Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

The most powerful SQLite database is a Cloudflare Developers Durable Object with row level security, query allowlist, data masking, REST API, web sockets + query caching. Today we're announcing Auth + RLS + Allowlist + Query Caching are available by default in StarbaseDB. Read more 🧵

Brayden

5,165 subscribers

20,431 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji Haberler & Politika

Anya Rossi• Live Now

Private livecam show

7 Yorum

Brayden Wilmoth profil fotoğrafı

Brayden Wilmoth1 yıl önce

StarbaseDB: Allowlist + RLS + Auth Example: Blog Post:

Brayden Wilmoth profil fotoğrafı

Brayden Wilmoth1 yıl önce

1. Query Caching Any request you make to your instance with the header "X-Starbase-Cache" in it will now automatically be cached for 60 seconds. Perfect for external data source use cases where connecting to Postgres, MySQL, Mongo or others and you want your data response cached on the edge. Early testing shows multi-second SQL requests going down to as little as ~50ms! Few caveats exist here including: - Response cached must be less than 1MiB (RPC restriction in Workers) - Query must not contain any modifying statements (SELECT only) - No dynamic parameters Many improvements to come here to improve all three of the above areas.

Brayden Wilmoth profil fotoğrafı

Brayden Wilmoth1 yıl önce

2. Allowlist You can now specify a specific list of queries that can be executed against your external data source to prevent users from trying to access data tables they shouldn't. This works when connecting StarbaseDB to other database viewers, or by hitting the endpoints your instance exposes. This feature is an essential piece to the puzzle for enabling executing SQL statements safely from the frontend and keeping security at the forefront.

Brayden Wilmoth profil fotoğrafı

Brayden Wilmoth1 yıl önce

3. Row Level Security A feature that is mostly touted as a core part of Postgres but always recommended to have a secondary layer in your application logic. Now as part of StarbaseDB it comes built in out of the box so you can define table policies that should exist. You can now query "SELECT * FROM todos;" and by design only get the todos that are relevant to the requesting user. When a policy exists on a table that indicates that RLS is turned "on" for that entire table. You can easily create rules for what operations can be performed. Again, another very important piece to the SQL from frontend goal. This feature is still in Early Access but want to give everyone the opportunity today to start working with it and providing feedback to us on how it should improve.

Brayden Wilmoth profil fotoğrafı

Brayden Wilmoth1 yıl önce

Lastly, all of this is still in EARLY ACCESS! More to come but we want to get this into peoples hands early and invite feedback. There will be quirks, limitations, and gotcha's I'm sure. The foundation has been set and now it is time for us to build & improve what we have. 🙏🚀

Sandrino Di Mattia profil fotoğrafı

Sandrino Di Mattia1 yıl önce

@CloudflareDev What are your thoughts on cost? Each time you query the DB it will count as 1 worker invocation, right?

Brayden Wilmoth profil fotoğrafı

Brayden Wilmoth1 yıl önce

@CloudflareDev 15,000,000 requests for $8 is a good problem to have in my books.

Benzer Videolar

Quick demo of Zero’s new background queries. Zero’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. It’s important to realize Zero isn’t really a cache. It’s a replica. It’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 “back”. 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.

Quick demo of Zero’s new background queries. Zero’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. It’s important to realize Zero isn’t really a cache. It’s a replica. It’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 “back”. 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 görüntüleme • 1 yıl önce

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 – uses DuckDB's CLI to query data locally, unlocking easy access to any file that DuckDB can read. + read-memories – 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 – gives Claude a mechanism to manage DuckDB state through a .sql file linked to your project. + duckdb-docs – uses a remote DuckDB full-text search database to query the DuckDB docs and answer all of your (and Claude's own) questions.

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 – uses DuckDB's CLI to query data locally, unlocking easy access to any file that DuckDB can read. + read-memories – 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 – gives Claude a mechanism to manage DuckDB state through a .sql file linked to your project. + duckdb-docs – uses a remote DuckDB full-text search database to query the DuckDB docs and answer all of your (and Claude's own) questions.

DuckDB

60,739 görüntüleme • 5 ay önce

Want cm-level accuracy in your app? Just API it. The GEODNET RTK API lets developers plug real-time, high-precision GNSS/RTK into drones, robots, mapping tools, and autonomous systems with a simple REST call. • Authenticate users • Query coverage • Get live base station data • Stream RTK corrections globally Build anything that needs precise location📍

Want cm-level accuracy in your app? Just API it. The GEODNET RTK API lets developers plug real-time, high-precision GNSS/RTK into drones, robots, mapping tools, and autonomous systems with a simple REST call. • Authenticate users • Query coverage • Get live base station data • Stream RTK corrections globally Build anything that needs precise location📍

GEODNET

32,595 görüntüleme • 9 ay önce

Today we are announcing Keenable AI, an AI-native index of the best human knowledge we have, starting with the open web. AI seems to know just about everything until you ask it about something you know deeply. The answer isn’t wrong, but it's just very average. We started Keenable to fix this problem: every model and every agent should be able to query, reason over, and continuously learn from the living web. Backed by a $26M Seed from Accel and Conviction. Built by the team that took on Google at Yandex Search, with researchers and engineers from Amazon AGI, X, and Perplexity. The Web Search API and Web Query Language for AI are live now. Together they make the web queryable at AI scale. Both are free until end of September. Seven days of benchmarks, stories, and launches ahead. Let your agents search.

Today we are announcing Keenable AI, an AI-native index of the best human knowledge we have, starting with the open web. AI seems to know just about everything until you ask it about something you know deeply. The answer isn’t wrong, but it's just very average. We started Keenable to fix this problem: every model and every agent should be able to query, reason over, and continuously learn from the living web. Backed by a $26M Seed from Accel and Conviction. Built by the team that took on Google at Yandex Search, with researchers and engineers from Amazon AGI, X, and Perplexity. The Web Search API and Web Query Language for AI are live now. Together they make the web queryable at AI scale. Both are free until end of September. Seven days of benchmarks, stories, and launches ahead. Let your agents search.

Andrey Styskin

539,902 görüntüleme • 10 gün önce

How Cloudflare cut query times by 35x without leaving Postgres: Their Postgres tables hit billions of rows, and every time-range query started getting slower. Plain Postgres scans the entire table on every query, regardless of the time window. They tried the manual route by building precomputed aggregates with cron jobs and evaluating ClickHouse, which needed a full ingestion pipeline just to handle their write pattern. Here's where most teams get stuck at exactly this point. They utilize manual partitioning, splitting data into child tables by day or month. Then they wire up cron jobs to refresh aggregate tables. Every schema change after that requires updating the cron logic and coordinating across teams. The infrastructure becomes the project. Tiger Cloud is managed TimescaleDB by Tiger Data - Creators of TimescaleDB on the Postgres you already know, with automatic time-based partitioning, continuous aggregates, and compression built in from the start. Cloudflare moved to TimescaleDB after exhausting the manual route and saw 5-35x query performance improvement on the same data. Here is how it works: → Hypertables partition data by timestamp automatically. Every time-range query hits only the relevant chunk, not the full table. → Continuous aggregates refresh incrementally in the background, with no cron jobs to maintain. To show what this looks like in practice, I built a real-time earthquake intelligence dashboard on a 3D globe using Claude Code and Tiger Cloud in a single session. The USGS earthquake catalog has 400,000+ events since 1900, each a timestamped row. The dashboard plots them as ripple animations sized by magnitude and colored by depth, with a time slider that scrubs through 120 years of seismic history. Every slider position fires a live query against the hypertable, and the side panel pulls from continuous aggregates. Claude Code connected to Tiger Cloud through the Tiger CLI MCP server, provisioned the database, pulled the USGS catalog, and assembled the full Next.js and Three.js frontend without leaving the session. The video below shows the final build in action, and I worked with the Tiger Data team to put this together. Tiger CLI is open-source (Apache 2.0) and works with Claude Code, Cursor, Codex, Gemini CLI, and VS Code. To try this yourself: → Sign up for Tiger Cloud here: New accounts get $1,000 in free credits, no credit card required. → Install Tiger CLI: curl -fsSL https(:)//cli(.)tigerdata(.)com | sh → Run tiger mcp install claude-code → Give Claude Code a prompt and let it build. I also wrote a full walkthrough on how you can turn any coding agent into a production-grade data engineer that can manage over a billion-row Postgres workloads. It covers everything from the database setup to the final build. Read it below.

How Cloudflare cut query times by 35x without leaving Postgres: Their Postgres tables hit billions of rows, and every time-range query started getting slower. Plain Postgres scans the entire table on every query, regardless of the time window. They tried the manual route by building precomputed aggregates with cron jobs and evaluating ClickHouse, which needed a full ingestion pipeline just to handle their write pattern. Here's where most teams get stuck at exactly this point. They utilize manual partitioning, splitting data into child tables by day or month. Then they wire up cron jobs to refresh aggregate tables. Every schema change after that requires updating the cron logic and coordinating across teams. The infrastructure becomes the project. Tiger Cloud is managed TimescaleDB by Tiger Data - Creators of TimescaleDB on the Postgres you already know, with automatic time-based partitioning, continuous aggregates, and compression built in from the start. Cloudflare moved to TimescaleDB after exhausting the manual route and saw 5-35x query performance improvement on the same data. Here is how it works: → Hypertables partition data by timestamp automatically. Every time-range query hits only the relevant chunk, not the full table. → Continuous aggregates refresh incrementally in the background, with no cron jobs to maintain. To show what this looks like in practice, I built a real-time earthquake intelligence dashboard on a 3D globe using Claude Code and Tiger Cloud in a single session. The USGS earthquake catalog has 400,000+ events since 1900, each a timestamped row. The dashboard plots them as ripple animations sized by magnitude and colored by depth, with a time slider that scrubs through 120 years of seismic history. Every slider position fires a live query against the hypertable, and the side panel pulls from continuous aggregates. Claude Code connected to Tiger Cloud through the Tiger CLI MCP server, provisioned the database, pulled the USGS catalog, and assembled the full Next.js and Three.js frontend without leaving the session. The video below shows the final build in action, and I worked with the Tiger Data team to put this together. Tiger CLI is open-source (Apache 2.0) and works with Claude Code, Cursor, Codex, Gemini CLI, and VS Code. To try this yourself: → Sign up for Tiger Cloud here: New accounts get $1,000 in free credits, no credit card required. → Install Tiger CLI: curl -fsSL https(:)//cli(.)tigerdata(.)com | sh → Run tiger mcp install claude-code → Give Claude Code a prompt and let it build. I also wrote a full walkthrough on how you can turn any coding agent into a production-grade data engineer that can manage over a billion-row Postgres workloads. It covers everything from the database setup to the final build. Read it below.

Avi Chawla

22,094 görüntüleme • 18 gün önce

60-Second SEO: All SEOs should be using the Google Ads "Search Keywords" report to immediately discover the most valuable queries for a business: Google Ads is the only place that you can get actual conversion data at the query level. The sad part is, this is a heavily underutilized report by many in the SEO community. By utilizing PPC data, you're able to see actual data around which queries are the most valuable for your business. To use it requires SEOs to be brave and venture into the Google Ads platform:

60-Second SEO: All SEOs should be using the Google Ads "Search Keywords" report to immediately discover the most valuable queries for a business: Google Ads is the only place that you can get actual conversion data at the query level. The sad part is, this is a heavily underutilized report by many in the SEO community. By utilizing PPC data, you're able to see actual data around which queries are the most valuable for your business. To use it requires SEOs to be brave and venture into the Google Ads platform:

Chris Long

20,901 görüntüleme • 2 yıl önce

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: ↳ Your data stays in place. No ETL pipelines or data duplication ↳ Query Postgres, MongoDB, REST APIs, and more using consistent SQL ↳ JOIN across different sources in real-time with a unified interface ↳ 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!

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: ↳ Your data stays in place. No ETL pipelines or data duplication ↳ Query Postgres, MongoDB, REST APIs, and more using consistent SQL ↳ JOIN across different sources in real-time with a unified interface ↳ 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 🚀

65,672 görüntüleme • 9 ay önce

$Google open-sourced MCP Toolbox for Databases. I gave it access to everything else. For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol However, most enterprise knowledge doesn't actually live in databases. It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs. So Agents can't see any of it, which means they're working with a fraction of the context they need. I fixed that using MindsDB. It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured. This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax. The clever part is how it connects to the MCP Toolbox. MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back. It doesn't know or care that the data came from five different sources behind the scenes. This setup unlocks some powerful capabilities: → One SQL interface for dozens of enterprise sources → Cross-datasource joins (combine GitHub and CRM data in a single query) → Built-in ML capabilities for working with unstructured data → Simple MCP tools that now have massively expanded reach In the video below, the Agent queries GitHub data and a customer review database in one SQL query. So what used to require ETL pipelines and weeks of engineering effort now happens instantly. At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with. I have shared the GitHub repo in the replies, where you can find more details about this.$

Google open-sourced MCP Toolbox for Databases. I gave it access to everything else. For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol However, most enterprise knowledge doesn't actually live in databases. It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs. So Agents can't see any of it, which means they're working with a fraction of the context they need. I fixed that using MindsDB. It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured. This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax. The clever part is how it connects to the MCP Toolbox. MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back. It doesn't know or care that the data came from five different sources behind the scenes. This setup unlocks some powerful capabilities: → One SQL interface for dozens of enterprise sources → Cross-datasource joins (combine GitHub and CRM data in a single query) → Built-in ML capabilities for working with unstructured data → Simple MCP tools that now have massively expanded reach In the video below, the Agent queries GitHub data and a customer review database in one SQL query. So what used to require ETL pipelines and weeks of engineering effort now happens instantly. At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with. I have shared the GitHub repo in the replies, where you can find more details about this.

Akshay 🚀

40,562 görüntüleme • 6 ay önce

Most people think Rerun is a visualization tool. In reality, it's a database masquerading as a visualizer. I wanted to showcase this functionality by building a full data pipeline consisting of: ingestion → baseline method → eval → finetuning for SLAM on egocentric data. I'll eventually extend this to the rest of my ego/exo datasets, but I wanted to start with a smaller bunch of datasets first. Rerun allows you to expose your saved .rrd files to a catalog where you store datasets. You can query, filter, and join them like any database using DataFusion under the hood. These are the same .rrd files that are automatically generated whenever you visualize anything in Rerun and decide to save it to disk. I brought in 109 VSLAM-LAB sequences across 14 datasets into the Rerun catalog as an example. These include 7Scenes, Euroc, eth3d, and others. Now I can query them with segment_table, filter_segments, and filter_contents instead of parsing CSVs and YAML files. With a strong set of ground-truth datasets for SLAM, baseline additions become nearly automatic with agents like Opus/Codex. This unification of data and visualization is imo the largest missing part for Physical AI. Visualization becomes a natural byproduct of having your data properly structured and queryable. The catalog API is what makes it a database, not just a viewer. I initially focused on VSLAM-LAB data, but I'll migrate all the egoexo data to this format in the coming days to really show just how useful this is.

Most people think Rerun is a visualization tool. In reality, it's a database masquerading as a visualizer. I wanted to showcase this functionality by building a full data pipeline consisting of: ingestion → baseline method → eval → finetuning for SLAM on egocentric data. I'll eventually extend this to the rest of my ego/exo datasets, but I wanted to start with a smaller bunch of datasets first. Rerun allows you to expose your saved .rrd files to a catalog where you store datasets. You can query, filter, and join them like any database using DataFusion under the hood. These are the same .rrd files that are automatically generated whenever you visualize anything in Rerun and decide to save it to disk. I brought in 109 VSLAM-LAB sequences across 14 datasets into the Rerun catalog as an example. These include 7Scenes, Euroc, eth3d, and others. Now I can query them with segment_table, filter_segments, and filter_contents instead of parsing CSVs and YAML files. With a strong set of ground-truth datasets for SLAM, baseline additions become nearly automatic with agents like Opus/Codex. This unification of data and visualization is imo the largest missing part for Physical AI. Visualization becomes a natural byproduct of having your data properly structured and queryable. The catalog API is what makes it a database, not just a viewer. I initially focused on VSLAM-LAB data, but I'll migrate all the egoexo data to this format in the coming days to really show just how useful this is.

Pablo Vela

34,937 görüntüleme • 4 ay önce

English is the most powerful language in the world. MongoDB just added support for MCP, and literally anyone can now query data without knowing anything about databases. If you know English, you are all set. I recorded a quick video to show you how I connect to a sample Airbnb database and run different queries: • How many listings? • How many listings in the US? • What's the list of countries in these listings? It takes 10 seconds to configure Claude, Cursor, WindSurf, or any other AI assistant to connect to MongoDB's MCP Server. By the way, the server supports much more than queries: • You can explore your collections • You can fetch schema information • You can generate app code snippets • You can manage your databases • You can handle cluster/user/admin tasks Here is a link to the MCP server GitHub repository: This is huge for developers. It's even bigger for non-developers. Thanks to the MongoDB team for collaborating with me on this post.

English is the most powerful language in the world. MongoDB just added support for MCP, and literally anyone can now query data without knowing anything about databases. If you know English, you are all set. I recorded a quick video to show you how I connect to a sample Airbnb database and run different queries: • How many listings? • How many listings in the US? • What's the list of countries in these listings? It takes 10 seconds to configure Claude, Cursor, WindSurf, or any other AI assistant to connect to MongoDB's MCP Server. By the way, the server supports much more than queries: • You can explore your collections • You can fetch schema information • You can generate app code snippets • You can manage your databases • You can handle cluster/user/admin tasks Here is a link to the MCP server GitHub repository: This is huge for developers. It's even bigger for non-developers. Thanks to the MongoDB team for collaborating with me on this post.

Santiago

44,855 görüntüleme • 1 yıl önce

As machine learning models grow in size, so too does their carbon footprint. As AI scales, it's important that we quantify and mitigate these emissions. In our new short course Carbon Aware Computing for GenAI Developers you'll learn from Google Cloud Developer Advocate Nikita Namjoshi how to: - Query the ElectricityMaps API for real-time data on regional electricity grid carbon intensity - Route your model training jobs to data centers in regions primarily powered by low-carbon sources like wind, solar, hydro and nuclear - Measure the carbon footprint of your ML training, inference, storage and API usage with the Google Cloud's Carbon Footprint tool - Optimize training job scheduling to run when clean energy is most abundant in a given region. You can sign up here:

As machine learning models grow in size, so too does their carbon footprint. As AI scales, it's important that we quantify and mitigate these emissions. In our new short course Carbon Aware Computing for GenAI Developers you'll learn from Google Cloud Developer Advocate Nikita Namjoshi how to: - Query the ElectricityMaps API for real-time data on regional electricity grid carbon intensity - Route your model training jobs to data centers in regions primarily powered by low-carbon sources like wind, solar, hydro and nuclear - Measure the carbon footprint of your ML training, inference, storage and API usage with the Google Cloud's Carbon Footprint tool - Optimize training job scheduling to run when clean energy is most abundant in a given region. You can sign up here:

Andrew Ng

105,900 görüntüleme • 2 yıl önce

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!

Santiago

110,133 görüntüleme • 1 yıl önce

In our latest benchmark, a traditional text-to-SQL approach required more than 4,400 schema-related tokens per query just to provide the model with enough context to understand a 28-table insurance data model. Think about that for a second: before AI can interpret the question, it first has to read the instruction manual. What we found is that when business context is already organized and governed, AI doesn't need to repeatedly rediscover how your data works. We created this white paper to help companies direct their attention to where costs are piling up and how Mosaic directly reduces them. Read the benchmark here: #EnterpriseAI #DataAnalytics #SemanticLayer #BusinessIntelligence

In our latest benchmark, a traditional text-to-SQL approach required more than 4,400 schema-related tokens per query just to provide the model with enough context to understand a 28-table insurance data model. Think about that for a second: before AI can interpret the question, it first has to read the instruction manual. What we found is that when business context is already organized and governed, AI doesn't need to repeatedly rediscover how your data works. We created this white paper to help companies direct their attention to where costs are piling up and how Mosaic directly reduces them. Read the benchmark here: #EnterpriseAI #DataAnalytics #SemanticLayer #BusinessIntelligence

Strategy

11,097 görüntüleme • 2 ay önce

🚨 The Silvia team just announced our latest engineering advancement. Every business wants access to the highest level of intelligence, but at the lowest cost possible. The rise of LLMs has made intelligence abundant, yet one of the hardest problems across startups and corporate America is predicting the compute cost associated with this intelligence. I have been dealing with this personally as we build Silvia and the problem comes up in almost every conversation I have with CEOs, founders, and executives. Every business embraced AI about 18 months ago and things seemed great until the compute bills started to show up. The bills for internal compute usage were difficult to swallow, but things got outrageous if you had an AI product that allowed your users to consume compute without limits. I know this problem intimately because that is the situation that Silvia was in. Every question that was asked meant higher compute costs for our company. But we didn’t want to limit usage because users were getting genuine value out of the product. This challenge sent our team down a deep rabbit hole of cutting costs, while improving the experience for users. The second part was really important: we did not want to degrade the user experience by simply taking away access to the highest quality models. Thankfully, resource constraints breed innovation. We aren’t the biggest company, nor do we have the largest balance sheet, but we came up with a very novel solution that we are announcing today. The Silvia engineering team built a model router that cut costs by up to 29%, decreased latency, and improved the quality of answers for users. Trifecta! The way we do this is by reading the first 500 characters of a query and then predicting the level of effort that will be needed by a model to answer the query. The highest effort needs are routed to the most powerful models. The lowest effort needs are routed to different, better models for the query. A good example of this would be “what is the date?” You don’t need to use the latest Anthropic model to answer this query. In fact, sending a simple query like this to the most powerful model will make your compute costs increase and will actually increase the latency, which means a worse user experience for the Silvia user. By implementing the model router, the user gets a better experience and we get lower costs. Win-win. One of the interesting aspects of the implementation is that our model router runs on CPUs instead of GPUs. This allows us to read the query and predict the level of effort needed in less than 1 millisecond. This CPU implementation is why latency is not affected, nor is cost significantly increased by any potential additional GPU consumption. Another important point is that many of you have probably seen the news that OpenRouter is being purchased by Stripe for around $7 billion. This is a great outcome from what appears to be a very smart, capable team. Their model routing API is related (their product and our internal implementation both touch model routing), but you should think of OpenRouter as making it possible to do model routing for companies, while Silvia’s model router is a custom, intelligent system that specifically routes Silvia queries to the right model. They give access to the functionality of model routing to many companies, while our internal product does the real decision-making specific to our use case. Lastly, our implementation of a model router is a strategic bet that will allow us to become model-agnostic over time. We don’t care who created the different models, we just want to route a query to the model best positioned to answer. The large model labs will never allow their users to be model agnostic, but that would require the lab to potentially route a query to a competitor’s model. No bueno in their eyes. Instead, Silvia being an independent AI research lab gives us the power of being agnostic. We simply want the best experience for our users. Last week we announced that Silvia is now the most accurate AI tax product on the market, including beating OpenAI, Anthropic, Google, and xAI. Today we are announcing a custom, in-house model router that rivals the best technology anyone else has built. There will be many more engineering announcements to come. I truly believe we have assembled one of the best AI teams and we are currently the best AI research lab in finance. If you are interested in learning more about the technical details of the model router, you can read the engineering blog post here: Everyone wants the best intelligence and the lowest cost. Silvia just showed the world what is possible in this pursuit. I anticipate many other companies will build this custom solutions to achieve the same benefits.

🚨 The Silvia team just announced our latest engineering advancement. Every business wants access to the highest level of intelligence, but at the lowest cost possible. The rise of LLMs has made intelligence abundant, yet one of the hardest problems across startups and corporate America is predicting the compute cost associated with this intelligence. I have been dealing with this personally as we build Silvia and the problem comes up in almost every conversation I have with CEOs, founders, and executives. Every business embraced AI about 18 months ago and things seemed great until the compute bills started to show up. The bills for internal compute usage were difficult to swallow, but things got outrageous if you had an AI product that allowed your users to consume compute without limits. I know this problem intimately because that is the situation that Silvia was in. Every question that was asked meant higher compute costs for our company. But we didn’t want to limit usage because users were getting genuine value out of the product. This challenge sent our team down a deep rabbit hole of cutting costs, while improving the experience for users. The second part was really important: we did not want to degrade the user experience by simply taking away access to the highest quality models. Thankfully, resource constraints breed innovation. We aren’t the biggest company, nor do we have the largest balance sheet, but we came up with a very novel solution that we are announcing today. The Silvia engineering team built a model router that cut costs by up to 29%, decreased latency, and improved the quality of answers for users. Trifecta! The way we do this is by reading the first 500 characters of a query and then predicting the level of effort that will be needed by a model to answer the query. The highest effort needs are routed to the most powerful models. The lowest effort needs are routed to different, better models for the query. A good example of this would be “what is the date?” You don’t need to use the latest Anthropic model to answer this query. In fact, sending a simple query like this to the most powerful model will make your compute costs increase and will actually increase the latency, which means a worse user experience for the Silvia user. By implementing the model router, the user gets a better experience and we get lower costs. Win-win. One of the interesting aspects of the implementation is that our model router runs on CPUs instead of GPUs. This allows us to read the query and predict the level of effort needed in less than 1 millisecond. This CPU implementation is why latency is not affected, nor is cost significantly increased by any potential additional GPU consumption. Another important point is that many of you have probably seen the news that OpenRouter is being purchased by Stripe for around $7 billion. This is a great outcome from what appears to be a very smart, capable team. Their model routing API is related (their product and our internal implementation both touch model routing), but you should think of OpenRouter as making it possible to do model routing for companies, while Silvia’s model router is a custom, intelligent system that specifically routes Silvia queries to the right model. They give access to the functionality of model routing to many companies, while our internal product does the real decision-making specific to our use case. Lastly, our implementation of a model router is a strategic bet that will allow us to become model-agnostic over time. We don’t care who created the different models, we just want to route a query to the model best positioned to answer. The large model labs will never allow their users to be model agnostic, but that would require the lab to potentially route a query to a competitor’s model. No bueno in their eyes. Instead, Silvia being an independent AI research lab gives us the power of being agnostic. We simply want the best experience for our users. Last week we announced that Silvia is now the most accurate AI tax product on the market, including beating OpenAI, Anthropic, Google, and xAI. Today we are announcing a custom, in-house model router that rivals the best technology anyone else has built. There will be many more engineering announcements to come. I truly believe we have assembled one of the best AI teams and we are currently the best AI research lab in finance. If you are interested in learning more about the technical details of the model router, you can read the engineering blog post here: Everyone wants the best intelligence and the lowest cost. Silvia just showed the world what is possible in this pursuit. I anticipate many other companies will build this custom solutions to achieve the same benefits.

Anthony Pompliano 🌪

75,896 görüntüleme • 16 gün önce

Introducing Rei Terminal [alpha-test] The frontend team cooked an early private-instance test for our holders while Rei SDK and Rei Core API teams are deep in code 👀 With Rei Quant Terminal Alpha, you can query for market insights, comparative analysis, trending tokens, token deep dives, sentiment analysis and more. 𝌭Query Examples to get started: Market Insights: -Give a brief recap of the crypto market and major news today. -Give a rundown on recent news and correlate the sentiment with performance of best categories of tokens. -What's the latest news in crypto? -What's the crypto market sentiment based on social media mentions? -What are the top 3 sectors gaining traction? -Give me the top holders holders of (insert token) Comparative Analysis: -How does AI agent category compare to the rest of the market? -Show me the AI agent token with the highest volume in the last 24 hours. -Which token had the most volatile price swings in the last 7 days? Trending Tokens: -What was the hottest coin on Base and Solana in the last 72 hours? -Which tokens are gaining the most traction right now? Token Deep Dives: -Give me a deep dive analysis of [contract address] including price target, price action, volume, sentiment. 𝌭Access Everyone who has alpha-tester role in Discord is automatically eligible. Min wallet balance: 800k $REI. Tiers will be added later. Access now → 𝌭Query Limits For the first Two days there will be a query limit of 10 per hour. The limit will be lifted gradually, in time all queries will be unlimited. 𝌭PSA With the current version, Rei is working as everyone's quant/assistant and will require users to press "Clear Conversation" to clear context, conversation archives will be integrated later, Deep Memory Will be integrated after we are done mapping the APIs. Let us know your feedback via Discord alpha-testing channel!

Introducing Rei Terminal [alpha-test] The frontend team cooked an early private-instance test for our holders while Rei SDK and Rei Core API teams are deep in code 👀 With Rei Quant Terminal Alpha, you can query for market insights, comparative analysis, trending tokens, token deep dives, sentiment analysis and more. 𝌭Query Examples to get started: Market Insights: -Give a brief recap of the crypto market and major news today. -Give a rundown on recent news and correlate the sentiment with performance of best categories of tokens. -What's the latest news in crypto? -What's the crypto market sentiment based on social media mentions? -What are the top 3 sectors gaining traction? -Give me the top holders holders of (insert token) Comparative Analysis: -How does AI agent category compare to the rest of the market? -Show me the AI agent token with the highest volume in the last 24 hours. -Which token had the most volatile price swings in the last 7 days? Trending Tokens: -What was the hottest coin on Base and Solana in the last 72 hours? -Which tokens are gaining the most traction right now? Token Deep Dives: -Give me a deep dive analysis of [contract address] including price target, price action, volume, sentiment. 𝌭Access Everyone who has alpha-tester role in Discord is automatically eligible. Min wallet balance: 800k $REI. Tiers will be added later. Access now → 𝌭Query Limits For the first Two days there will be a query limit of 10 per hour. The limit will be lifted gradually, in time all queries will be unlimited. 𝌭PSA With the current version, Rei is working as everyone's quant/assistant and will require users to press "Clear Conversation" to clear context, conversation archives will be integrated later, Deep Memory Will be integrated after we are done mapping the APIs. Let us know your feedback via Discord alpha-testing channel!

Rei

30,951 görüntüleme • 1 yıl önce

A new roadmap. A New Era of The Graph 🗺️ The Graph’s new roadmap introduces a bold and transformative vision for the future of The Graph! The new R&D roadmap details an expansion of The Graph’s ability to serve web3’s growing demands for data access, while better serving builders and protocol contributors, and improving the overall simplicity and efficiency of the network. After three years of serving builders, The Graph Network is mature, reliable, and performant. The Graph ecosystem has followed through on its commitment to democratize access to blockchain data while also establishing subgraphs as a web3 standard. But The Graph’s innovation journey doesn’t end there. The New Era of The Graph is organized into five core objectives: 1️⃣ World of Data Services: Expanding to provide new data services beyond subgraphs to deliver a rich market of data on the network, serving novel use cases for data scientists and more. This will include more data sources, new query languages, and support for LLMs. 2️⃣ Developer Empowerment: Supporting developers through enhanced DevEx and tooling by introducing streamlined billing, clear pricing models, a new free query plan, and reduced gas fees. A more SaaS-like experience for devs, without compromising on decentralization! 3️⃣ Protocol Evolution & Resiliency: Delivering improvements resulting in a more resilient, flexible, and simple protocol, including updates to delegation. 4️⃣ Optimized Indexer Performance: Boosting network performance with improved Indexer tooling and operational capabilities to deliver increased scalability, reduce costs, and enhanced network reliability. 5️⃣ Interconnected Graph of Data: Creating tools for composable data and a global, organized knowledge graph – interlinking open data and making it easier to build upon. The new roadmap sets in motion an exciting evolution in web3 data infrastructure. In a phased rollout, The Graph will introduce many new features and benefits, including the integration of new data services, new query languages, enhanced developer tooling, improved UX + UI, alongside greater protocol efficiency and resilience. As this new era unfolds, The Graph crystallizes as the connective tissue across the many layers of the web3 stack, evolving into a comprehensive, interwoven graph of data equipped to serve every project dreamt up by web3’s innovators. Read the full announcement linked in the comment below!

A new roadmap. A New Era of The Graph 🗺️ The Graph’s new roadmap introduces a bold and transformative vision for the future of The Graph! The new R&D roadmap details an expansion of The Graph’s ability to serve web3’s growing demands for data access, while better serving builders and protocol contributors, and improving the overall simplicity and efficiency of the network. After three years of serving builders, The Graph Network is mature, reliable, and performant. The Graph ecosystem has followed through on its commitment to democratize access to blockchain data while also establishing subgraphs as a web3 standard. But The Graph’s innovation journey doesn’t end there. The New Era of The Graph is organized into five core objectives: 1️⃣ World of Data Services: Expanding to provide new data services beyond subgraphs to deliver a rich market of data on the network, serving novel use cases for data scientists and more. This will include more data sources, new query languages, and support for LLMs. 2️⃣ Developer Empowerment: Supporting developers through enhanced DevEx and tooling by introducing streamlined billing, clear pricing models, a new free query plan, and reduced gas fees. A more SaaS-like experience for devs, without compromising on decentralization! 3️⃣ Protocol Evolution & Resiliency: Delivering improvements resulting in a more resilient, flexible, and simple protocol, including updates to delegation. 4️⃣ Optimized Indexer Performance: Boosting network performance with improved Indexer tooling and operational capabilities to deliver increased scalability, reduce costs, and enhanced network reliability. 5️⃣ Interconnected Graph of Data: Creating tools for composable data and a global, organized knowledge graph – interlinking open data and making it easier to build upon. The new roadmap sets in motion an exciting evolution in web3 data infrastructure. In a phased rollout, The Graph will introduce many new features and benefits, including the integration of new data services, new query languages, enhanced developer tooling, improved UX + UI, alongside greater protocol efficiency and resilience. As this new era unfolds, The Graph crystallizes as the connective tissue across the many layers of the web3 stack, evolving into a comprehensive, interwoven graph of data equipped to serve every project dreamt up by web3’s innovators. Read the full announcement linked in the comment below!

The Graph

425,373 görüntüleme • 2 yıl önce

Existing real estate apps like Zillow are great for searching for homes, but homebuyers can't actually take action because their business model involves selling leads to agents. We built TurboHome so that we control the entire transaction which allows us the redesign the experience from first principles with the homebuyer at the center. Today we're rolling out our new buyer app which gives our customers direct access to world class AI tools with their expert real estate agent in the loop for the entire journey. A few things you can do with 1 click: - Find properties - Run a valuation - Schedule tours - Query live MLS data for insights - Draft offers - Chat with your agent Available on web, mobile, and iMessage at

Existing real estate apps like Zillow are great for searching for homes, but homebuyers can't actually take action because their business model involves selling leads to agents. We built TurboHome so that we control the entire transaction which allows us the redesign the experience from first principles with the homebuyer at the center. Today we're rolling out our new buyer app which gives our customers direct access to world class AI tools with their expert real estate agent in the loop for the entire journey. A few things you can do with 1 click: - Find properties - Run a valuation - Schedule tours - Query live MLS data for insights - Draft offers - Chat with your agent Available on web, mobile, and iMessage at

Ben Bear

439,502 görüntüleme • 29 gün önce

We successfully achieved an RCE on GitLab in its default configuration. Historically, most GitLab RCEs have lived in the web or application-logic layers. This time, guided by the depthfirst spirit, we went deeper: into the low-level gem dependency chain beneath GitLab. The result? By sending crafted JSON data, we could exploit memory-corruption vulnerabilities buried deep in that chain and take control of the GitLab application server. depthfirst brings together some of the smartest people, and is building the best security AI agent. Follow our work, and come join us! Read more about this in the comment...

We successfully achieved an RCE on GitLab in its default configuration. Historically, most GitLab RCEs have lived in the web or application-logic layers. This time, guided by the depthfirst spirit, we went deeper: into the low-level gem dependency chain beneath GitLab. The result? By sending crafted JSON data, we could exploit memory-corruption vulnerabilities buried deep in that chain and take control of the GitLab application server. depthfirst brings together some of the smartest people, and is building the best security AI agent. Follow our work, and come join us! Read more about this in the comment...

Yuhang Wu

101,498 görüntüleme • 1 ay önce

The Graph’s Sunrise of Decentralized Data is here 🌅 The hosted service has officially upgraded to The Graph Network, now the exclusive home of The Graph’s data services. Experience web3 data with ultra-fast syncing, reliable uptime, global redundancy and much more – all secured by decentralization. With support for over 50 chains, 6,000+ subgraphs on the network and available to query, and many new developer experience-enhancing features, anyone can easily tap into the network’s best-in-class performance. Thousands of dapps and teams like Aave, Art Blocks, Balancer, Snapshot, Decentraland, ens.eth, Lido, Messari by Blockworks, PancakeSwap, and Sushi.com already rely on the network, which has successfully served billions of high-quality queries per quarter across thousands of subgraphs. The Graph’s decentralized model allows web3 developers to build confidently, knowing they are leveraging a scalable data layer to meet the industry’s growing activity. The future of web3 is built on The Graph.

The Graph’s Sunrise of Decentralized Data is here 🌅 The hosted service has officially upgraded to The Graph Network, now the exclusive home of The Graph’s data services. Experience web3 data with ultra-fast syncing, reliable uptime, global redundancy and much more – all secured by decentralization. With support for over 50 chains, 6,000+ subgraphs on the network and available to query, and many new developer experience-enhancing features, anyone can easily tap into the network’s best-in-class performance. Thousands of dapps and teams like Aave, Art Blocks, Balancer, Snapshot, Decentraland, ens.eth, Lido, Messari by Blockworks, PancakeSwap, and Sushi.com already rely on the network, which has successfully served billions of high-quality queries per quarter across thousands of subgraphs. The Graph’s decentralized model allows web3 developers to build confidently, knowing they are leveraging a scalable data layer to meet the industry’s growing activity. The future of web3 is built on The Graph.

The Graph

100,424 görüntüleme • 2 yıl önce