- Видео 107
- Просмотров 1 196 100
Leon van Zyl
Южно-Африканская Республика
Добавлен 2 июн 2010
Welcome to my RUclips channel! Here, you'll find a range of programming tutorials and discussions on the latest technology and trends in the full stack development space. I create content for both experienced developers and those just starting out in the field, with a focus on helping you improve your skills and stay up-to-date with the latest advancements in the industry. Tune in for step-by-step guides, advice on best practices, and insights into the most popular technologies and frameworks. Whether you're a seasoned pro or a newcomer to the world of full stack development, there's something for everyone on my channel. Thanks for stopping by, and I hope you enjoy the content!
Build Multi-Agent AI Teams with RAG & Custom Tools! (No-Code) | FlowiseAI
How to Build Multi-Agent AI Teams with RAG & Custom Tools
In this video about building multi-agent AI teams with RAG and Custom Tools you will learn to take take your agentflows to the next level. You will learn how to add a custom knowledge base (a PDF file) to the flow and also create a custom tools for sending emails.
🙏 Support My Channel:
Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl
PayPal Donation: www.paypal.com/ncp/payment/EKRQ8QSGV6CWW
📑 Useful Links:
Make.com: www.make.com/en/register?pc=leonvanzyl
💬 Chat with Like-Minded Individuals on Discord:
discord.gg/VwHZzbNawh
🧠 I can build your chatbots for you!
www.cognaitiv.ai
🕒 TIMESTAMPS:
00:00 - Intro
02:16 - Creating the Agent Team
04:55 -...
In this video about building multi-agent AI teams with RAG and Custom Tools you will learn to take take your agentflows to the next level. You will learn how to add a custom knowledge base (a PDF file) to the flow and also create a custom tools for sending emails.
🙏 Support My Channel:
Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl
PayPal Donation: www.paypal.com/ncp/payment/EKRQ8QSGV6CWW
📑 Useful Links:
Make.com: www.make.com/en/register?pc=leonvanzyl
💬 Chat with Like-Minded Individuals on Discord:
discord.gg/VwHZzbNawh
🧠 I can build your chatbots for you!
www.cognaitiv.ai
🕒 TIMESTAMPS:
00:00 - Intro
02:16 - Creating the Agent Team
04:55 -...
Просмотров: 3 507
Видео
Multi-Modal is POWERFUL! Building an AI Image Generator in MINUTES (No-Code)
Просмотров 1,9 тыс.14 часов назад
In this video you will learn how to build an AI image generator using the multi-modal features of VectorShift. VectorShift is a no-code platform for building AI applications that run in the cloud. We will combine the power of GPT-4o's Vision Capabilities with Dall-E to both extract information from an image AND generate new images using AI. 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeaco...
Building a Lead Gen Chatbot using GPT-4o (No-Code) | VectorShift Tutorial
Просмотров 2,6 тыс.14 дней назад
In this video about Automations in VectorShift, you will learn how to automate everyday tasks using AI and VectorShift. We will use VectorShift automation to automatically create a draft email in Gmail when a Typeform form is submitted. 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl PayPal Donation: www.paypal.com/ncp/payment/EKRQ8QSGV6CWW 📑 Useful Links: VectorShift:...
How to Update Flowise AI (Local, Docker & Render)
Просмотров 2,3 тыс.14 дней назад
How to Update Flowise AI (Local, Docker & Render) In this video about updating Flowise we will go over the processes of updating Flowise in several situations. These include updating Flowise AI globally, in a localized node environment, Docker and Render.com. 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl PayPal Donation: www.paypal.com/ncp/payment/EKRQ8QSGV6CWW 💬 Cha...
How to Build AI Agent Teams (NO-CODE!) | Flowise Agentflows Tutorial
Просмотров 15 тыс.21 день назад
How to Build AI Agent Teams using Flowise Agentflows. Flowise Agentflows makes it easy to build AI Agent Teams using a no-code solution. With agentflows you can assign as many workers to your team / crew as you want. These agents will work together / collaborate to achieve a goal. This is similar to frameworks like CrewAI and Autogen but does not require any coding, so anyone can build AI Agent...
How to Build a Q&A Chatbot with RAG (No Code!) - Langflow Tutorial #3
Просмотров 3,2 тыс.28 дней назад
How to Build a Q&A Chatbot with RAG (No Code!) In this video you will learn how to build a chatbot that is able to answer questions from a database (like Word Documents, PDFs, etc) using RAG and Langflow. 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl PayPal Donation: www.paypal.com/ncp/payment/EKRQ8QSGV6CWW 💬 Chat with Like-Minded Individuals on Discord: discord.gg/V...
How to Create an AI Chatbot with Memory - Langflow Tutorial #2
Просмотров 2,9 тыс.28 дней назад
How to Create an AI Chatbot with Chat Memory with Langflow. In this Langflow tutorial video you will learn how to create an AI Chatbot without writing any code. You will learn many different aspect about Langflow, like Chat Inputs, Chat Outputs, Prompts, the OpenAI node and the Memory node for retrieving conversation history. 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeacoffee.com/leonva...
How to Build AI Apps for FREE (No-Code) - Langflow Tutorial #1
Просмотров 4,7 тыс.28 дней назад
How to Build AI Apps for FREE (No-Code) with Langflow. Langflow is a powerful no-code platform for building advanced AI applications without needed to write any code. In this Langflow Tutorial series you will learn how to set up Langflow locally and you will learn how to navigate the Langflow UI (including the Store). You will also create your first project. 🙏 Support My Channel: Buy me a coffe...
VectorShift: Build an AI Agent that Adapts to User Intent (Multi-Step Actions!)
Просмотров 3,7 тыс.Месяц назад
In this video we will use VectorShift to build an AI agent that can identify the user's intent and then execute specific tasks for that intent. This agent will answer questions from a CSV file (ie. a CSV Agent) and use RAG to answer questions from a knowledge base (a PDF in this instance). 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl PayPal Donation: www.paypal.com/...
Forget OpenAI! Flowise Tool Agents Work with ANYONE (ft. Claude 3)
Просмотров 8 тыс.Месяц назад
Flowise recently added a Tool Agent to the platform. The Flowise Tool Agent allows you to attach any AI model that supports function calling or tool use to it. This means that you are no longer limitedto using OpenAI for creating AI Agents and all other major models are supported - like Gemini, Claude, Groq and more. 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl PayP...
Flowise Record Manager: Stop Duplicate Data Forever!
Просмотров 4,4 тыс.Месяц назад
In this Flowise Record Managers video we will have a look at one of the easiest solutions for preventing duplicate and stale data in your vector stores. 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl PayPal Donation: www.paypal.com/ncp/payment/EKRQ8QSGV6CWW 💬 Chat with Like-Minded Individuals on Discord: discord.gg/VwHZzbNawh 🧠 I can build your chatbots for you! www.c...
How To Use Meta AI in WhatsApp (ft. Llama 3)
Просмотров 14 тыс.2 месяца назад
How To Use Meta AI in WhatsApp In this video on How To Use Meta AI in WhatsApp we will have a look at setting up Meta AI on iPhones and Android devices. We will also have a look at some of the most important features introduced with Llama 3, like the ability to generate AI content, AI images and even search the internet. The Meta AI chatbot in WhatsApp can be incredibly useful for assisting wit...
10x Your Productivity with AI! No-Code Automation with VectorShift
Просмотров 3,2 тыс.2 месяца назад
In this video about Automations in VectorShift, you will learn how to automate everyday tasks using AI and VectorShift. We will use VectorShift automation to automatically create a draft email in Gmail when a Typeform form is submitted. 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl PayPal Donation: www.paypal.com/ncp/payment/EKRQ8QSGV6CWW 📑 Useful Links: VectorShift:...
8 SECRET Flowise AI Features You DIDN'T Know Existed (Supercharge Your Workflow!)
Просмотров 6 тыс.2 месяца назад
In this Flowise AI video we will have a look at 8 Secret Features in Flowise that will greatly improve your chatflows. We will have a look at Multi Modal support, like Vision and Speech to Text, Starter Prompts, Chat Feedback and much more. 🙏 Support My Channel: Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl PayPal Donation: www.paypal.com/ncp/payment/EKRQ8QSGV6CWW 💬 Chat with Like-Minded ...
Claude 3 Tool Use (Function Calling) Tutorial | JavaScript & Anthropic API
Просмотров 1,8 тыс.2 месяца назад
Claude 3 Tool Use (Function Calling) Tutorial | JavaScript & Anthropic API
VectorShift: New No-code AI builder that Live-Sync to Your Data
Просмотров 6 тыс.2 месяца назад
VectorShift: New No-code AI builder that Live-Sync to Your Data
NVIDIA Chat with RTX: Free, Local RAG Chatbot
Просмотров 3,2 тыс.2 месяца назад
NVIDIA Chat with RTX: Free, Local RAG Chatbot
FREE AI in Flowise! Use Hugging Face Models (No Code)
Просмотров 8 тыс.2 месяца назад
FREE AI in Flowise! Use Hugging Face Models (No Code)
Add Flowise to ANYTHING! Flowise API Crash Course
Просмотров 14 тыс.3 месяца назад
Add Flowise to ANYTHING! Flowise API Crash Course
Claude 3 API Crash Course for BEGINNERS (Haiku, Sonnet, Opus)
Просмотров 2,4 тыс.3 месяца назад
Claude 3 API Crash Course for BEGINNERS (Haiku, Sonnet, Opus)
Flowise Ollama Tutorial | How to Load Local LLM on Flowise
Просмотров 11 тыс.3 месяца назад
Flowise Ollama Tutorial | How to Load Local LLM on Flowise
OpenAI Vision API Crash Course - Chat with Images (Node)
Просмотров 2,5 тыс.3 месяца назад
OpenAI Vision API Crash Course - Chat with Images (Node)
Adding AI Chatbots to Websites - FlowiseAI Tutorial #10
Просмотров 7 тыс.3 месяца назад
Adding AI Chatbots to Websites - FlowiseAI Tutorial #10
How To Access Flowise From ANYWHERE - Flowise Tutorial #9
Просмотров 7 тыс.3 месяца назад
How To Access Flowise From ANYWHERE - Flowise Tutorial #9
Building a Personal Assistant using Agents (no-code) - Flowise Tutorial #8
Просмотров 16 тыс.4 месяца назад
Building a Personal Assistant using Agents (no-code) - Flowise Tutorial #8
Analysing Chatflows using LangSmith - FlowiseAI Tutorial #7
Просмотров 7 тыс.4 месяца назад
Analysing Chatflows using LangSmith - FlowiseAI Tutorial #7
Chatting With Your Own Data! Chat, Predict, & Analyze - FlowiseAI Tutorial #6
Просмотров 22 тыс.4 месяца назад
Chatting With Your Own Data! Chat, Predict, & Analyze - FlowiseAI Tutorial #6
Building Chatbots with Long-Term Memory - FlowiseAI Tutorial #5
Просмотров 11 тыс.4 месяца назад
Building Chatbots with Long-Term Memory - FlowiseAI Tutorial #5
LangChain Tutorial (Python) #7: Long Term Chat Memory with Upstash Redis
Просмотров 4,6 тыс.4 месяца назад
LangChain Tutorial (Python) #7: Long Term Chat Memory with Upstash Redis
LangChain Tutorial (JS) #7: Long Term Conversation Memory
Просмотров 3,5 тыс.4 месяца назад
LangChain Tutorial (JS) #7: Long Term Conversation Memory
Awesome video Leon! Love the use of the prompt engineering team! So helpful - My workers are working overtime :D
Awsome!
Awesome, you came through!
You're welcome 😁
Hi Leon. Great video. Can I use azure instead of openai?
Yes, you can use any model that supports function calling
excellent video leon, thanks!!🙏 I have a problem with the chat, I can upload my document correctly, but when the worker reads the file it cuts the information in half, I need it to read 60 texts and generate a summary, but it only just give me 30 back
Try increasing the k number on the vector store node. Typically using a vector store to summarise data is counter intuitive, but you might have more luck if you increase the number of docs returned. You could also consider to upload the entire doc without any chunking.
Great video
Thank you
Very nice video, and my compliments on the Google setup. It is one of the simplest, most straightforward presentations I have seen. Most are overly complex and difficult to follow, which usually results in failure. However, in the code generation example, I would have liked to see an example in which the code is executed to get some idea of the quality of the generated code. Thanks for another great video. Wayne
Thank you Wayne, I appreciate your constructive feedback 🙏
Excellent presentation, thank you.
Thank YOU
Thank you sir for all of this!
when I connect retriever tool to the Worker I get: "Aborted! Error: Aborted! at agentNode (/opt/render/project/src/packages/components/dist/nodes/multiagents/Worker/Worker.js:239:15) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async RunnableLambda.workerNode [as func] (/opt/render/project/src/packages/components/dist/nodes/multiagents/Worker/Worker.js:106:53) at async /opt/render/project/src/node_modules/.pnpm/@langchain+core@0.1.63/node_modules/@langchain/core/dist/runnables/base.cjs:1337:34 as well as 400 Invalid 'tools[0].function.name': string does not match pattern. Expected a string that matches the pattern '^[a-zA-Z0-9_-]+$'. Error: 400 Invalid 'tools[0].function.name': string does not match pattern. Expected a string that matches the pattern '^[a-zA-Z0-9_-]+$'. at APIError.generate (/opt/render/project/src/node_modules/.pnpm/openai@4.51.0_encoding@0.1.13/node_modules/openai/error.js:45:20) at OpenAI.makeStatusError (/opt/render/project/src/node_modules/.pnpm/openai@4.51.0_encoding@0.1.13/node_modules/openai/core.js:275:33) at OpenAI.makeRequest (/opt/render/project/src/node_modules/.pnpm/openai@4.51.0_encoding@0.1.13/node_modules/openai/core.js:318:30) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async /opt/render/project/src/node_modules/.pnpm/@langchain+openai@0.0.30_encoding@0.1.13/node_modules/@langchain/openai/dist/chat_models.cjs:760:29 at async RetryOperation._fn (/opt/render/project/src/node_modules/.pnpm/p-retry@4.6.2/node_modules/p-retry/index.js:50:12) any ideas? If i run the whole setting at a normal Conversational retrieval QA Chain it works...
first of all thanks for the amazing content :*
What did you name the tool? I think your tool name contains some invalid characters. It needs to be all lowercase with no spaces. Use underscrores (_) instead of spaces.
@@leonvanzyl yep spacing.... no spacing in the title 🙈 thaaaaaaaanks
Hey Leon, great video! Is there a way to parse the information that is coming out from retrieving the document say in CSV format from the supervisor's end?
You would basically have to create two separate flows, where an LLM chain calls the agentflow and then parses the information. Happy to create a video on it, just can't think of a use-case? Mind sharing yours?
@@leonvanzyl Oh that makes sense! Thanks. My use-case is a bit complex, but in short, I am trying to retrieve information from a medical guideline document, and turn the result into a downloadable table for the providers.
Langflow v1 is now available and we no longer need to install the pre-release build. In order to install Langflow, simply run: pip install langflow
Hi ... would you consider Langflow v1 stable? You mentioned in another post that re: "issues with stability and lack of reliable way to deploy the platform" . Do you know if these issues are addressed in this release?
You solved the problem that I had witk Gmail API and Make before. Thank you very much!
Haha, glad I could help
Your presentatiom is so perfect that makes me feel really lucky! Very well done, Leon!!! Congratulations!!!
Wow, thank you!!
Great video!!! How can I create a worker that access a database? Thanks a lot!!
This is Gold❤ Thank you, Leon!! Excellent as always! ❤👌🙏🥇
Thank you! 😊
Another great video, thank you Leon! Since Flowise uses LangGraph to orchestrate the multi-agents workflows, how can such workflows be extended with Conditional Edges and Loops?
I know that conditional edges are coming soon. Will definitely create videos as these features roll out 👍
video showing calls with n8n would great to keep it all self hosted and open
Flowise is also self hosted and free 😊. I'll definitely create videos on n8n soon. For interest sake, where do you host your n8n instance?
how to call ollama endpoint from Flowise on cloud?
You would have to find a way to host Ollama in the cloud as well... which is not really in scope for a Flowise tutorial. I'm sure there are some resources out there for an "Ollama Deployment".
How can we keep the human in the loop to review and steer the output of the agents at each step?
Another great job!
Thank you 😊
You've truly made my day! Your remarkable effort in putting it all together is appreciated. Thank you!
You're welcome 🤗
great video - thank you for sharing - Claude 3.5 is now available :) - I will try to do some mix diffrent models agents:)
Sounds awesome!
Flowise or langgraph or crewai ?
Agentflow is LangGraph
Nice job leon! Thanks! I would love to see an integration between flowise and WhatsApp 🤞
Great video as always sir, please continue bringing content on Agents. Is it possible yet to have a human in the loop? Like to approve/reject agent's work before proceeding?
Will do 👍. Not possible to create human in the loop [yet].
@@leonvanzyl thanks, I will keep an eye on it, I think once Langchain/Flowise allow a human in the loop to steer the agent's work, it will be terrific and an easier decision for companies. Thanks.
Need more videos on Agents
Will do
Thanks for making this! Have you had much success with other models besides ChatGPT?
Yes, the Anthropic models are brilliant!
Just what i needed right now. Good timing :)
Hehe, you're welcome 🤗
Can you make a video where you connect to a MySql DB and ask in natural language questions and retrieve data from the DB?
Hi Leon, quick question. With Autogen Studio, I can build an agent team that uses a tool\skill that can authenticate to Azure via the Graph API with specific authentication parameters (Tenant ID, Secret, etc...), and other agents can then write bespoke code that can use that authentication to answer my query e.g. how many users do not have MFA or add users to a group where the manager is Bob Smith. My question is "Can this same dynamic query\coding be created using a common authentication via Graph API with Flowise?" So far my Flowise experience has been that I have to create a custom tool for every conceivable scenario, as opposed to letting agents create and refine code dynamically and incorporate the correct Graph API authentication parameters to achieve the goal.
Really useful, as always, Thanks so much, Lyon!!
You're welcome 🤗
@Leon Van Zyl, how do I get in touch, sent email via website, and discord is dead?
I'll see if I can find your mail. Inbox is quite busy 😜
@@leonvanzyl appreciate it
So incredibly helpful
You're welcome 🤗
Hello Leon, this platform is not self-hosted like Flowise (free). What advantages does it offer compared to Flowise for migrating?
i wish like comfy ui you can just drop a file into empty canvas and it populates all these nodes
You can import an existing flow, if that's what you mean? The marketplace is full of templates that you can simply copy into your own space.
@@leonvanzyl ok maybe the marketplace has better examples now, but you don't really previously one's like you just did, they were all very basic before
Thank you for the tut. Does it have any advantages before a single agent with multiple tools? Like executing RAG via Chain, Retriever or Chatflow tool?
You're welcome! Plenty of advantages. You could assign different models to each worker based on their role. For instance, a coder agent could have model assigned to it that is brilliant at producing code, etc. I like splitting the roles and responsibilities across different agents as apposed to forcing everything into a single agent.
You can prompt the different agents to be expert XYZ like in a company you would have different divisions or specialised workers and not just one person doing everything
@@leonvanzyl Thank you!
Thanks a lot !
Great video boss! . Btw Can u do a video on flowise where a customer chatbot send an automatic emails to client regarding the conversation had or any important information
You're welcome! This is an interesting use-case. I am planning to create a video on using agentflows with memory in the future, and this might be a good use-case for the tutorial.
@@leonvanzyl Thank you , That sounds perfect. Can't wait for that video 😃👌
So useful. Thanks!
You're welcome 🤗
This is even better than the outdated and paid materials out there. Thank you for your efforts
Wow, thank you!
temperature is set at 0.3 but still bring up unwanted stuff. Also replaced buffer window with a upstash redis memory. This helped in increasing the context window . But hallucination has not stopped :(
Rey adjusting the system prompt to instruct the model to not make it answers.
I have a question: is there any way to use gpt-4o model now in Flowise, the date today is 24/6/2024. Thanks in advance
Yes! Flowise added GPT4o support the moment the model was made available. Just update your Flowise instance
@@leonvanzyl Oh right thanks a lot
Also, people can use huggingface 'sentence-transformers/all-MiniLM-L6-v2 ' model for free embedding and Gemini instead of openAI llm for free
thank you so much . Redis mem made a lot of difference and my chatbot answers everything perfectly.
can the chatbot be called by iOS apps?
Yes, the iOS apps can call the Flowise APIs.
super super helpful!! can you teach us how to deploy on Google cloud? Thanks~
It would be awesome if you could show a way to iterate on result in a way like "Artifacts" of Claude3.5. (if it's possible)
Thanks. If we update Docker container, do we loose our workflows?
can you please share the link to booking agent video?
Hey Leon. I get "Message Stopped" when I provide an input, not executing my request. Do you happen to know a solution for this?
Same Here ! if you can find the answer I'm willing :)