Загрузка видео...

Не удалось загрузить видео

На главную

🚀Introducing TMLR Beyond PDF! 🎬This is a new, HTML-based submission format for TMLR, that supports interactive figures and videos, along with the usual LaTeX and images. 🎉Thanks to TMLR Editors in Chief Hugo Larochelle Gautam Kamath Naila Murray Nihar B. Shah Laurent Charlin!

PaulVicol's profile picture

Paul Vicol

1,504 subscribers

64,622 просмотров • 8 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important information that lets you and your agents do meaningful work. HTML artifacts present that information in interesting ways that allow you to take important actions along with your agents. My HTML artifacts sit on top of my LLM wikis. They are dynamic and are easily extended as needs arise. I have hooked my Artifacts to talk to my agents, and similarly, the agents can talk to artifacts. This has allowed me to build powerful artifacts that reduce my inbox to zero, keep me updated on any topic of interest, fast prototyping, do deep research, design/trigger new experiments, generate figures to improve understanding, schedule research, search relevant information, discover topics, and so much more. What you see in the clip is not a website. It's a simple interactive HTML artifact. HTML artifacts are useful for designers, engineers, researchers, students, and anyone working with agents. Lastly, HTML doesn't replace Markdown. They are a much better combination working together.
0:20

LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important information that lets you and your agents do meaningful work. HTML artifacts present that information in interesting ways that allow you to take important actions along with your agents. My HTML artifacts sit on top of my LLM wikis. They are dynamic and are easily extended as needs arise. I have hooked my Artifacts to talk to my agents, and similarly, the agents can talk to artifacts. This has allowed me to build powerful artifacts that reduce my inbox to zero, keep me updated on any topic of interest, fast prototyping, do deep research, design/trigger new experiments, generate figures to improve understanding, schedule research, search relevant information, discover topics, and so much more. What you see in the clip is not a website. It's a simple interactive HTML artifact. HTML artifacts are useful for designers, engineers, researchers, students, and anyone working with agents. Lastly, HTML doesn't replace Markdown. They are a much better combination working together.

elvis

248,444 просмотров • 2 месяцев назад

Coming soon! A new episode of '@ 𝟒 𝐏𝐚𝐫𝐥𝐢𝐚𝐦𝐞𝐧𝐭 𝐒𝐭𝐫𝐞𝐞𝐭' (@ 𝟒 𝐏𝐚𝐫𝐥𝐢𝐚𝐦𝐞𝐧𝐭 𝐒𝐭𝐫𝐞𝐞𝐭), a show where newsmakers engage in a candid conversation with PTI (Press Trust of India) editors in its HQ. Watch an engaging episode with actor-producer Sohum Shah (Sohum Shah) as he opened up on his unique journey from the small town of Sri Ganganagar in Rajasthan to the glamorous world of Mumbai where his mythological mystery-drama 'Tumbbad' changed the direction of horror films. Shah also opined on the discrimination against non-English speakers in Hindi film industry and his own struggle to navigate the class divide of the industry. Sohum Shah's honesty is also reflected in his love and admiration for Shah Rukh Khan, Om Puri and Irrfan Khan. Don't miss this fascinating and unique conversation exclusively on "@ 𝟒 𝐏𝐚𝐫𝐥𝐢𝐚𝐦𝐞𝐧𝐭 𝐒𝐭𝐫𝐞𝐞𝐭" with PTI's senior editors. Subscribe to PTI's YouTube channel ( for in-depth reports, exclusive interviews, and special visual stories that take you beyond the headlines. #PTIExclusive #4ParliamentStreet #PTIVideos
0:50

Coming soon! A new episode of '@ 𝟒 𝐏𝐚𝐫𝐥𝐢𝐚𝐦𝐞𝐧𝐭 𝐒𝐭𝐫𝐞𝐞𝐭' (@ 𝟒 𝐏𝐚𝐫𝐥𝐢𝐚𝐦𝐞𝐧𝐭 𝐒𝐭𝐫𝐞𝐞𝐭), a show where newsmakers engage in a candid conversation with PTI (Press Trust of India) editors in its HQ. Watch an engaging episode with actor-producer Sohum Shah (Sohum Shah) as he opened up on his unique journey from the small town of Sri Ganganagar in Rajasthan to the glamorous world of Mumbai where his mythological mystery-drama 'Tumbbad' changed the direction of horror films. Shah also opined on the discrimination against non-English speakers in Hindi film industry and his own struggle to navigate the class divide of the industry. Sohum Shah's honesty is also reflected in his love and admiration for Shah Rukh Khan, Om Puri and Irrfan Khan. Don't miss this fascinating and unique conversation exclusively on "@ 𝟒 𝐏𝐚𝐫𝐥𝐢𝐚𝐦𝐞𝐧𝐭 𝐒𝐭𝐫𝐞𝐞𝐭" with PTI's senior editors. Subscribe to PTI's YouTube channel ( for in-depth reports, exclusive interviews, and special visual stories that take you beyond the headlines. #PTIExclusive #4ParliamentStreet #PTIVideos

Press Trust of India

89,163 просмотров • 1 год назад

In this quick Fizzy demo, I share a brand new feature we added this week. Bug, issue, idea tracking tools typically require you to explain the issue with text, and then attach images, files, and videos as secondary source material to flesh things out. That's great for a lot of cases, of course. But we want to go further with Fizzy. And by going further, expand the set of possibilities where Fizzy would be a great fit for tracking all sorts of other things that would be better represented as visuals first, text second. A flip from the usual. With that, we're introducing Picture Cards. Here's how they work:
3:30

In this quick Fizzy demo, I share a brand new feature we added this week. Bug, issue, idea tracking tools typically require you to explain the issue with text, and then attach images, files, and videos as secondary source material to flesh things out. That's great for a lot of cases, of course. But we want to go further with Fizzy. And by going further, expand the set of possibilities where Fizzy would be a great fit for tracking all sorts of other things that would be better represented as visuals first, text second. A flip from the usual. With that, we're introducing Picture Cards. Here's how they work:

Jason Fried

17,295 просмотров • 1 год назад

Midjourney v7 plus Luma new Camera Motion Concepts is incredible. This is Mercs. I created this short last night, using my personalization settings in the new MJ v7 along with the new dynamic camera options in #Ray2 The camera moves you can get are next level. I used the new Actor Mode for voice and Dreamina AI for impressive lip sync. It's been incredible building a film studio with Promise. It forces me to stay on my AI filmmaker grind and try out the latest and greatest toolstack. Images upscaled in Magnific.ai and videos in Topaz Labs Edited in Adobe Premiere.
1:16

Midjourney v7 plus Luma new Camera Motion Concepts is incredible. This is Mercs. I created this short last night, using my personalization settings in the new MJ v7 along with the new dynamic camera options in #Ray2 The camera moves you can get are next level. I used the new Actor Mode for voice and Dreamina AI for impressive lip sync. It's been incredible building a film studio with Promise. It forces me to stay on my AI filmmaker grind and try out the latest and greatest toolstack. Images upscaled in Magnific.ai and videos in Topaz Labs Edited in Adobe Premiere.

Dave Clark

31,739 просмотров • 1 год назад

Qubic Community – Happy New Year! 🎉 2024 has been an incredible journey, and it’s all thanks to YOU! 🙏 We’ve shared so many unforgettable moments, and we’re beyond excited for what’s ahead in 2025! 🚀 We’re on the path to AGI and leading the way with the fastest smart contract engine on the market. 2025 is shaping up to be full of new projects and exciting developments! 🌟 Wishing you a fantastic New Year's Eve and a bright start to the new year! 🎆 Here’s to making 2025 even better! 🥂 Cheers to all of you!
1:17

Qubic Community – Happy New Year! 🎉 2024 has been an incredible journey, and it’s all thanks to YOU! 🙏 We’ve shared so many unforgettable moments, and we’re beyond excited for what’s ahead in 2025! 🚀 We’re on the path to AGI and leading the way with the fastest smart contract engine on the market. 2025 is shaping up to be full of new projects and exciting developments! 🌟 Wishing you a fantastic New Year's Eve and a bright start to the new year! 🎆 Here’s to making 2025 even better! 🥂 Cheers to all of you!

Qubic

19,866 просмотров • 1 год назад

👉🏻 🎉🚀 Qwen is back with something new! We've just rolled out Qwen Chat v0.2 after two weeks of hard work, and it's packed with awesome new features! 🌟 Now you can explore web search , create stunning videos, and generate amazing images – all in one place! ✨ Combine that with our existing powers like artifacts, image understanding, and document comprehension, and you've got the ultimate tool for both work and play! 💼📱 Ready to supercharge your daily routine? Let’s make life easier and more fun together! 🎮🔍🎨 Oh, this is not an end, we still have a lot for the Chinese spring festival! Stay tuned!
1:24

👉🏻 🎉🚀 Qwen is back with something new! We've just rolled out Qwen Chat v0.2 after two weeks of hard work, and it's packed with awesome new features! 🌟 Now you can explore web search , create stunning videos, and generate amazing images – all in one place! ✨ Combine that with our existing powers like artifacts, image understanding, and document comprehension, and you've got the ultimate tool for both work and play! 💼📱 Ready to supercharge your daily routine? Let’s make life easier and more fun together! 🎮🔍🎨 Oh, this is not an end, we still have a lot for the Chinese spring festival! Stay tuned!

Qwen

183,752 просмотров • 1 год назад

LiteParse Samples 📄🧑‍🏫 LiteParse is our free and fast document parser that can parse text with bounding boxes from any document. I’ve created a new repository that contains some demos on how you can make use of its outputs! ✅ Comparison against PyPDF and PyMuPDF ✅ Visual Citations: search for any keyword and see joined bounding boxes pop up in the source images It should be a default tool to help AI agents OCR any document type (supports PDF, Word, Powerpoint + dozens of other formats), before heavier-weight VLM-based document parsing solutions (like our own LlamaParse). LiteParse Samples repo: LiteParse:
0:33

LiteParse Samples 📄🧑‍🏫 LiteParse is our free and fast document parser that can parse text with bounding boxes from any document. I’ve created a new repository that contains some demos on how you can make use of its outputs! ✅ Comparison against PyPDF and PyMuPDF ✅ Visual Citations: search for any keyword and see joined bounding boxes pop up in the source images It should be a default tool to help AI agents OCR any document type (supports PDF, Word, Powerpoint + dozens of other formats), before heavier-weight VLM-based document parsing solutions (like our own LlamaParse). LiteParse Samples repo: LiteParse:

Jerry Liu

13,196 просмотров • 3 месяцев назад

I'm excited to release Latent Scope 1.0! Thanks to Fable clearing 2 years of backlog, you can now point your workhorse model at a directory of images, a text corpus or even existing RAG db and get back an interactive map for looking at your data through the eyes of a transformer. Latent Scope started as a set of scripts with a frontend to try and make it less tedious to run the process of projecting & clustering embeddings. Now we let agents do the tedium and the library is essentially a skill that reliably outputs data maps that you can explore. In this release we enabled a ton of stuff, starting with performance increases by switching the backend to LanceDB and enabling cuML GPU acceleration. We added support for images, and late interaction (ColBERT models) as well as 3D UMAP support. We also added Leland McInnes new EVoC clustering method. All that is topped off with a skill definition and an Impeccable powered UI revamp. See the thread for more videos and demos!
0:57

I'm excited to release Latent Scope 1.0! Thanks to Fable clearing 2 years of backlog, you can now point your workhorse model at a directory of images, a text corpus or even existing RAG db and get back an interactive map for looking at your data through the eyes of a transformer. Latent Scope started as a set of scripts with a frontend to try and make it less tedious to run the process of projecting & clustering embeddings. Now we let agents do the tedium and the library is essentially a skill that reliably outputs data maps that you can explore. In this release we enabled a ton of stuff, starting with performance increases by switching the backend to LanceDB and enabling cuML GPU acceleration. We added support for images, and late interaction (ColBERT models) as well as 3D UMAP support. We also added Leland McInnes new EVoC clustering method. All that is topped off with a skill definition and an Impeccable powered UI revamp. See the thread for more videos and demos!

Ian Johnson 🔬🤖

17,648 просмотров • 15 дней назад

Text-to-SQL is dead 💀 The next generation of querying is agentic - and it’s already here. This paper ( introduces a type of agentic querying called 𝗙𝘂𝗻𝗰𝘁𝗶𝗼𝗻 𝗖𝗮𝗹𝗹𝗶𝗻𝗴 that uses an LLM to structure queries using predefined function calls in JSON format, with optional arguments for search, filters, aggregation, and grouping. Along with that, it also tests out a bunch of different models with a new dataset, DBGorilla, designed to evaluate agentic querying techniques on real-world use cases. Weaviate AI Database also just released a 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁, designed based on some of the work in this paper, to handle advanced agentic querying out of the box, find out more here:
3:32

Text-to-SQL is dead 💀 The next generation of querying is agentic - and it’s already here. This paper ( introduces a type of agentic querying called 𝗙𝘂𝗻𝗰𝘁𝗶𝗼𝗻 𝗖𝗮𝗹𝗹𝗶𝗻𝗴 that uses an LLM to structure queries using predefined function calls in JSON format, with optional arguments for search, filters, aggregation, and grouping. Along with that, it also tests out a bunch of different models with a new dataset, DBGorilla, designed to evaluate agentic querying techniques on real-world use cases. Weaviate AI Database also just released a 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁, designed based on some of the work in this paper, to handle advanced agentic querying out of the box, find out more here:

Victoria Slocum

189,014 просмотров • 1 год назад

🚀 Excited to share that "From Silicon Valley to Riyadh" is now live on stc group and will be on Saudia Airlines starting Oct 1st! 🎬 This documentary is the story of the rise of venture capital as a new asset class in the region and it captures Saudi Arabia’s bold journey towards becoming a global tech hub. Watch the trailer and join the conversation! 🌍 Huge thanks to NCDC, stc group, Red Sea Global, @Impact46, Agent 003 - Chinese Mew King, evision, and Saudi for their support in bringing this vision to life. 🙏
1:02

🚀 Excited to share that "From Silicon Valley to Riyadh" is now live on stc group and will be on Saudia Airlines starting Oct 1st! 🎬 This documentary is the story of the rise of venture capital as a new asset class in the region and it captures Saudi Arabia’s bold journey towards becoming a global tech hub. Watch the trailer and join the conversation! 🌍 Huge thanks to NCDC, stc group, Red Sea Global, @Impact46, Agent 003 - Chinese Mew King, evision, and Saudi for their support in bringing this vision to life. 🙏

Somi Arian

17,222 просмотров • 1 год назад

Nimo Infinity 🎉 - Introducing a New AI Browser, Purpose-Built for Productivity. One Canvas for All Your AI Apps and Agents. Nimo We were totally broke in 2024, but we didn’t want to give up. We built Nimo Infinity to rethink the interface for AI. Beautiful design, one canvas for all your apps, and built-in memory and context, all deeply focused on productivity. Comment ‘Nimo Infinity’ 👇 below to get early access with 100 free tasks. Our mission is to build an entirely new AI OS that is secure, intelligent, and interactive. Today, we are taking the first step with an AI Browser. We’ve spent the last 7 years working on Nimo Spatial OS and ultra-portable spatial computers. That experience has shaped how we approach the AI Browser with a completely new interface, purpose-built for AI.
0:56

Nimo Infinity 🎉 - Introducing a New AI Browser, Purpose-Built for Productivity. One Canvas for All Your AI Apps and Agents. Nimo We were totally broke in 2024, but we didn’t want to give up. We built Nimo Infinity to rethink the interface for AI. Beautiful design, one canvas for all your apps, and built-in memory and context, all deeply focused on productivity. Comment ‘Nimo Infinity’ 👇 below to get early access with 100 free tasks. Our mission is to build an entirely new AI OS that is secure, intelligent, and interactive. Today, we are taking the first step with an AI Browser. We’ve spent the last 7 years working on Nimo Spatial OS and ultra-portable spatial computers. That experience has shaped how we approach the AI Browser with a completely new interface, purpose-built for AI.

rohildev

27,345 просмотров • 1 год назад

🌟 Introducing GlobalGPT V2.0 – the ultimate AI workspace! 🎉 Here’s what's new: 🔧 Feature Upgrades: Smart Personal Workspace: Tailor-made model recommendations based on your role, plus the ability to customize your own workbench. Explore Page: Interact effortlessly with AI tools to find your perfect match. Language & Theme Options: Choose your preferred language and switch themes even without logging in. 🎨 UI Enhancements: New Light Mode UI: Designed to meet all your visual needs. 🧠 Core AI Model Updates: Updated Models: o1-preview, Grok, Llama 3.1 405B, Gemini 1.5 Pro for language; Flux, Ideogram for images; and Luma for videos. Coming Soon: Midjourney’s new update, Runway, Open Canvas, Morphic, and Copyleak. Stay ahead with GLBGPT V2.0! 🚀 #AI #TechUpdate #GlobalGPT
0:20

🌟 Introducing GlobalGPT V2.0 – the ultimate AI workspace! 🎉 Here’s what's new: 🔧 Feature Upgrades: Smart Personal Workspace: Tailor-made model recommendations based on your role, plus the ability to customize your own workbench. Explore Page: Interact effortlessly with AI tools to find your perfect match. Language & Theme Options: Choose your preferred language and switch themes even without logging in. 🎨 UI Enhancements: New Light Mode UI: Designed to meet all your visual needs. 🧠 Core AI Model Updates: Updated Models: o1-preview, Grok, Llama 3.1 405B, Gemini 1.5 Pro for language; Flux, Ideogram for images; and Luma for videos. Coming Soon: Midjourney’s new update, Runway, Open Canvas, Morphic, and Copyleak. Stay ahead with GLBGPT V2.0! 🚀 #AI #TechUpdate #GlobalGPT

GlobalGPT

19,382 просмотров • 1 год назад

It's an exciting moment for Sizewell B nuclear power station. We’ve signed Heads of Terms with the UK Government, setting out the key principles for an agreement that would enable Sizewell B to continue generating reliable, low-carbon electricity until at least 2055. This 20‑year lifetime extension beyond the original shutdown date of 2035 is a vote of confidence in our people, their skills and the role nuclear plays in strengthening the UK’s energy security and powering an electric Britain. Robert Gunn, Station Director at Sizewell B, explains what this means for the site, our people and the communities it supports. Find out more:
0:57

It's an exciting moment for Sizewell B nuclear power station. We’ve signed Heads of Terms with the UK Government, setting out the key principles for an agreement that would enable Sizewell B to continue generating reliable, low-carbon electricity until at least 2055. This 20‑year lifetime extension beyond the original shutdown date of 2035 is a vote of confidence in our people, their skills and the role nuclear plays in strengthening the UK’s energy security and powering an electric Britain. Robert Gunn, Station Director at Sizewell B, explains what this means for the site, our people and the communities it supports. Find out more:

EDF 🇬🇧

16,118 просмотров • 18 дней назад

Introducing Ask YouTube, our new conversational search experience in YouTube. 📽️ With Ask YouTube, you can ask more complex search queries, like needing help planning a road trip through the California coast or wanting tips on how to teach your kid to ride a bike. You can even ask follow-up questions to continue refining what you’re looking for. Ask YouTube will compile the most relevant videos across all of YouTube’s catalogue — including long-form videos and Shorts — and provide an interactive, structured response instead of the usual list of video recommendations. Ask YouTube is currently available for Premium members in the U.S., and it’ll be rolling out to all YouTube users soon.
0:49

Introducing Ask YouTube, our new conversational search experience in YouTube. 📽️ With Ask YouTube, you can ask more complex search queries, like needing help planning a road trip through the California coast or wanting tips on how to teach your kid to ride a bike. You can even ask follow-up questions to continue refining what you’re looking for. Ask YouTube will compile the most relevant videos across all of YouTube’s catalogue — including long-form videos and Shorts — and provide an interactive, structured response instead of the usual list of video recommendations. Ask YouTube is currently available for Premium members in the U.S., and it’ll be rolling out to all YouTube users soon.

Google

210,872 просмотров • 2 месяцев назад

$BTC update 24 April 2026 These video updates are for educational purposes only and should never ever be considered as investment or trading advice. Always do your own research and planning. " $BTC and the crypto currency market have somewhat stabilised in recent weeks as these assets have based into the phase and for the very first time in several months $BTC flipped an SR which triggered long positions in coins such as $DOGE (which itself based in phase after an 85% washout). On the lower timeframes this market is making positive patterns for the very first time since late summer 2025 and that data cannot be ignored and there's potential for some relief in this sector, however there is a caveat to all of this and that is implied volatilities suggest there is potential for a hard sell setting up and that syncs with my higher tf outlook for the crypto market that any move higher is countertrend and there will likely be another wave down 66-68 k is now the SR below (but think about the sideways low and what that tells you about supply and demand and what can happen in the future). above that 70.8k is the local level of demand. As always, thanks to those who support the feed". This was last week's text update and as we can $BTC has followed along and now on the very ltf the patterns are bullish telling us that conditions have indeed changed and a move into the mid 80ks can set up after a period of consolidation. There is a warning in this analysis and that is yields and the VIX telling us that an important top is likely being set in the #spx and that what we are seeing in #crypto is likely a countertrend bear market rally. As always, thanks to those who support the feed. These videos take a lot of time to plan and create so I appreciate the support.
15:50

$BTC update 24 April 2026 These video updates are for educational purposes only and should never ever be considered as investment or trading advice. Always do your own research and planning. " $BTC and the crypto currency market have somewhat stabilised in recent weeks as these assets have based into the phase and for the very first time in several months $BTC flipped an SR which triggered long positions in coins such as $DOGE (which itself based in phase after an 85% washout). On the lower timeframes this market is making positive patterns for the very first time since late summer 2025 and that data cannot be ignored and there's potential for some relief in this sector, however there is a caveat to all of this and that is implied volatilities suggest there is potential for a hard sell setting up and that syncs with my higher tf outlook for the crypto market that any move higher is countertrend and there will likely be another wave down 66-68 k is now the SR below (but think about the sideways low and what that tells you about supply and demand and what can happen in the future). above that 70.8k is the local level of demand. As always, thanks to those who support the feed". This was last week's text update and as we can $BTC has followed along and now on the very ltf the patterns are bullish telling us that conditions have indeed changed and a move into the mid 80ks can set up after a period of consolidation. There is a warning in this analysis and that is yields and the VIX telling us that an important top is likely being set in the #spx and that what we are seeing in #crypto is likely a countertrend bear market rally. As always, thanks to those who support the feed. These videos take a lot of time to plan and create so I appreciate the support.

venture

71,873 просмотров • 3 месяцев назад

Finished this desktop app that does CRT shaders and VHS/composite video distortion 🙌 I was tired of doing those in separate apps, so I figured I'd just put them together. AFAIK, it's the only one that does both at this level of quality and control. It supports images and videos, with VERY granular control over every parameter from subtle to completely obliterated. To be clear, I'm a dummy. This is just hacking together two existing open source projects that are the best in the world at what they do: NTSC-RS for the TV effect, and the CRT shaders from Retroarch. Download link in the replies 🧵
0:37

Finished this desktop app that does CRT shaders and VHS/composite video distortion 🙌 I was tired of doing those in separate apps, so I figured I'd just put them together. AFAIK, it's the only one that does both at this level of quality and control. It supports images and videos, with VERY granular control over every parameter from subtle to completely obliterated. To be clear, I'm a dummy. This is just hacking together two existing open source projects that are the best in the world at what they do: NTSC-RS for the TV effect, and the CRT shaders from Retroarch. Download link in the replies 🧵

Finn McKenty

32,228 просмотров • 6 дней назад

Introducing Document Extraction as an MCP Server ✂️📑 A huge use case for AI agents is being able to extract out items from a diverse set of complex documents in a repeatable manner - whether it’s legal contracts, invoices, financial statements, passports, and more. In this case, 🚫 prompting ChatGPT/Claude is too error-prone/not systematic. 💡We’ve created a plug-and-play MCP server around our core document extraction capabilities within LlamaCloud. 1. Build an extraction agent in LlamaCloud with a standardized schema. 2. Plug it as an MCP tool within ChatGPT/Claude. 3. For your next extraction job, get the outputs in a standardized format through the tool! Huge shoutout to Tuana and Logan Markewich for working on this - this is thanks to the latest updates to our llamacloud-mcp demo repo, which supports both extraction and retrieval as MCP tools. Repo: Sign up:
0:28

Introducing Document Extraction as an MCP Server ✂️📑 A huge use case for AI agents is being able to extract out items from a diverse set of complex documents in a repeatable manner - whether it’s legal contracts, invoices, financial statements, passports, and more. In this case, 🚫 prompting ChatGPT/Claude is too error-prone/not systematic. 💡We’ve created a plug-and-play MCP server around our core document extraction capabilities within LlamaCloud. 1. Build an extraction agent in LlamaCloud with a standardized schema. 2. Plug it as an MCP tool within ChatGPT/Claude. 3. For your next extraction job, get the outputs in a standardized format through the tool! Huge shoutout to Tuana and Logan Markewich for working on this - this is thanks to the latest updates to our llamacloud-mcp demo repo, which supports both extraction and retrieval as MCP tools. Repo: Sign up:

Jerry Liu

57,827 просмотров • 1 год назад

i watched a guy screenshare how he makes millions with 7 ai agent workflows, his name is rowan cheung from the rundown 1/ an avatar that records videos so he doesn’t have to and gets millions of views 2/ a voice-to-tweet system that turns walks into content. 3/ a newsletter “editor in chief” that polishes every draft and gets seen by 1m+ people 4/a meeting agent that schedules without calendly links. 5/a tutor that makes every youtube video interactive. 6/ an onboarding gpt that trains new hires faster than managers. 7/ an inbox agent that filters spam and finds sponsors. he shares his workflows & prompts on The Startup Ideas Podcast (SIP) 🧃 (thanks Rowan Cheung) what hit me was how normal it all felt. like… this is just the new baseline for running a business maybe because it is
43:06

i watched a guy screenshare how he makes millions with 7 ai agent workflows, his name is rowan cheung from the rundown 1/ an avatar that records videos so he doesn’t have to and gets millions of views 2/ a voice-to-tweet system that turns walks into content. 3/ a newsletter “editor in chief” that polishes every draft and gets seen by 1m+ people 4/a meeting agent that schedules without calendly links. 5/a tutor that makes every youtube video interactive. 6/ an onboarding gpt that trains new hires faster than managers. 7/ an inbox agent that filters spam and finds sponsors. he shares his workflows & prompts on The Startup Ideas Podcast (SIP) 🧃 (thanks Rowan Cheung) what hit me was how normal it all felt. like… this is just the new baseline for running a business maybe because it is

GREG ISENBERG

228,496 просмотров • 10 месяцев назад