正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Jupyter Agents - LLMs running data analysis directly in a notebook! The agent can load data, execute code, plot results and following your guidance and ideas! A very natural way to collaborate with an LLM over data and it's just scratching the surface of what's possible soon!

Leandro von Werra

11,336 subscribers

200,291 次观看 • 1 年前 •via X (Twitter)

教育新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

9 条评论

Leandro von Werra 的头像

Leandro von Werra1 年前

Or watch how the model solves the Lokta-Volterra equation and plots the results and refines them. Try it out:

Nivge 的头像

Nivge1 年前

Here's a jupyter agent for notebooks in VS-Code: Works really good

نعمت | Nemat 的头像

نعمت | Nemat1 年前

Please checkout my automated kaggle challenge solver it hasl lots in common:

Thomas Capelle 的头像

Thomas Capelle1 年前

Seems very similar to what Jeremy is using in the course (cc. @jeremyphoward )

Fabrizio Milo 的头像

Fabrizio Milo1 年前

Is it an extension for jupyter or does he has some specialized training to interact with jupyter?

Saquib Mehmood 的头像

Saquib Mehmood1 年前

Bro, even my own self-developed AI copilot does it using a local model. So thanks, anyways.

Fatih 的头像

Fatih1 年前

Is it open source?

Léo - eu/acc 的头像

Léo - eu/acc1 年前

My job is over

Maxime Rivest 🧙‍♂️🦙 的头像

Maxime Rivest 🧙‍♂️🦙1 年前

Very similar to jupyter-whisper a. Excited to check it out!

相关视频

Excited to release: Jupyter Agent 2 The agent can load data, execute code, plot results inside Jupyter faster than you can scroll! 🤖 Powered by Qwen3-Coder ⚡️ Running on Cerebras ⚙️ Executed in E2B ↕️ Upload your files All videos are in *real time*!

Excited to release: Jupyter Agent 2 The agent can load data, execute code, plot results inside Jupyter faster than you can scroll! 🤖 Powered by Qwen3-Coder ⚡️ Running on Cerebras ⚙️ Executed in E2B ↕️ Upload your files All videos are in real time!

Leandro von Werra

66,165 次观看 • 10 个月前

Welcome to Agentforce: a powerful data platform and an exceptional agent builder. The key to making agents truly effective is data. Salesforce agents deliver greater accuracy thanks to our integrated & comprehensive data & metadata. Without data, you're left with just a "dumb" LLM. No agent platform will gain traction without integrating data and metadata at its core. Get Agentforce at Dreamforce. ❤️

Welcome to Agentforce: a powerful data platform and an exceptional agent builder. The key to making agents truly effective is data. Salesforce agents deliver greater accuracy thanks to our integrated & comprehensive data & metadata. Without data, you're left with just a "dumb" LLM. No agent platform will gain traction without integrating data and metadata at its core. Get Agentforce at Dreamforce. ❤️

Marc Benioff

49,456 次观看 • 1 年前

INCREDIBLE!!! Gemini did 6 hours of manual data analysis work in just 2 mins. Gemini in a Colab notebook now lets you plan, analyze, and visualize your data. I used a dataset of 100k rows and didn't write or execute a single line of code. Completely hands-off!

INCREDIBLE!!! Gemini did 6 hours of manual data analysis work in just 2 mins. Gemini in a Colab notebook now lets you plan, analyze, and visualize your data. I used a dataset of 100k rows and didn't write or execute a single line of code. Completely hands-off!

Avi Chawla

300,110 次观看 • 1 年前

How to Create a Spinning Globe 🌍 with Your Own Data Layers (No Coding Required) Learn how to create a spinning 3D globe map without writing any code using a simple web-based tool. In this step-by-step geospatial tutorial, you'll see how to build an interactive spinning globe, overlay raster and vector data layers, and visualize datasets directly in your browser or in a Jupyter Notebook environment. Web-based demo: Jupyter notebook demo: Video tutorial: #geospatial #opensource #python #jupyter #maplibre

How to Create a Spinning Globe 🌍 with Your Own Data Layers (No Coding Required) Learn how to create a spinning 3D globe map without writing any code using a simple web-based tool. In this step-by-step geospatial tutorial, you'll see how to build an interactive spinning globe, overlay raster and vector data layers, and visualize datasets directly in your browser or in a Jupyter Notebook environment. Web-based demo: Jupyter notebook demo: Video tutorial: #geospatial #opensource #python #jupyter #maplibre

Qiusheng Wu

12,637 次观看 • 3 个月前

Google release its Data science Agent The Google Data Science Agent in Colab (powered by Gemini) revolutionizes data analysis by allowing users to easily formulate their analysis goals in natural language. This automatically generates fully functional Colab notebooks, which drastically reduces tedious routine work such as code creation, data import and setup. Particularly noteworthy are the flexibility of the generated notebooks, the ease of collaboration and the fast, accurate results thanks to Gemini 2.0.

Google release its Data science Agent The Google Data Science Agent in Colab (powered by Gemini) revolutionizes data analysis by allowing users to easily formulate their analysis goals in natural language. This automatically generates fully functional Colab notebooks, which drastically reduces tedious routine work such as code creation, data import and setup. Particularly noteworthy are the flexibility of the generated notebooks, the ease of collaboration and the fast, accurate results thanks to Gemini 2.0.

Chubby♨️

111,412 次观看 • 1 年前

CODE EXECUTION IN CANVAS🎨 Canvas becomes an automated SWE and a data scientist. Search for API docs, ask the model to write code and execute, get the plot!

CODE EXECUTION IN CANVAS🎨 Canvas becomes an automated SWE and a data scientist. Search for API docs, ask the model to write code and execute, get the plot!

Karina Nguyen

46,579 次观看 • 1 年前

Nexus brings your data, tools, and AI together in one place. Here’s a sneak peek: see how to set up data lakes, connect LLMs, build agents, and chat with your data. 🎥 Watch the walkthrough: $NAI #MeetNexus

Nexus brings your data, tools, and AI together in one place. Here’s a sneak peek: see how to set up data lakes, connect LLMs, build agents, and chat with your data. 🎥 Watch the walkthrough: $NAI #MeetNexus

Nuklai

21,102 次观看 • 11 个月前

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

LlamaIndex 🦙

475,732 次观看 • 2 年前

Introducing: enrich-excel Hermes Agent or OpenClaw🦞 can now enrich any Excel sheet with live web data. > uses our free Search and Fetch to find missing data > writes results directly into the running Excel via AppleScript All in just a few seconds and one Skill.

Introducing: enrich-excel Hermes Agent or OpenClaw🦞 can now enrich any Excel sheet with live web data. > uses our free Search and Fetch to find missing data > writes results directly into the running Excel via AppleScript All in just a few seconds and one Skill.

TinyFish

58,574 次观看 • 1 个月前

This is going to change Data Analytics! A Dashboard UI inside the Jupyter Notebook which makes Visualizing Easy! Using just one line of code and is easy to deploy as well!

This is going to change Data Analytics! A Dashboard UI inside the Jupyter Notebook which makes Visualizing Easy! Using just one line of code and is easy to deploy as well!

Sasi 📊📈

92,180 次观看 • 2 年前

Today, we’re pushing a major update to Edison Analysis, our data analysis agent, which is tuned for scientific research and SOTA across data analysis benchmarks. In contrast to Kosmos, which runs for 6-12 hours and produces tens of thousands of lines of code, Edison Analysis runs for seconds to minutes and is best for specific, well-defined computational tasks. It is available both on our platform under the Analysis tab, and via API, and costs only one credit per run, so it is available to users on both free and paid tiers. Edison Analysis is a modified version of the data analysis agent Kosmos uses in its trajectories. Try it out! One of the most important improvements over our previous data analysis agents has been the addition of a specialized data retrieval tool. Edison Analysis can either use this tool to access data, or can pull data down directly via API. To evaluate this tool, we ranked the most commonly used public data repositories across recent papers from BioRxiv, and created a new benchmark that measures the ability of a language agent system to retrieve raw data from those sources. Edison Analysis gets 71% on this benchmark, and we’ll be working to increase this over time. You can read more about our benchmarks in the our blog post, link below. Some features worth highlighting: 1. Edison Analysis produces a report on the analysis it runs, along with a Jupyter notebook that you can download to reproduce the analysis yourself. Every figure it produces is linked back to the specific lines of code used to produce the figure, to make it easy to reproduce. 2. It works well with both Python and R. 3. One of the best uses for Edison Analysis is to use it to retrieve datasets that you can then analyze with Kosmos. We have a bunch of major improvements to Edison Analysis coming in the next few months that we’re excited to share. In the meantime, congratulations to the team, especially Ludovico Mitchener, Jon Laurent, Conor Igoe , Alex Andonian, and many more.

Today, we’re pushing a major update to Edison Analysis, our data analysis agent, which is tuned for scientific research and SOTA across data analysis benchmarks. In contrast to Kosmos, which runs for 6-12 hours and produces tens of thousands of lines of code, Edison Analysis runs for seconds to minutes and is best for specific, well-defined computational tasks. It is available both on our platform under the Analysis tab, and via API, and costs only one credit per run, so it is available to users on both free and paid tiers. Edison Analysis is a modified version of the data analysis agent Kosmos uses in its trajectories. Try it out! One of the most important improvements over our previous data analysis agents has been the addition of a specialized data retrieval tool. Edison Analysis can either use this tool to access data, or can pull data down directly via API. To evaluate this tool, we ranked the most commonly used public data repositories across recent papers from BioRxiv, and created a new benchmark that measures the ability of a language agent system to retrieve raw data from those sources. Edison Analysis gets 71% on this benchmark, and we’ll be working to increase this over time. You can read more about our benchmarks in the our blog post, link below. Some features worth highlighting: 1. Edison Analysis produces a report on the analysis it runs, along with a Jupyter notebook that you can download to reproduce the analysis yourself. Every figure it produces is linked back to the specific lines of code used to produce the figure, to make it easy to reproduce. 2. It works well with both Python and R. 3. One of the best uses for Edison Analysis is to use it to retrieve datasets that you can then analyze with Kosmos. We have a bunch of major improvements to Edison Analysis coming in the next few months that we’re excited to share. In the meantime, congratulations to the team, especially Ludovico Mitchener, Jon Laurent, Conor Igoe , Alex Andonian, and many more.

Sam Rodriques

61,760 次观看 • 7 个月前

I built an AI Data Analysis Agent. Just upload CSV/Excel files and analyze data through natural language. It uses DuckDB for lightning-fast processing. 100% Opensource Code with step-by-step tutorial.

I built an AI Data Analysis Agent. Just upload CSV/Excel files and analyze data through natural language. It uses DuckDB for lightning-fast processing. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

88,517 次观看 • 1 年前

I built an AI data visualization Agent. The AI Agent can automatically generate the code and visualize the data using code interpreter sandbox. 100% Opensource Code with step-by-step tutorial.

I built an AI data visualization Agent. The AI Agent can automatically generate the code and visualize the data using code interpreter sandbox. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

67,845 次观看 • 1 年前

Microsoft has just announced Copilot's ability to process data in Excel by generating Python code. - Request a detailed analysis - Copilot generates Python - Excel executes the code to show the result All without having to write a single formula. Just natural language. Huge deal for data analysis and visualization.

Microsoft has just announced Copilot's ability to process data in Excel by generating Python code. - Request a detailed analysis - Copilot generates Python - Excel executes the code to show the result All without having to write a single formula. Just natural language. Huge deal for data analysis and visualization.

Paul Couvert

373,713 次观看 • 1 年前

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Hurley

33,300 次观看 • 2 个月前

Check this!! Microsoft open-sourced a no-code data analysis tool. It's called Data Formulator and it provides AI-powered data analysis and an drag-and-drop UI for viz tasks. It also works beyond the initial dataset by creating relevant fields and the corresponding viz.

Check this!! Microsoft open-sourced a no-code data analysis tool. It's called Data Formulator and it provides AI-powered data analysis and an drag-and-drop UI for viz tasks. It also works beyond the initial dataset by creating relevant fields and the corresponding viz.

Avi Chawla

260,087 次观看 • 1 年前

Data teams spend weeks on simple requests. (This AI answers them in minutes.) Most data analysis is repetitive manual tasks. Data teams spend more time on setup than actual analysis. The workflow usually looks like this: → Run some exploratory data analysis in a local Jupyter notebook or environment → Pull data from multiple disconnected sources → Write code from scratch for every analysis → Export static charts that stakeholders can't explore (or wrestle with legacy BI to create a dashboard) → Manually send updates via email or Slack when data changes → Start over for each new request Most teams accept this as "how data analysis works." While business decisions wait for insights. That's where Fabi changes the entire approach. It's a powerful, AI-native platform built for teams that want to boost productivity and supercharge their data workflows. Instead of working on separate tools and manual processes, you collaborate on analysis that automatically delivers insights where teams work. Here's what makes Fabi different: AI-Native Analysis Environment ↳ SQL and Python work together with AI assistance that handles coding and debugging automatically. Smart Automation Workflows ↳ Automatically send AI-powered reports and summaries right where business works in Slack, email, and spreadsheets. Universal Data Integration ↳ Analyze data from files, Google Sheets, Airtable, plus your data warehouse and databases in one place. Collaborative Data Apps ↳ Create interactive dashboards that stakeholders can explore and ask follow-up questions directly. What you can do with Fabi that legacy BI can't: ➟ Send AI-generated insights directly to Slack channels ➟ Automatically email data summaries to stakeholders ➟ Analyze uploaded files without complex ETL processes ➟ Collaborate on analysis like Google Docs for data ➟ Build workflows that push insights to spreadsheets Perfect for teams that want to move beyond the constraints of legacy and increase their impact. Teams using Fabi see immediate results: ✓ Insights delivered in minutes instead of days ✓ Reduced context switching between tools ✓ Stakeholders explore data independently ✓ Workflows automated to save hours of manual work From analysis to automated delivery - all in one AI-native environment. 📌 Try Fabi today: 👉 Follow Fabi.ai and marc for Fabi updates. 🔄 Repost to help other teams streamline data analysis #DataAnalysis #ModernBI #DataOps #InteractiveDashboards #FabiPartnership #SponsoredByFabi

Data teams spend weeks on simple requests. (This AI answers them in minutes.) Most data analysis is repetitive manual tasks. Data teams spend more time on setup than actual analysis. The workflow usually looks like this: → Run some exploratory data analysis in a local Jupyter notebook or environment → Pull data from multiple disconnected sources → Write code from scratch for every analysis → Export static charts that stakeholders can't explore (or wrestle with legacy BI to create a dashboard) → Manually send updates via email or Slack when data changes → Start over for each new request Most teams accept this as "how data analysis works." While business decisions wait for insights. That's where Fabi changes the entire approach. It's a powerful, AI-native platform built for teams that want to boost productivity and supercharge their data workflows. Instead of working on separate tools and manual processes, you collaborate on analysis that automatically delivers insights where teams work. Here's what makes Fabi different: AI-Native Analysis Environment ↳ SQL and Python work together with AI assistance that handles coding and debugging automatically. Smart Automation Workflows ↳ Automatically send AI-powered reports and summaries right where business works in Slack, email, and spreadsheets. Universal Data Integration ↳ Analyze data from files, Google Sheets, Airtable, plus your data warehouse and databases in one place. Collaborative Data Apps ↳ Create interactive dashboards that stakeholders can explore and ask follow-up questions directly. What you can do with Fabi that legacy BI can't: ➟ Send AI-generated insights directly to Slack channels ➟ Automatically email data summaries to stakeholders ➟ Analyze uploaded files without complex ETL processes ➟ Collaborate on analysis like Google Docs for data ➟ Build workflows that push insights to spreadsheets Perfect for teams that want to move beyond the constraints of legacy and increase their impact. Teams using Fabi see immediate results: ✓ Insights delivered in minutes instead of days ✓ Reduced context switching between tools ✓ Stakeholders explore data independently ✓ Workflows automated to save hours of manual work From analysis to automated delivery - all in one AI-native environment. 📌 Try Fabi today: 👉 Follow Fabi.ai and marc for Fabi updates. 🔄 Repost to help other teams streamline data analysis #DataAnalysis #ModernBI #DataOps #InteractiveDashboards #FabiPartnership #SponsoredByFabi

Andrew Bolis

36,504 次观看 • 9 个月前

Agents are finally starting to work in biology. We’ve partnered with Anthropic and major biotech vendors - Vizgen, AtlasXOmics, Takara, 10x Genomics - to build a tool that allows scientists to steer their own analysis with natural language. Raw spatial data to publication quality figures. Our team believes this will soon be the standard way biologists interact with data. Spatial biology agents look a bit different from coding products: - tailored to the molecular details of each kit type - run in sandboxes on very large machines - orchestrate data infra, eg. bioinformatics workflows, with tool calls - build graphical analysis notebooks to communicate results Detailed breakdown of engineering decisions, product philosophy and concrete flows follows:

Agents are finally starting to work in biology. We’ve partnered with Anthropic and major biotech vendors - Vizgen, AtlasXOmics, Takara, 10x Genomics - to build a tool that allows scientists to steer their own analysis with natural language. Raw spatial data to publication quality figures. Our team believes this will soon be the standard way biologists interact with data. Spatial biology agents look a bit different from coding products: - tailored to the molecular details of each kit type - run in sandboxes on very large machines - orchestrate data infra, eg. bioinformatics workflows, with tool calls - build graphical analysis notebooks to communicate results Detailed breakdown of engineering decisions, product philosophy and concrete flows follows:

Kenny Workman

114,050 次观看 • 7 个月前

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Aaron Levie

16,161 次观看 • 2 个月前