Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🆕 Retrieval Engine by tackles the AI hallucination problem 🔥 RAG grounds AI responses in your docs (with citations!), reducing fabricated outputs that pretend to be accurate. 1️⃣ Upload docs 2️⃣ Ask questions 3️⃣ Get cited answers Built for when accuracy really matters. Try it now ⤵️

io.net

448,134 subscribers

19,765 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

io.net1 year ago

Try Retreival Engine now:

ksminnovation1 year ago

AI is transforming healthcare! A KSM-led study shows AI can detect Celiac disease 4 years earlier @TalPatalon @MedPredict

Leonard McDoogan1 year ago

$IO

Alberto1 year ago

RAG grounds AI responses in your docs (with citations!), reducing fabricated outputs that pretend to be accurate.

Akash.eth1 year ago

Lfg

TASMAN1 year ago

👍🔥🚀💻🥇

Boss | IONET Astronaut - Dev1 year ago

Looks great 🔥

FEKU1 year ago

@shadid_io 🔥 can’t wait to test it tomorrow

Lele1 year ago

$IO

0xJacky 🟣1 year ago

In $IO We Trust

Related Videos

Open-source retrieval-augmented generation engine that combines advanced RAG techniques with agentic capabilities for grounded, traceable AI answers.

Open-source retrieval-augmented generation engine that combines advanced RAG techniques with agentic capabilities for grounded, traceable AI answers.

GitHub Projects Community

20,985 views • 2 months ago

over the weekend i built and shipped Sentra for our docs. we use Mintlify for documentation. the built-in assistant kept running into context issues. wrong answers, missing context, no citations. so we extended Sentra's capability to the docs site directly. now when you're reading Dodo Payments docs, you can ask Sentra questions right there. it pulls context from our entire documentation via RAG (the same contextmcp (completely opensource) + Pinecone vector search with reranking), generates grounded answers, and cites the exact doc pages. built as a single Cloudflare Worker serving both the widget and the chat endpoint. React widget bundled into one self-contained IIFE, mounted in Shadow DOM so it doesn't conflict with Mintlify's styles. OpenAI models routed through Cloudflare AI Gateway. Vercel's AI SDK for streaming and shadcn for beautiful chat components. live now at

over the weekend i built and shipped Sentra for our docs. we use Mintlify for documentation. the built-in assistant kept running into context issues. wrong answers, missing context, no citations. so we extended Sentra's capability to the docs site directly. now when you're reading Dodo Payments docs, you can ask Sentra questions right there. it pulls context from our entire documentation via RAG (the same contextmcp (completely opensource) + Pinecone vector search with reranking), generates grounded answers, and cites the exact doc pages. built as a single Cloudflare Worker serving both the widget and the chat endpoint. React widget bundled into one self-contained IIFE, mounted in Shadow DOM so it doesn't conflict with Mintlify's styles. OpenAI models routed through Cloudflare AI Gateway. Vercel's AI SDK for streaming and shadcn for beautiful chat components. live now at

Ayush Agarwal

18,001 views • 11 days ago

Box AI uses OpenAI models to deliver smart RAG capabilities natively in a Box Hub. With the Box AI API, you can easily search a Hub, extract insights from multiple docs, generate code snippets, and get answers to complex questions—all within your custom apps ⚡️

Box AI uses OpenAI models to deliver smart RAG capabilities natively in a Box Hub. With the Box AI API, you can easily search a Hub, extract insights from multiple docs, generate code snippets, and get answers to complex questions—all within your custom apps ⚡️

Box

223,611 views • 1 year ago

Need fast answers? We’ve added AI chat support and unified search to the Solana Developer Docs powered by — find what you need instantly. Get real-time answers to your questions and build faster. Live now!

Need fast answers? We’ve added AI chat support and unified search to the Solana Developer Docs powered by — find what you need instantly. Get real-time answers to your questions and build faster. Live now!

Solana Developers

40,321 views • 1 year ago

Introducing Fireplexity - our open source Perplexity clone 🔥 Ask any question and get AI-powered answers with cited sources, all powered by our /search and /scrape endpoints. Fork the example and build your own AI answer engine today 👇

Introducing Fireplexity - our open source Perplexity clone 🔥 Ask any question and get AI-powered answers with cited sources, all powered by our /search and /scrape endpoints. Fork the example and build your own AI answer engine today 👇

Firecrawl

81,200 views • 1 year ago

We've been obsessing a lot about creating the best possible AI support experience Dub.co. And I think we've found the magic formula. The stack: ✦ Mintlify → docs + help articles ✦ Upstash vector → vector search ✦ AI SDK + Claude sonnet → LLM/retrieval ✦ Plain → support infra Here's how it works: We consolidated our docs + help articles on Mintlify (best-in-class docs platform) so all our support content is now in one place. On every push to main, we sync changes to our Upstash Vector DB. We also built a custom chat interface that retrieves content from Upstash Vector and generates responses via AI SDK + Claude sonnet. The best part: The AI agent uses 𝚝𝚘𝚘𝚕() from AI SDK to retrieve the user's workspace / partner data to provide accurate responses. Finally, if the user needs to speak to a human, we generate a 𝚃𝚒𝚌𝚔𝚎𝚝𝚄𝚙𝚕𝚘𝚊𝚍 UI that lets users upload screenshots + add more context, before creating a ticket on Plain. Cherry on top: The chat interface is embeddable, so we're able to embed it both in our Mintlify docs + support portal 👇 Since we launched this, it's been a gamechanger for scaling support – reducing support workload and creating a much better experience for our users. Highly recommend giving this a try!

We've been obsessing a lot about creating the best possible AI support experience Dub.co. And I think we've found the magic formula. The stack: ✦ Mintlify → docs + help articles ✦ Upstash vector → vector search ✦ AI SDK + Claude sonnet → LLM/retrieval ✦ Plain → support infra Here's how it works: We consolidated our docs + help articles on Mintlify (best-in-class docs platform) so all our support content is now in one place. On every push to main, we sync changes to our Upstash Vector DB. We also built a custom chat interface that retrieves content from Upstash Vector and generates responses via AI SDK + Claude sonnet. The best part: The AI agent uses 𝚝𝚘𝚘𝚕() from AI SDK to retrieve the user's workspace / partner data to provide accurate responses. Finally, if the user needs to speak to a human, we generate a 𝚃𝚒𝚌𝚔𝚎𝚝𝚄𝚙𝚕𝚘𝚊𝚍 UI that lets users upload screenshots + add more context, before creating a ticket on Plain. Cherry on top: The chat interface is embeddable, so we're able to embed it both in our Mintlify docs + support portal 👇 Since we launched this, it's been a gamechanger for scaling support – reducing support workload and creating a much better experience for our users. Highly recommend giving this a try!

Steven Tey

22,284 views • 4 months ago

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Avi Chawla

11,927 views • 3 months ago

🆕 Say hello to greater productivity with Zoom Docs, the AI-first collaborative docs solution for Zoom Workplace 👉 Zoom Docs’ AI-first modular design easily adapts to team and project needs, including documents, wikis, tables, and project trackers — providing a single place to manage work 📂✅ With the power of AI Companion, Zoom Docs simplifies work and brings information together for optimal results.

🆕 Say hello to greater productivity with Zoom Docs, the AI-first collaborative docs solution for Zoom Workplace 👉 Zoom Docs’ AI-first modular design easily adapts to team and project needs, including documents, wikis, tables, and project trackers — providing a single place to manage work 📂✅ With the power of AI Companion, Zoom Docs simplifies work and brings information together for optimal results.

Zoom

37,961 views • 1 year ago

One search—across all your apps—with #GeminiEnterprise. Simply ask questions about your work to get specific, actionable answers you need from your meetings, docs, and projects without having to hunt for information →

One search—across all your apps—with #GeminiEnterprise. Simply ask questions about your work to get specific, actionable answers you need from your meetings, docs, and projects without having to hunt for information →

Google Cloud

11,730 views • 6 months ago

IT’S HERE! 🔥 Our BIGGEST feature drop of the year: AI Music Videos! 🎵📽️ 1️⃣ Upload your track 2️⃣ Pick your character 3️⃣ Get a fully custom music video in MINUTES Close out the year with a BANG! Check out the epic sample outputs in the thread 🧵👇

IT’S HERE! 🔥 Our BIGGEST feature drop of the year: AI Music Videos! 🎵📽️ 1️⃣ Upload your track 2️⃣ Pick your character 3️⃣ Get a fully custom music video in MINUTES Close out the year with a BANG! Check out the epic sample outputs in the thread 🧵👇

Affogato AI

3,194,942 views • 1 year ago

Most teams waste hours digging through docs, StackOverflow, and old Slack threads. CA: FCGLv72C18362Ent3BDNqToracaaM2sYukjTXS7hBAGS Support engineers answer the same questions again and again. So I built Slack Integrations 👇 An AI agent that lives directly inside your Slack workspace. • answers technical questions using your docs • runs on an offline RAG pipeline + online inference agent • replaces repetitive support workflows • fully open source • costs less than 0.5 dollars to run Two Python apps. One intelligent Slack agent. No more digging. Just ask.

Most teams waste hours digging through docs, StackOverflow, and old Slack threads. CA: FCGLv72C18362Ent3BDNqToracaaM2sYukjTXS7hBAGS Support engineers answer the same questions again and again. So I built Slack Integrations 👇 An AI agent that lives directly inside your Slack workspace. • answers technical questions using your docs • runs on an offline RAG pipeline + online inference agent • replaces repetitive support workflows • fully open source • costs less than 0.5 dollars to run Two Python apps. One intelligent Slack agent. No more digging. Just ask.

Karthik

18,339 views • 5 months ago

💡Ask anything and get answers that think deeper. With AI Answers in #XiaomiHyperOS3, you can search across text, images, or voice — and get precise, AI-powered responses in seconds.

💡Ask anything and get answers that think deeper. With AI Answers in #XiaomiHyperOS3, you can search across text, images, or voice — and get precise, AI-powered responses in seconds.

Xiaomi HyperOS

10,577 views • 7 months ago

AI can now remember users across conversations 👀 It remembers your team's chaos chats, docs, meeting notes and turns it into actual decks, PRDs, onboarding docs. This is what memory-native AI really means:

AI can now remember users across conversations 👀 It remembers your team's chaos chats, docs, meeting notes and turns it into actual decks, PRDs, onboarding docs. This is what memory-native AI really means:

Eyisha Zyer

20,862 views • 8 months ago

The future of documentation is AI native and personalized. Answers grounded in your source of truth, powered by agentic retrieval, and includes citations for deeper dives. Start by typing cmd + i.

The future of documentation is AI native and personalized. Answers grounded in your source of truth, powered by agentic retrieval, and includes citations for deeper dives. Start by typing cmd + i.

Mintlify

54,726 views • 1 year ago

Your AI agents are giving you generic outputs because they have zero context... I just built a RAG workflow that ingests your data and creates a searchable database that your AI can reference. Now your workflows will give precise, contextual responses instead of generic slop. Follow + comment "RAG" and I'll send you the complete n8n workflow.

Your AI agents are giving you generic outputs because they have zero context... I just built a RAG workflow that ingests your data and creates a searchable database that your AI can reference. Now your workflows will give precise, contextual responses instead of generic slop. Follow + comment "RAG" and I'll send you the complete n8n workflow.

Tom

51,483 views • 1 year ago

Godela is an AI-powered physics engine that gives engineers instant answers to complex questions. No solvers, no code— just upload your design or data and ask. Congrats on the launch, @cinnamonsipper and Abhijit!

Godela is an AI-powered physics engine that gives engineers instant answers to complex questions. No solvers, no code— just upload your design or data and ask. Congrats on the launch, @cinnamonsipper and Abhijit!

Y Combinator

40,147 views • 1 year ago

HTML docs are starting to replace Notion for us. The missing piece was collaboration. So we built a Google Drive for HTML docs with a WYSIWYG editor, commenting, share links, and password protection. It works through MCP. Just ask Claude to upload to Moda:

HTML docs are starting to replace Notion for us. The missing piece was collaboration. So we built a Google Drive for HTML docs with a WYSIWYG editor, commenting, share links, and password protection. It works through MCP. Just ask Claude to upload to Moda:

Anvisha

357,505 views • 1 month ago

🚀 Meet MCS Platform v2.0 – Your Hyper-Intelligent Personal Medical Diagnosis Swarm 🩺 Save time and money with fast, AI-powered medical diagnosis. Skip the wait for a doctor and get accurate insights instantly—right when you need them. MCS Platform v2.0 is here to make healthcare more accessible and efficient. What Makes It Great: 1️⃣ Instant Results: Enter symptoms or upload reports, and let our advanced AI provide clear, reliable diagnostic insights in seconds. 2️⃣ Easy to Use: A simple, intuitive interface designed for anyone to get answers quickly and easily. 3️⃣ Always Reliable: Powered by AI swarm intelligence for precision and efficiency you can trust. 🌐 Try it now Below ⬇️ like and retweet pls ?😊

🚀 Meet MCS Platform v2.0 – Your Hyper-Intelligent Personal Medical Diagnosis Swarm 🩺 Save time and money with fast, AI-powered medical diagnosis. Skip the wait for a doctor and get accurate insights instantly—right when you need them. MCS Platform v2.0 is here to make healthcare more accessible and efficient. What Makes It Great: 1️⃣ Instant Results: Enter symptoms or upload reports, and let our advanced AI provide clear, reliable diagnostic insights in seconds. 2️⃣ Easy to Use: A simple, intuitive interface designed for anyone to get answers quickly and easily. 3️⃣ Always Reliable: Powered by AI swarm intelligence for precision and efficiency you can trust. 🌐 Try it now Below ⬇️ like and retweet pls ?😊

MCS

18,624 views • 1 year ago