- Видео 151
- Просмотров 141 849
Cloud Number 9
Добавлен 22 мар 2010
Welcome to Cloud No 9: Where Tech Meets Vision!
I'm a Tech-Strategic Consultant, AI Strategist Advisor, and a Mentor at Google for Startups and a GDE. At Cloud No 9, we specialize in blending cutting-edge internet trends with insightful business strategies.
Join me in a journey from the ground up, as we bootstrap innovative projects to successful customer launches. Cloud No 9 isn't just a channel; it's a launchpad for ideas that believe in the transformative power of technology for the greater good.
As we explore the dynamic interplay of technology and entrepreneurship, Cloud No 9 is your hub for inspiration and groundbreaking insights. Together, let's navigate the skies of innovation and shape a better, tech-driven tomorrow.
I'm a Tech-Strategic Consultant, AI Strategist Advisor, and a Mentor at Google for Startups and a GDE. At Cloud No 9, we specialize in blending cutting-edge internet trends with insightful business strategies.
Join me in a journey from the ground up, as we bootstrap innovative projects to successful customer launches. Cloud No 9 isn't just a channel; it's a launchpad for ideas that believe in the transformative power of technology for the greater good.
As we explore the dynamic interplay of technology and entrepreneurship, Cloud No 9 is your hub for inspiration and groundbreaking insights. Together, let's navigate the skies of innovation and shape a better, tech-driven tomorrow.
Understanding RAG: Retrieval Augmented Generation in AI
Dive into the fascinating world of Retrieval Augmented Generation (RAG) in AI! In this video, we explore the history, definition, and mechanics of RAG. Discover how RAG enhances the responses of Large Language Models (LLMs) by integrating real-time retrieval of relevant information. We'll also delve into the concepts of embedding and vector databases. Whether you're an AI enthusiast or a curious learner, this video provides clear examples and insightful explanations to help you understand the power and potential of RAG in modern AI technology. Don't miss out on this enlightening journey into AI advancements!
00:00 intro
00:38 History of RAG
01:43 What is RAG
04:10 Solving the problem - The hu...
00:00 intro
00:38 History of RAG
01:43 What is RAG
04:10 Solving the problem - The hu...
Просмотров: 493
Видео
Google's Scariest API Yet? What You Must Know about DPAPI
Просмотров 1,6 тыс.3 месяца назад
In this video, I explore Google's Data Portability API (DPAPI), arguably the most concerning API Google has released to date. I'll walk you through what DPAPI is, highlighting its potential to significantly impact our privacy. I stress the importance of being vigilant about the data permissions we grant to services, sharing my personal approach to safeguarding my data privacy and encouraging yo...
Google's Data Portability API - Quick Start
Просмотров 1384 месяца назад
A developer's guide to the Data Portability API (DPAPI) v1 Beta. DPAPI is a new API that allows users to transfer their data from Google services to other services. This video will show you how to build an app that use DPAPI to transfer user Google data to another service. Google documents: developers.google.com/data-portability My repo: github.com/kulaone/DP_API-quickstart Linda Lawton channel...
Software Developer - How to Survive the AI Revolution
Просмотров 2296 месяцев назад
Are AI tools the new tractors in the field of software development? Join me in this thought-provoking video where I delve into the inevitable impact of AI on software developers' jobs. I not only discuss the future of our profession in an AI-dominated world, but also provide practical advice on how to stay ahead of the curve. Learn how to harness AI tools effectively for coding. Link to the T-s...
Gemini Pro Vision on Cloud Functions
Просмотров 2476 месяцев назад
In this video, I show you how to use Gemini Pro Vision with Vertex AI on cloud functions. It's easier than you think! Link to the code: github.com/kulaone/cn9_gemini_pro_vision_cf Link to Deploying LangChain on Cloud Functions: ruclips.net/video/q_vrmT8MyEs/видео.html 00:00 Intro 00:09 Create a Cloud Function 01:28 Add Vertex AI 06:13 Front-End 07:58 Fix and Test 10:21 End
ChatGPT - Are we using it WRONG???
Просмотров 9957 месяцев назад
Let's explore the world of AI chatbots! In this video, we explore whether we're really using ChatGPT and other chatbots to their full potential or if there's more to these digital tools than meets the eye. Discover the surprising ways to interact with ChatGPT, and let's rethink our approach to these incredible AI companions. Links to chatbots: ChatGPT - chat.openai.com Bard - bard.google.com Cl...
Deploying LangChain on Cloud Functions
Просмотров 8767 месяцев назад
Join me, as I guide you through the seamless process of deploying LangChain to Cloud Functions. This tutorial is perfect for developers and AI enthusiasts looking to elevate their LLM projects from Colab notebooks to a more robust and secure cloud environment. We'll explore the benefits of using Cloud Functions, demonstrate the deployment process step-by-step, and discuss how LangChain's framew...
?!?!סבא צ׳טבטו וחברים, טרנד חולף
Просмотров 184Год назад
האם מדובר בטרנד חולף או טכנולוגיה שתשנה את העולם?
You probably don't need zoom for that.
Просмотров 404 года назад
Zoom is not the best way for one on one meeting/video chatting. Here is what I think you need to use instead. Link to whereby: whereby.com/ Link to Google calendar: calendar.google.com/ Link to Google hangouts: hangouts.google.com/
Google project Jacquard (Hebrew review)
Просмотров 1598 лет назад
Google project Jacquard (Hebrew review)
Oneplus One second review(after 3 month) ((Hebrew))
Просмотров 4269 лет назад
Oneplus One second review(after 3 month) ((Hebrew))
This is awesome. I'd love to see one where we pass, for example, a Firebase auth user to the function so that the langchain chatflow only utilizes data/vectors/prompts that are specific and limited to the authorized user.
Yes, that is the main idea. I'm using it with RAG so that each user has access only to documents based on their authorisation level.
@@cloud_no_9 Nice! I'm playing with the new Firestore Semantic Search extension. It's still very early, but solves the vertexai issue of not storing the vectors with the user's docs. Haven't yet figured out how to a) get a file upload to generate embeddings through this extension or how to integrate it directly with Gemini or other components in the GCP stack, but it's worth pecking around to see if I can make it work. I like keeping the data and the vectors right there under tight auth from Firebase and doing as few external integrations as possible. One nice thing is that each vector embedding with that extension is an item in a list/array of floats/doubles rather than a separate row or document like in a Pinecone or Supabase implementation. Means I don't need a subcollection to manage the vectors under a large file....if I can figure out how to get the extension to work with files (there is a workaround) the way it does with the immediate document content, where it generates a "embedding" list field and a separate tracking collection to do record management, so that changes to data don't get out of sync with vectors.
That's why i don't store anything in Google... Email and that's it
Hey, listen to your audio on something that's capable of rendering bass. Every time you thump the table, there's a loud low boom. Not an audio expert, so no clue how to fix it, but perhaps not mount (or place) the mic on the desk might be a good start? I think it's vibrations carried through the microphone stand into the microphone itself.
Thank you so much for taking the time to point this out! I hadn't realized how the thumping on the table was affecting the audio quality. I'll definitely look into better ways to position or mount the microphone to avoid this issue in the future. Thanks again for your helpful feedback!
@@cloud_no_9 Sure thing man. Thank _you_ for the informative video!
Your AI generated thumbnail has a typo. Shocking.
I would say this API is appropriately named...
More people need to see this video. Blanket permissions are disastrous.
I'm very curious to see what this would return for my account since I have both search history and location history turned off
You can use Google Takeout or My Activity to see that. myactivity.google.com/myactivity
great video. i agree with you. its scary. i really think its time to degoogle my life. i use google timeline and such because i like seeing where i was at what point - its so convinient. but to see them knowing about political views like that and such is kinda nuts. its probably time to invest some time to really start and find a way to create a similar experience with selfhosted solutions.
Are there good self-hosted solutions that can give the same high level of services like Google?
I think this method returns the answers in one go. How do you stream the response? Also how do you process documents, which is a good feature of Langchain?
You're correct, the method shown in the video returns the answers in one go, primarily because Cloud Functions doesn't support streaming or chunked responses. This is a limitation I'm aware of, and I'm exploring possible solutions. Once I've developed a robust method, I plan to create a follow-up video to share the solution. In the meantime, if you're looking to implement a streaming response, you might consider converting your code to run on Cloud Run, which supports server-side streaming. Regarding document processing, I utilize Cloud Functions to fetch the document initially. After retrieval, I employ langchain.document_loaders to segment the document into manageable parts, embed these parts, and subsequently store them in a vector database. This setup is particularly useful for implementing Retriever-Reader models like RAG (Retrieval-Augmented Generation), allowing for more dynamic and contextually aware responses. Stay tuned for updates, and thank you for your interest.
Less workforce needed for each line of code, but each coder can produce so much more. This is fine for me, as I only work on my own projects.
Totally agree with you. I think we're going to see much more entrepreneurs bootstrapping with smaller teams or just by themselves.
Thank you, it's the first video I've come across which really summarizes how to properly deploy Langchain to GCP!
Great to hear!
good job!
🎯 Key Takeaways for quick navigation: 00:00 🤖 *Suggests that perceived limitations of ChatGPT may stem from incorrect usage rather than the tool itself.* 00:31 📚 *Compares chatbots to librarians in a vast library, adept at fetching information but with limited understanding.* 01:01 🧒 *Likens LLMs to a 10-year-old librarian who can find and read information but may lack deeper comprehension.* 01:30 🧮 *Points out the limitations of LLMs in solving complex problems without specific guidance.* 02:00 ⌛ *Notes the rapid development of chatbot technology, anticipating future advancements.* 02:28 🤔 *Highlights the chatbot's strength in information gathering but limitation in processing advanced concepts.* 02:59 🎭 *Discusses the "Must Obey" rule of chatbots, leading them to fabricate answers when uncertain.* 04:01 📜 *Explains the influence of a chatbot's programming rules on its response capabilities.* 04:57 🕵️♂️ *Suggests creative ways to bypass chatbot limitations while adhering to their rules.* 05:55 🤝 *Recommends using chatbots as companions for thought processes rather than just for Q&A.* 07:21 💭 *Proposes using chatbots as external tools to expand and enhance personal thinking processes.* 08:28 🏆 *Emphasizes the importance of the user's expertise when interacting with chatbots.* 10:07 👨🏫 *Advises leveraging chatbots to supplement, not replace, one's own knowledge and expertise.* 11:12 ⏰ *Stresses the value of investing time in learning and understanding how to use chatbots effectively.* 12:09 🎭 *Notes the varying personalities and capabilities of different chatbots based on their training and rules.* 13:08 🔄 *Highlights the evolving nature of ChatGPT and the need to adapt prompts for newer versions.* 14:11 🔁 *Discusses using various chatbots for different tasks based on their unique strengths.* 15:09 🗣️ *Mentions Claude's efficiency in handling large information sets with minimal hallucination.* 16:10 🧠 *Points out Pi's design for more emotional and deep conversations.* 17:15 💻 *Highlights Phind's utility for software developers in writing better code.* 18:18 🤹♂️ *Encourages experimenting with different chatbots to find the best one for a specific task.* 19:23 🛠️ *Likens using multiple chatbots to choosing the right tool for a job, each with its unique advantages.* Made with HARPA AI
Great info. Thank you!
Thanks for the listing and reviewing the different available ChatBots. Interesting approach here. Thanks for the guide!
Glad it was helpful!
Very nice coverage. Surprised you only have 436 subscribers. You need to post more often!
Thanks! Working on it!
Bro, if you have inner dialogue... You PROBABLY have a chip implant. 8 I think the pilot program started in the late 70's. By the kid 80's nearly all us chipped. AI microchips implanted in infants... Or first availability. Good age, I'm guessing you have a chip, anyone over 40 that didn't get one when they were still in the maternity ward... Got it under anaesthesia.
Is there an easy way to ask all these ai bots the same question and then click through to continue with the one that you think answered the best?
Hi Michael, Regarding your question: As much as I know, there isn't a straightforward method available for this, especially for general users. Each major AI chatbot, operates within its own unique platform, necessitating separate interactions with each bot. However, based on my experience, there is a potential workaround for those with programming skills. It involves using the APIs of these chatbots. By writing a custom script or program, it's possible to send a query to multiple AI services simultaneously and gather their responses. In fact, I've explored similar topics in my work and even written an article about it, which you can find here: medium.com/p/eb0158618b66. This article might offer some insights or guidance if you interested in pursuing a similar approach.
Great vid. Thanks so much. It's really helpful
Great explainer!
האם אפשר להגדיר מה כן יעבור ומה לא כי לא מתאים לי שהכל יעבור לדרופבוקס והכל מתמלא מהרבה דברים שאני לא מעונינת אז מה עושים
אני כבר שנים לא משתמש בדרופבוקס (הסרטון מלפני 11 שנה), אז יש מצב שהתשובה שלי לא מעודכנת. אפשר להגדיר איזה ספריות יעלו לענן ואיזה לא, אז בגדול אפשר לקבוע שיש ספריות קבועות שתמיד מגובות ואז אין בעיה עם שאר הקבצים שלא רוצים לסנכרן.
היי, האם אני יכול להתחבר בעזרת אפליקציה של גוגל הום לטלויזיה חכמה או לרמקול עם chromecast מובנה? או שהאפשרות הזו חסומה בישראל?
איך אני מוצא את האתר?
mail.google.com/
אני בבית
שלום לרשום שם בעברית אנגלית לפני סיבסמת הבנק או רק סיסמת הבנק.
איך זה עובד היום כי האפליקציה עודכנה???
אני לא משתמש באפליקצה הזו יותר. יש את השירות של גוגל, עושה את העבודה מעולה. פשוט תכתוב בחיפוש בגוגל ״where is my phone״
אחלה, עובד !
היי בבבקשה חשוב לי מאוד... יש לי רמקול של google home שקניתי מארה"ב , רק רוצה לדעת איך אפשר לנגן שירים ביוטיוב עליו...אשמח לעזרה ממך... תודה מראש2020
שלח לי באימייל ממש חשוב לי תודה רבה לך... shmuelo1234@gmail.com
זה חינם?
לא בא לי להרוס לך ,אבל המבטא שלך ממש גרוע ואתה מדבר בשפה לשונית מאוד נמוכה, ולכן היא לא מבינה אותך. צריך לדבר מאוד ברור עם מערכות בסגנון הזה.
why dont you specify what language your speaking to save the world time by accidentally clicking on this....?
I updated the name of the video, Thanks for the tip.
איך עושים את זה!!!???
היי קיבלתי גוגל הום מטנה, לא הצלחנו להתחבר ליוטיוב, גם לא לדיזר וגם זה בלתי אפשרי להירשם לגוגל מיוזיק....מאחזב מאוד, לא מתאים לארץ.
אני לא מצליח לעביר מצגת ppt ל - prezi אשמח לעזרה בעניין . תודה
שלום דניאל, אני כבר שנים לא משתמש בפריזי למצגות. שווה לעשות חיפוש בגוגל ולחפש את התשובה לשאלה שלך
מי שלא יודע איך לעלות סרטון ליוטיוב שיבדוק ביוטיוב בי
הי הבנתי שהשימוש בגוגל הום מחייב לפתוח ולהרשם עם גימייל אמריקאי על מנת שיעבוד עם יוטיוב גוגל פלי וכו?? בנוסף אם יש לי כבר מספר מוצרים חכמים של שיאומי האם הגוגל הום יושע להתממשק אליהם?
Gal asulin הצלחת להתחבר? אצלנו לא עובד, כלום, מוזיקה לא עוברת. .
איך הסתדרת עם זה שהמטען לגוגל הום הוא משתמש בשקע אמריקאי?
השנאי תומך ב 110 וגם 220 אז כל מה שצריך זה רק מתאם לחשמל.
KulaOneIL תודה רבה אני מזמין עכשיו גוגל הום
אם יש לי מכשיר שנמחקו לו ישומי מערכת ואיפוס לא עוזר האם התקנת הרום (גרסה מחדש לאנדרואיד) תעזור לפון??
קשה לי לדעת מה בדיוק הבעיה ולכן אני לא יודע האם זה יעזור. אבל שווה לקפוץ למעבדה או למישהו שמבין
KulaOneIL דרך איזה אפליקציה זה נמחק
לא הבנתי את השאלה, בכל מקרה, אני חוזר על ההמלצה שלי. שווה לבדוק במעבדה או אצל מישהו שמבין בתחום.
אם הטלפון כבוי זה עובד?
לא, אבל היום אפשר להשתמש בכלים של גוגל לחיפוש הטלפון: myaccount.google.com/find-your-phone
לא. גם הכלי גוגל לא יעזרו..
אבל איך מעלים ליוטיוב
כשפרסמתי את זה לפני 6 שנים, זה היה חלק אינטגרלי ביוטיוב. אני מאמין שהיום גם יש להם דרך לשמור את זה ביוטיוב. חפש באתר שלהם: goanimate.com/
ייכנכעככמיכבניטמכרחצמהבכראאינצן9טא רב נחטטח
יש לך גם סקירה על 1+3 ?
לא.
לא רשמת בסוף מהי המצלמה!
רשום בכותרת Theta
אדיר
תחזור להעלות סירטונים בבקשה
אפשר לקבל את הכתובת של החנות/מעבדה? בבקשה :)
+Belle Sch. www.vmobile.co.il/
מאיפה אתה מקבל את כל הטלפונים והמוצרים עליהם אתה עושה סקירה?
וואו! אחד הסרטונים החזקים ביותר שלך
איך הצלחת לעלות תסרטון ליוטיוב בלי לשלם תענה מהר (:
ספרים של אמבר בצד שמאל שם? :)