already up to date with server*. If you make a different query the data from the background query is used client-side to answer the new query instantly if possible. This all happens completely automatically. Just by adding the ttl flag.
1:01

Quick demo of Zeroโ€™s new background queries. Zeroโ€™s sync is query-based. Rather than specifying what data you want using rules or some other separate system, you just use queries. Right inside the client app, you do a query using a full sql-style language. You get filters, subqueries , limits, etc. Zero syncs the data backing these queries to the client. Itโ€™s important to realize Zero isnโ€™t really a cache. Itโ€™s a replica. Itโ€™s eagerly replicating a precise snapshot of a slice of your database - the slice covered by the queries you have open. So there is never stale data in Zero. When you close a query we delete the rows uniquely returned by that query because we can no longer keep them up to date. Of course that kind of sucks for the common case of doing a query, navigating, then pressing โ€œbackโ€. Ideally we want that back nav to be fast. To address this Zero 0.17 adds background queries. You can add a ttl to a query and it will keep running and syncing in the background. This is much different than normal caching because this data stays up to date. If you make the same query again, the results will be *instantly* available *and already up to date with server*. If you make a different query the data from the background query is used client-side to answer the new query instantly if possible. This all happens completely automatically. Just by adding the ttl flag.

Aaron Boodman

18,808 ๆฌก่ง‚็œ‹ โ€ข 1 ๅนดๅ‰

PEOPLE OF THE EARTH. Figured out how to ask natural language questions of current financial data and get back a natural language response...with correct/relevant numbers! ๐Ÿคฏ๐Ÿ’ฐโœจ So. Freaking. Cool. 1. Send database schema along with the question and relevant scope/parameters to GPT. 2. GPT returns SQL query. 3. Run SQL query on your data. 4. Take returned data and pass it in along with the original question. 5. GPT returns natural language answer with relevant data! Original Question: What was the highest price of Apple's stock over the past decade and how does it compare to Tesla's highest stock price? And on what date were those highest prices? Final Answer: The highest price of Apple's stock over the past decade was $182.94 on January 4, 2022, while Tesla's highest stock price was $414.50 on November 4, 2021.
3:23

PEOPLE OF THE EARTH. Figured out how to ask natural language questions of current financial data and get back a natural language response...with correct/relevant numbers! ๐Ÿคฏ๐Ÿ’ฐโœจ So. Freaking. Cool. 1. Send database schema along with the question and relevant scope/parameters to GPT. 2. GPT returns SQL query. 3. Run SQL query on your data. 4. Take returned data and pass it in along with the original question. 5. GPT returns natural language answer with relevant data! Original Question: What was the highest price of Apple's stock over the past decade and how does it compare to Tesla's highest stock price? And on what date were those highest prices? Final Answer: The highest price of Apple's stock over the past decade was $182.94 on January 4, 2022, while Tesla's highest stock price was $414.50 on November 4, 2021.

Josh Pigford

245,298 ๆฌก่ง‚็œ‹ โ€ข 3 ๅนดๅ‰

There are 5 million oil and gas wells across the US - but you want to know what's going on in your area. AI helps you cut through the noise. Draw a shape on the map, query the wells - AI tells you who's operating, what they're drilling, how deep they're going.
1:17

There are 5 million oil and gas wells across the US - but you want to know what's going on in your area. AI helps you cut through the noise. Draw a shape on the map, query the wells - AI tells you who's operating, what they're drilling, how deep they're going.

Kyle Walker

23,174 ๆฌก่ง‚็œ‹ โ€ข 4 ไธชๆœˆๅ‰

You can now chat directly with your Vercel Marketplace integrations. Ask questions, query data, or take action in plain English. Powered by MCP under the hood. Try it with Neon, Supabase, Dash0, Stripe, Prisma and Mux, and more coming soon โ†’
0:46

You can now chat directly with your Vercel Marketplace integrations. Ask questions, query data, or take action in plain English. Powered by MCP under the hood. Try it with Neon, Supabase, Dash0, Stripe, Prisma and Mux, and more coming soon โ†’

Vercel Developers

24,916 ๆฌก่ง‚็œ‹ โ€ข 5 ไธชๆœˆๅ‰

When CBI gives a green light to charge sheet you in cash-for-query scam but you have already married a senior advocate for this day Then you at your wedding reception ๐Ÿ˜‚:
2:10

When CBI gives a green light to charge sheet you in cash-for-query scam but you have already married a senior advocate for this day Then you at your wedding reception ๐Ÿ˜‚:

Monica Verma

40,826 ๆฌก่ง‚็œ‹ โ€ข 7 ไธชๆœˆๅ‰

AI tools you should know about 1. - Free Access to GPT-4; No Subscriptions, No Usage Limits, Share & earn 2. - Blog to video 3. - GitHub data explorer 4. - SQL queries for Prisma
0:43

AI tools you should know about 1. - Free Access to GPT-4; No Subscriptions, No Usage Limits, Share & earn 2. - Blog to video 3. - GitHub data explorer 4. - SQL queries for Prisma

Csaba Kissi

63,119 ๆฌก่ง‚็œ‹ โ€ข 2 ๅนดๅ‰

RouteLLM: Choose the Best LLM for Your Query! Use a single interface to access all state-of-the-art LLMs: - o1 for hard problems - Sonnet 3.5 for standard coding - GPT-4o for essays - Gemini Flash 2.0 for longer contexts Mix and match to use the best LLM for your query on ChatLLM.
0:57

RouteLLM: Choose the Best LLM for Your Query! Use a single interface to access all state-of-the-art LLMs: - o1 for hard problems - Sonnet 3.5 for standard coding - GPT-4o for essays - Gemini Flash 2.0 for longer contexts Mix and match to use the best LLM for your query on ChatLLM.

Akshay ๐Ÿš€

56,316 ๆฌก่ง‚็œ‹ โ€ข 1 ๅนดๅ‰

Have you ever been frustrated trying to find relevant web results for complex search queries? Introducing Deep Search, a new Bing feature which leverages GPT-4 to expand your query into many variations and multiple probable intents, so that you can find highly relevant results.
0:26

Have you ever been frustrated trying to find relevant web results for complex search queries? Introducing Deep Search, a new Bing feature which leverages GPT-4 to expand your query into many variations and multiple probable intents, so that you can find highly relevant results.

Jordi Ribas

23,613 ๆฌก่ง‚็œ‹ โ€ข 2 ๅนดๅ‰

RouteLLM is insanely good at picking the right model based on the context of the query. One of my favorite features of ChatLLM, it understands the query and routes perfectly: - o3 for complex. - GPT-4.1 for normal query. - 3.7 / Gemini 2.5 Pro for coding. Absolutely brilliant!
0:46

RouteLLM is insanely good at picking the right model based on the context of the query. One of my favorite features of ChatLLM, it understands the query and routes perfectly: - o3 for complex. - GPT-4.1 for normal query. - 3.7 / Gemini 2.5 Pro for coding. Absolutely brilliant!

AshutoshShrivastava

50,521 ๆฌก่ง‚็œ‹ โ€ข 1 ๅนดๅ‰

RouteLLM - Use The Best LLM For Your Query We have updated RouteLLM to route to all the SOTA LLMs o1 for hard problems Sonnet 3.5 for standard coding GPT-4o for essays Gemini Flash 2.0 for big context Mix and match to use the best LLM for your query on ChatLLM.
0:57

RouteLLM - Use The Best LLM For Your Query We have updated RouteLLM to route to all the SOTA LLMs o1 for hard problems Sonnet 3.5 for standard coding GPT-4o for essays Gemini Flash 2.0 for big context Mix and match to use the best LLM for your query on ChatLLM.

Bindu Reddy

17,230 ๆฌก่ง‚็œ‹ โ€ข 1 ๅนดๅ‰

"When you know exactly what you want and aren't afraid to ask for it. ๐Ÿ’…โœจ ๐ŸŽฌFoolsRushIn"
0:58

"When you know exactly what you want and aren't afraid to ask for it. ๐Ÿ’…โœจ ๐ŸŽฌFoolsRushIn"

HIL~LARY

120,228 ๆฌก่ง‚็œ‹ โ€ข 25 ๅคฉๅ‰

Your agents can't keep up with real-time data. Especially when it's scattered across dozens of sources. Most teams waste weeks building custom connectors for every database, API, and data warehouse. Then they build ETL pipelines to sync everything. By the time your agent retrieves the data, it's already outdated. Picture this: Your Postgres database updated 5 minutes ago. Your MongoDB collection changed 2 minutes ago. Your agent is still pulling from yesterday's snapshot. This is why most production RAG systems fail. There's a better approach: MindsDB is an open-source AI platform with a federated data engine that lets you query multiple data sources in real-time using SQL - without moving any data. Here's what makes it different: โ†ณ Your data stays in place. No ETL pipelines or data duplication โ†ณ Query Postgres, MongoDB, REST APIs, and more using consistent SQL โ†ณ JOIN across different sources in real-time with a unified interface โ†ณ Works with both structured and un-structured data And here's the best part: You don't even need to write SQL. Just describe what you want in plain English, and MindsDB converts it to SQL automatically. The system does all the heavy lifting. The breakthrough for AI agents is simple: When data updates at the source, your agent gets fresh results immediately. No sync delays. No stale embeddings. No custom code for each integration. You can literally write a SQL query that joins a Postgres table with a MongoDB collection and gets live results. This is what production AI applications need but rarely get. In this video, I give you a complete walkthrough of what we just discussed and how to actually do it. Make sure you watch this till the end. I've shared the link to MindsDB's GitHub repo in the next tweet!
9:28

Your agents can't keep up with real-time data. Especially when it's scattered across dozens of sources. Most teams waste weeks building custom connectors for every database, API, and data warehouse. Then they build ETL pipelines to sync everything. By the time your agent retrieves the data, it's already outdated. Picture this: Your Postgres database updated 5 minutes ago. Your MongoDB collection changed 2 minutes ago. Your agent is still pulling from yesterday's snapshot. This is why most production RAG systems fail. There's a better approach: MindsDB is an open-source AI platform with a federated data engine that lets you query multiple data sources in real-time using SQL - without moving any data. Here's what makes it different: โ†ณ Your data stays in place. No ETL pipelines or data duplication โ†ณ Query Postgres, MongoDB, REST APIs, and more using consistent SQL โ†ณ JOIN across different sources in real-time with a unified interface โ†ณ Works with both structured and un-structured data And here's the best part: You don't even need to write SQL. Just describe what you want in plain English, and MindsDB converts it to SQL automatically. The system does all the heavy lifting. The breakthrough for AI agents is simple: When data updates at the source, your agent gets fresh results immediately. No sync delays. No stale embeddings. No custom code for each integration. You can literally write a SQL query that joins a Postgres table with a MongoDB collection and gets live results. This is what production AI applications need but rarely get. In this video, I give you a complete walkthrough of what we just discussed and how to actually do it. Make sure you watch this till the end. I've shared the link to MindsDB's GitHub repo in the next tweet!

Akshay ๐Ÿš€

65,672 ๆฌก่ง‚็œ‹ โ€ข 7 ไธชๆœˆๅ‰

This Python script helps you better understand how embeddings work for SEO. Input a sentence + a query and BERT will calculate a content "Similarity Score": Search engines use embedding models to translate your content into numeric values. This is how they're able to mathematically determine whether a page on your site is actually relevant to a query someone is searching for. Once both the content and query are run through embeddings - they can calculate the "cosine similarity" or how similar the two entities are to each one. With this Python script, you can actually visualize how cosine similarity works for yourself. To you use you'll simply: 1. Save the Python script to a text file 2. Use your Terminal to run the script 3. You'll be prompted for both a "Sentence" and "Query" 4. Once entered, the script will calculate a "Similarity Score" between the text and query. This is how relevant your sentence is for the target keyword. By running this, you'll see that search engines are able to come with an calculation of content relevance. You'll need to think about the content on your site the same way - which sections have high scores and which ones have low ones? I've linked the Python script in the comments below. No coding knowledge is required and it walks you step by step on how to implement it.
2:37

This Python script helps you better understand how embeddings work for SEO. Input a sentence + a query and BERT will calculate a content "Similarity Score": Search engines use embedding models to translate your content into numeric values. This is how they're able to mathematically determine whether a page on your site is actually relevant to a query someone is searching for. Once both the content and query are run through embeddings - they can calculate the "cosine similarity" or how similar the two entities are to each one. With this Python script, you can actually visualize how cosine similarity works for yourself. To you use you'll simply: 1. Save the Python script to a text file 2. Use your Terminal to run the script 3. You'll be prompted for both a "Sentence" and "Query" 4. Once entered, the script will calculate a "Similarity Score" between the text and query. This is how relevant your sentence is for the target keyword. By running this, you'll see that search engines are able to come with an calculation of content relevance. You'll need to think about the content on your site the same way - which sections have high scores and which ones have low ones? I've linked the Python script in the comments below. No coding knowledge is required and it walks you step by step on how to implement it.

Chris Long

13,185 ๆฌก่ง‚็œ‹ โ€ข 1 ๅนดๅ‰

This is a tool that used GPT that lets you connect to PostgresDB or MongoDB, lets users type in questions, and it generates the query code (even advanced table joins), runs the code and returns the answer instantly. Like a query co-pilot. Here are my thoughts ๐Ÿ‘‡๐Ÿป
0:23

This is a tool that used GPT that lets you connect to PostgresDB or MongoDB, lets users type in questions, and it generates the query code (even advanced table joins), runs the code and returns the answer instantly. Like a query co-pilot. Here are my thoughts ๐Ÿ‘‡๐Ÿป

Duy

68,809 ๆฌก่ง‚็œ‹ โ€ข 3 ๅนดๅ‰

GraphQL to TypeScript type, no code gen. Written purely in TypeScript type. With Prisma-like query syntax fully type-safe. Should cover almost all of the GraphQL specs, now. Here's a demo.
1:45

GraphQL to TypeScript type, no code gen. Written purely in TypeScript type. With Prisma-like query syntax fully type-safe. Should cover almost all of the GraphQL specs, now. Here's a demo.

SaltyAom

100,697 ๆฌก่ง‚็œ‹ โ€ข 2 ๅนดๅ‰

Did you know that you can query your bill through *977#. This video explains the steps you can take to check your electricity bill.
0:31

Did you know that you can query your bill through *977#. This video explains the steps you can take to check your electricity bill.

Kenya Power

20,624 ๆฌก่ง‚็œ‹ โ€ข 1 ๅนดๅ‰

๐Ÿ†• We shipped an MCP server! You can new query your Readwise highlights inside of Claude, Cursor and more:
0:22

๐Ÿ†• We shipped an MCP server! You can new query your Readwise highlights inside of Claude, Cursor and more:

Readwise

59,060 ๆฌก่ง‚็œ‹ โ€ข 1 ๅนดๅ‰

DeFi data just became model-ready. Introducing Query Builder for DefiLlama Sheets. Instead of writing complex formulas or stitching together multiple queries, you can now pull exactly the data you want into Sheets or Excel in a few clicks. > Build spreadsheet formulas visually > Query multiple projects in a single request > Analyze historical metrics side by side with clean, consistent data
0:52

DeFi data just became model-ready. Introducing Query Builder for DefiLlama Sheets. Instead of writing complex formulas or stitching together multiple queries, you can now pull exactly the data you want into Sheets or Excel in a few clicks. > Build spreadsheet formulas visually > Query multiple projects in a single request > Analyze historical metrics side by side with clean, consistent data

DefiLlama.com

21,653 ๆฌก่ง‚็œ‹ โ€ข 4 ไธชๆœˆๅ‰

๐Ÿ’ก CSS Tip! A small tool to create a quantity query selector using has(). Adjust the setting and get your selector in no time! ๐Ÿ˜Ž I am trying a new kind of "interactive CSS Tip". Let me know what you think. Link in the reply ๐Ÿ‘‡
0:34

๐Ÿ’ก CSS Tip! A small tool to create a quantity query selector using has(). Adjust the setting and get your selector in no time! ๐Ÿ˜Ž I am trying a new kind of "interactive CSS Tip". Let me know what you think. Link in the reply ๐Ÿ‘‡

CSS by T. Afif

19,823 ๆฌก่ง‚็œ‹ โ€ข 1 ๅนดๅ‰

We're excited to announce duckdb-skills, a DuckDB plugin for Claude Code! We think the embedded nature of DuckDB makes it a perfect companion for Claude in your local workflows. The skills supported include: + read-file and query โ€“ uses DuckDB's CLI to query data locally, unlocking easy access to any file that DuckDB can read. + read-memories โ€“ a clever idea to store your Claude memories in DuckDB and query them at blazing speed. These are powered by two additional skills: + attach-db โ€“ gives Claude a mechanism to manage DuckDB state through a .sql file linked to your project. + duckdb-docs โ€“ uses a remote DuckDB full-text search database to query the DuckDB docs and answer all of your (and Claude's own) questions.
2:16

We're excited to announce duckdb-skills, a DuckDB plugin for Claude Code! We think the embedded nature of DuckDB makes it a perfect companion for Claude in your local workflows. The skills supported include: + read-file and query โ€“ uses DuckDB's CLI to query data locally, unlocking easy access to any file that DuckDB can read. + read-memories โ€“ a clever idea to store your Claude memories in DuckDB and query them at blazing speed. These are powered by two additional skills: + attach-db โ€“ gives Claude a mechanism to manage DuckDB state through a .sql file linked to your project. + duckdb-docs โ€“ uses a remote DuckDB full-text search database to query the DuckDB docs and answer all of your (and Claude's own) questions.

DuckDB

60,551 ๆฌก่ง‚็œ‹ โ€ข 3 ไธชๆœˆๅ‰