- 23
- 50 860
Thomas Ingram
เข้าร่วมเมื่อ 30 ธ.ค. 2009
Create Advanced Sequential AI Agents in Flowise + N8N With Vision and Web Design Skills | Part 1
Are you ready to give your AI Agents superpowers such as vision, coding and web design skills? With the latest models such as Google Gemini 1.5 Pro and DeepSeek Coder you can accelerate your Agency workflows.
In this video we will walk you through a Real Time Web Design Agent and Coding team that can analyze images of web pages and generate HTML code.
We'll also show you how you can use Flowise to upload and analyze any image using the image upload feature in Flowise.
If you'd like to get access to this entire Agent workflow, it's now available as as a apart of our updated Flowise Core Essentials training. This full course is perfect for anyone who wants to learn how to build with AI using Flowise. See the link below for al the details:
Flowise Mastery Training 2025:
onyxstudiosinteractive.com/flowise-core-essentials
AI Consulting:
onyxstudiosinteractive.com/consulting/
In this video we will walk you through a Real Time Web Design Agent and Coding team that can analyze images of web pages and generate HTML code.
We'll also show you how you can use Flowise to upload and analyze any image using the image upload feature in Flowise.
If you'd like to get access to this entire Agent workflow, it's now available as as a apart of our updated Flowise Core Essentials training. This full course is perfect for anyone who wants to learn how to build with AI using Flowise. See the link below for al the details:
Flowise Mastery Training 2025:
onyxstudiosinteractive.com/flowise-core-essentials
AI Consulting:
onyxstudiosinteractive.com/consulting/
มุมมอง: 204
วีดีโอ
Create Advanced Sequential AI Agents in Flowise + N8N With Vision and Web Design Skills | Part 2
มุมมอง 3549 ชั่วโมงที่ผ่านมา
Are you ready to give your AI Agents advanced powers such as vision, coding and web design skills? With the latest models such as Google Gemini 1.5 Pro and DeepSeek Coder this is now possible. In this video, We'll show you how to create an agentic workflow that generates original mobile responsive web pages using vision, coding, and research tools. We'll also cover 3x powerful N8N automations t...
How to Improve Your RAG Chatbot Accuracy with N8N and Rerankers (Part 2)
มุมมอง 344หลายเดือนก่อน
► Clone/Copy this Agentflow and Download the Code: onyxstudiosinteractive.com/n8n-automation-pegasus-workflow Episode 9 Slides: onyxstudiosinteractive.com/episode-9-slides-download/ Want to make your RAG chatbot and AI responses even more reliable and accurate? If so you'll want to include Rerankers in your AI toolkit.... Rerankers are algorithms that take the documents returned by your RAG Vec...
How to Improve Your RAG Chatbot Accuracy with Flowise and Rerankers (Part 1)
มุมมอง 461หลายเดือนก่อน
► Clone/Copy this Agentflow and Download the Code: onyxstudiosinteractive.com/n8n-automation-pegasus-workflow Episode 9 Slides: onyxstudiosinteractive.com/episode-9-slides-download/ Want to make your RAG chatbot responses even more reliable and accurate? In this episode, we'll dive into the world of Rerankers - powerful algorithms that rank documents based on relevance to the original question,...
How to Build Advanced AI Ecommerce Agents using Flowise, Postgres and N8N (Text-to-SQL) | Part 1
มุมมอง 3.1K2 หลายเดือนก่อน
► Clone/Copy this Agentflow and Download the Code: onyxstudiosinteractive.com/ecom-agents-download Ecommerce AI Agents are here and ready to take over your website chat... Take your ecommerce business to the next level with AI-powered product recommendations. In this video, you'll learn how to build an advanced ecommerce AI agent that can understand customer conversations and recommend products...
How to Build Advanced AI Ecommerce Agents using Flowise, Postgres and N8N (E2B) | Part 2
มุมมอง 9802 หลายเดือนก่อน
► Clone/Copy this Agentflow and Download the Code: onyxstudiosinteractive.com/ecom-agents-download In part one of this Episode we built an AI agent for our ecommerce website chat that could recommend products to customers. However now it's time to talk about how our agent can also help us analyze ecommerce sales data to produce charts and graphs using E2B sandboxes. In order to test our agent, ...
Flowise Core Essentials: Learn the Fundamentals of Flowise and Build Custom AI Applications
มุมมอง 5224 หลายเดือนก่อน
Have you ever wanted to learn more about Flowise and its extensive features to build powerful chatbots? In this course, we'll introduce you to the essential Flowise concepts and techniques so you can create and deploy effective chatbots without needing any coding experience. onyxstudiosinteractive.com/flowise-core-essentials Flowise is a versatile platform for building flexible chatbots for cus...
Flowise AI 2 What's New?! Top 7 Features to Build Your AI Chatbots | Part 1
มุมมอง 1.8K4 หลายเดือนก่อน
Flowise version 2.0 has arrived, and it's packed with exciting new features and tools to help you build your chatbots. In this video, we'll cover the latest updates and features of Flowise 2.0, including the introduction of Flowise Cloud and Sequential Agents. ► Clone/Copy this Sequential Agentflow and Download the Code: onyxstudiosinteractive.com/flight-booking-agent-download ► Need More Flowi...
How To Create Sequential Agents in Flowise and Build Next-Level AI Applications! | Part 2
มุมมอง 5K4 หลายเดือนก่อน
Unlock the full potential of Flowise 2.0 with Sequential Agents, the cutting-edge feature that enables you to create complex chat flows and AI applications where teams of agents work in harmony. In this video, we walk you through the development of a Flight Booking System utilizing real-time API flight data and a dynamic set of sequential agents that collaborate to search for flights and manage...
Creating Mobile Apps with Flowise and Flutterflow | Part 2
มุมมอง 1.1K7 หลายเดือนก่อน
This episode has taken me some time to produce, however now that Flowise has been out, it's time to start building some real world apps! Once you've created a few chatflows, integrating them into custom web and mobile applications can help add even more capabilities and superpowers to your projects. In this video, we'll introduce you to Flutterflow, a low code platform for creating beautiful cu...
Creating Mobile Apps with Flowise and Flutterflow | Part 1
มุมมอง 1.5K7 หลายเดือนก่อน
This episode has taken me some time to produce, however now that Flowise has been out, it's time to start building some real world apps! Once you've created a few chatflows, integrating them into custom web and mobile applications can help add even more capabilities and superpowers to your projects. In this video, we'll introduce you to Flutterflow, a low code platform for creating beautiful cu...
Create an AI Product Recommendation Engine For Ecommerce with Flowise | Part 2
มุมมอง 3.1K9 หลายเดือนก่อน
If you've ever wanted to create an Ecommerce Product Recommendation App this video is for you. Having the ability to recommend products to customers based on specific requirements is a great way to help customer make purchases and increase sales. In this video, we'll create a basic Product Recommendation App for a Home Theater Design Company using Flowise and N8N, an automation platfom. We'll a...
Learn the Basics of Prompt Chaining in Flowise | Part 1
มุมมอง 3.3K9 หลายเดือนก่อน
Prompt Chaining is one of the best ways to create advanced AI workflows that can combine multiple tasks so you can create a wide variety of applications and automations. In this video, you'll learn how to chain prompts together to help you complete more complex tasks. In the example we'll design a workflow that effortlessly generates detailed Midjourney prompts for our Character Design, Art and...
Chain Node Mastery Preview - Build Powerful AI Applications in Flowise with Chain Nodes
มุมมอง 7569 หลายเดือนก่อน
Have you ever wanted to learn more about all of Twelve main chain nodes in Flowise and what they do? In this Mini Course We'll cover each of the 12 Chain nodes in Flowise and show you how to use them to create a variety of AI applications. onyxstudiosinteractive.com/chain-node-mastery-mini-course/ Chain nodes are the building blocks of Flowise, a powerful tool for creating conversational AI app...
Creating Custom JavaScript Functions in Flowise | Part 1
มุมมอง 3.7K11 หลายเดือนก่อน
In this video, learn about all the recent updates to Flowise including support for Pinecone Serverless, MMR Search and Custom JavaScript Functions. Custom JavaScript functions allow you to create powerful chatflows without having to do any OpenAI function calling. Your JavaScript can run independently and anywhere in your flow. In part 2 of this video, we'll take a look at the brand new LlamaIn...
Learn How to Use LlamaIndex with Langchain in Flowise | LlamaIndex vs Langchain Part 2
มุมมอง 7K11 หลายเดือนก่อน
Learn How to Use LlamaIndex with Langchain in Flowise | LlamaIndex vs Langchain Part 2
Manage LLM Vector Databases and Long Term Memory in Flowise | AI Vector Tools Review | Part 2
มุมมอง 1.5K11 หลายเดือนก่อน
Manage LLM Vector Databases and Long Term Memory in Flowise | AI Vector Tools Review | Part 2
Manage LLM Vector Databases and Long Term Memory in Flowise | AI Vector Tools Review | Part 1
มุมมอง 1.9K11 หลายเดือนก่อน
Manage LLM Vector Databases and Long Term Memory in Flowise | AI Vector Tools Review | Part 1
Mixtral 8x7B vs GPT 3.5 Turbo - Mixture of Expert Model Challenges OpenAI GPT 3.5 (Testing & Review)
มุมมอง 743ปีที่แล้ว
Mixtral 8x7B vs GPT 3.5 Turbo - Mixture of Expert Model Challenges OpenAI GPT 3.5 (Testing & Review)
Mistral Medium VS OpenAI GPT-4 Showdown + Flowise Deployment (Part 2)
มุมมอง 1.1Kปีที่แล้ว
Mistral Medium VS OpenAI GPT-4 Showdown Flowise Deployment (Part 2)
Create a Flowise Assistant with Custom Tools and APIs | AI Automation Tutorial | Part 2
มุมมอง 2.4Kปีที่แล้ว
Create a Flowise Assistant with Custom Tools and APIs | AI Automation Tutorial | Part 2
Create a Flowise Assistant with Custom Tools and APIs | AI Automation Tutorial | Part 1
มุมมอง 10Kปีที่แล้ว
Create a Flowise Assistant with Custom Tools and APIs | AI Automation Tutorial | Part 1
Shouldn't you be using State and then conditionals to pass the info to the approriate agent? Would help with hallucinations and getting responses from agents even when you dont need them.
This is pretty cool. One question: why didn’t you build the entire project using n8n alone? What value does Flowise bring for the main agent orchestration versus n8n?
That's a good question. Both Flowise and N8N each have their own unique strengths. When it comes to designing AI workflows, Flowise has more AI focused tools as well as a better chat interface. As far as agent orchestration, Flowise also has more options than N8N since it's built from the ground up for AI. For this build though you could also do it in N8N since it's pretty straightforward. I just tend to use Flowise though for designing AI Agentflows because its interface is more intuitive in the same way that N8N's interface is more intuitive when creating automations. They work pretty well together as a team.
@ That’s interesting and thanks for the speedy reply. I recently created a Competitor Analysis tool using a n8n workflow where I used a Flowise workflow as a tool for a LLM tasked with research. The Flowise workflow contained an agentic rag flow using the LlamaIndex nodes to interact with 15 company knowledge bases while the n8n workflow took care of constructing the final reports. Dead easy to setup and super satisfying to see it working.
Great and valuable content!
Good video as usual. Is it possible to use these vision models to extract information from passports image or financial statement images? If yes, we need a video for that.
You could extract data from any identification as long the text is visible. It's pretty similar to the part in the video where I extracted data from an image of a table of survey data. You would just need to adjust your prompt and if necessary use structured JSON outputs.
@OnyxStudiosInteractive Most of LLMs are sensored and personal information in any Identification images are not alloweded to be extracted.
@ I can understand that, they don't want their models to be used to collect sensitive and personal data without user permission.
Incredible changes! Love it😎😎
I wish I could purchase this course 😂
hi. can we use custom JS functions after using an agent? If an agent gives a response, i want to use that and write some JS code and that output to be passed to the next agent?
@@AneeshaRao100 Sure you can do that with an LLM chain. Just connect the output of the LLM Chain module to the input variable of the Custom JS Function module. Alternatively you can also use an agent like the tool agent....you just connect two different Custom JS Functions..one calls the tool agent via API and then passes the output to another Custom JS Function node.
Any reason why you are using N8B and FlowWise? why not just use N8N?
Hey Thomas, I absolutely love your content! It’s so great to see another FW video from you. Your style and the way you explain everything in such detail is just amazing. Thank you so much for putting in all the effort to create this-it’s truly appreciated!
Thanks for sharing this. As a no coder, I am trying to find an effective way to implement such a RAG within n8n without much coding. As my app backend is on Xano, their somewhat recently released Ai capabilities seems good. They can allow you search and rank results pulled from the DB. What’s also great is that you can create row-level triggers to create an embedding for any fields you want. I am still experimenting but I am trying to find a way to use Xano as a vector database but it is not an available integration. I was wondering if you have experiences using an API within n8n to retrieve embeddings for an agent or using the workflow retrieval to something like this?
That cool to hear about Xano...there are so many new tools being developed right now and integrated with existing plaforms. There's a lot of options for vector databases that are pretty solid and easy to implement into your application. You can even use the Flowise API to embed documents programmatically into a vector store. As far as using API's in N8N, you can use nodes like the HTTP node in N8N to retreive data using a HTTP Curl request. That's what I did for the Brave Search API in the video. You just need to have the right parameters for the API request. If you'd like to talk more about you project let me know and we can schedule a call.
@@OnyxStudiosInteractiveThanks a lot! I am testing a few things as I build the n8n flow and ingestion flow. Your video already gave me some ideas to test 👍🏻 But will surely come back if I am stuck. Thank you!
Thanks. This is useful, but it should say Flowize in the title, not n8n 👍🏻 I am exploring options to do the same within n8n as well.
Thanks a lot. Your right, Part 1 is more about Flowise and an intro to the N8N tutorial in Part 2. Let me know if you have any questions. Once you get the ranking workflow up it becomes possible to go beyond and even add features not found in the Langchain and enterprise rerankers.
Thanks Thomas, this is a really useful video. Is there a reason why you are using SQL rather than json for the database/product list?
I'm glad you enjoyed the video. We're using SQL because we need a database to store and retrieve the product information. JSON is simply a data format. SQL also gives us an easy way to query the database using AI and automation.
@@OnyxStudiosInteractive Thank you Thomas for the clarification!
Could you please share that javascript code with functions as i am getting some issue in accessing function through prompt template.
Hey Thomas, just a quick thank you note for your n8n videos on TH-cam. We appreciate it!
how can you do prompt chaining and vector reading? I cant find a way to have both
I'm confused, where does the Agent come in? This looks like the normal SQL Prompt template from the market place with some nice backend automation but not an agent flow...
This is essentially a single agent flow. In this case the agent uses a variety of tools and training to turn your request into an SQL query and then filter the results to recommend products based on what you're looking for. That's why it's an agentflow. It's not a multi-agent or a sequential agentflow where multiple agents are working together. You could do that but it would be more complicated and potentially take longer. As far as the SQL Prompt template, I used it as a starting point but the template is intended to be more of a concept. It is not plug and play and takes a lot of work and customization for a specific use case.
@OnyxStudiosInteractive Great video However, one could argue this is a simple RAG system as well. Converting the query into embedding, converting products or their descriptions into embeddings and saving them in a database. Perform a similarity search between the query embedding and the products embeddings, extract most relevant products and recommend them to the client. There is no thinking in this flow, thus no need for an agent.
@@dantshisungu395 I've tried that before and it doesn't scale very well. The issue is that large ecom product databases are constantly changing with inventory updates and you can't really rely on simple embeddings and similarity search when you have potentially thousands of products. It's much more reliable to search the database first and then choose from the products that are currently available.
@OnyxStudiosInteractive Thanks a lot for the feedback, I will try to implement it and see how it works. However, note that it is not a matter of quantity here, rather how to effectively embed products' descriptions into the right multidimensional space. Maybe trying out different embedding models and see which one performs better
@@dantshisungu395 Sure thing let me know how it works for you. You could also try graph vector databases like neo4j as well however the real challenge is always going to be updating your embeddings and syncing it with your entire product inventory database. That's why SQL query language is so powerful.
👍Download/Clone This AgentFlow: onyxstudiosinteractive.com/ecom-agents-download 👍Get Our New Training - Flowise Core Essentials: onyxstudiosinteractive.com/flowise-core-essentials
👍Download/Clone This AgentFlow: onyxstudiosinteractive.com/ecom-agents-download 👍Get Our New Training - Flowise Core Essentials: onyxstudiosinteractive.com/flowise-core-essentials
Thanks Thomas. Really a good video. I have shared your video to my team here in Dubai. We would appreciate if you show us simple and complex examples of how to leverage flowise with Zapier
Great content! I built a flow that's basically Supabase -> OpenAI LLM, and you upsert a PDF/Word doc with tables, charts, etc, and I'd say the responses are 70-80% correct. Would LlamaIndex be more suitable for this? Would it yield better results? Response accuracy is very important in my application, as I use it for analyzing court cases, sales reports, and such. Thanks, keep up the good work.
Part 1 link, please.
Hey nice..where’s the details on connecting to FW in flutterflow?…can’t see it anywhere
hi thomas, is flowise is still free and has the same function even if you dont use the cloud version?
@@healthadvice3091 That's right Flowise is Open source and you can deploy on your own computer, server or a service like Railway. Although the cloud version has a few additional features like storage and database backup that you have to provide yourself in the self hosted option.
@@OnyxStudiosInteractive wow i like it as i am from 3rd world country (im a broke tech guy) i just need to find a cheaper alternative hosting
I have clients looking for tutorials on Flowise. Do you have an affiliate program, or could I run through before I recommend it.
Hi there, that sounds interesting...We may be able to setup a referral program for you. Send me your email and we can discuss it.
👍Download/Clone This AgentFlow: onyxstudiosinteractive.com/flight-booking-agent-download 👍Get Our New Training - Flowise Core Essentials: onyxstudiosinteractive.com/flowise-core-essentials
👍Download/Clone This AgentFlow: onyxstudiosinteractive.com/flight-booking-agent-download 👍Get Our New Training - Flowise Core Essentials: onyxstudiosinteractive.com/flowise-core-essentials
Thank you so much...
You're welcome. Sequential agents are pretty awesome.
Hi. When was the course produced and released?
Hi Bill. Thanks for your interest. The course is brand new. We produced and released it in August so it's current with the latest version of Flowise. However it will also be updated as new features and versions of Flowise are introduced.
@@OnyxStudiosInteractive Great so it was produced using v2? Do the sample projects in the course include multi or sequential agents or doesn't it go that deep? Thanks.
@@Bill-ai That's right, it was produced with Flowise version 2. There's actually a project in the course that includes an AgentFlows team along with an N8N integration for downloading TH-cam transcripts and web search to research and create different types of content. I wanted to keep it easy to follow while also including some of the latest Flowise features from v2.
Sequential agents are disruptive innovators! Remember to look at other AI technologies that can help your projects develop even better. #Innovation #SequentialAgents #AI
You're definitely right about that. It's amazing that we're on the cutting edge of AI development and we haven't even gotten started.😅
fix the orthograph in the formation titles = Ecommerce . Great Video
Thanks for watching!
That looks cool!
Thanks! I'm glad you liked it. haha need to make an animation next time😅
There is a way to send a personalized Session Id, for example from another system I send the id, flowise does not create an id, but I want to do it in Create Sequential Agents
I don't think Agentflows supports custom Session Ids since they're stll pretty new at the moment. You may want to ask in the Discord group.
Hey man, only a few minutes in but it's already a great video. Thank you!
Thank you! I'm glad you enjoyed it!
Agentflows and Sequential Agents are pointless at the moment, the output on the embed is poorly formatted and confusing, there are no options to display the output like its presented inside the test chat in Flowise, with separate agent displays nicely formatted and with avatars in an easy to read output, then when it comes to calling them through API the entire response of the supervisor and workers comes out in one block of text. Neither of which can be used in production or even chatbot embed for a client for instance the output is just too badly formatted.
They are still pretty new and will go through more development over time. What's most exciting is giving them the ability to add a human in the loop input at any point in the agent flow as well as displaying the text output in the frontend chat window. Amazing to think that we're still in the early days of AI development with the best yet to come!😅
@@OnyxStudiosInteractive
Hi Thomas, great video! Thank you! So far the most complex flow Ive seen. Very exciting. Would you be so kind to share the Flow so we can work ourselves on it and experiment a little bit? Thank you!
Thanks! I'm glad you enjoyed it. As far as sharing the code, I'm actually going to be doing more of that and making the workflows available for download since it can really save people time and help them develop their own agentflows. The flow for this Agentflow is now available in the store on my website: onyxstudiosinteractive.com/flight-booking-agent-download
When do the tools start working and how?
Amazing tutorial.. Can I use my custom API to send those data to instead of using Zapier or n8n?
Very much needed video. Flowise and flutterflow is a great combination and much needed. request you to make a video of flowise openai assistant streaming on flutterflow front end pls
Hey could you please share the final JS functions with us? I am having issues returning the JS function output in chat when using as ending node.
Love the tutorial! Thanks
Great tutorial. Thanks for sharing
Brother, This is awesome series, I learn a lot, can you make a voice note taking app, where people will took notes just using voice command just like iron man movie, when user say a keyword like jarvis voice, App will active and took notes automatically,.
Wow, amazing! Thank you for sharing this with us! One question: do you still Need flowise? Couldn‘t you have it all done in n8n?
You're welcome! That's a great question...you can probably recreate most chatflows in N8N as long as you have Langchain modules. However I think Flowise has a much more intuitive user experience. N8N is primarily an automation tool though so it's more designed to work with Flowise rather than replace it.
This is outstanding, thank you for sharing it.
I'm glad you enjoyed it!
Hi Thomas, Thanks for your great topics and videos about flowise and how to use it with the business. Is it possible to share flows that you use in your video so we can use it as a guidance? I have an account in N8N also and need to try your great demos. thanks in advance
I am still waiting your reply. just say yes or no.
Hey Thanks! I'm glad you enjoyed the videos! While there are some things I'm unfortunately not able to share, I am working on a membership site where I'll be able to share some of the flows and assets from the episodes. Hopefully it will be finished this month.
I was wondering how to setup an agent that supported a vector database + memory + custom tools. Thank you very much
To do that you should use the tool agent combined with the retriever tool in Flowsie
@@OnyxStudiosInteractive thanks, I'll try that today.
Hi Thomas - thank you for this video. I’m not a coder but I’ve tinkered and can follow your JAVA script. Where can I find the rest of the code? You showed one node but again, for someone like me, I would need all three example nodes to make it work. If you don’t want to post it, can I reach out some other way? Thanks!!
It took me a while to find it. Send me your email and I'll send it to you. It's pretty straightforward, the first node just takes the question and sends it to other chatflows. Something like this is actually easier to implement with an automation tool with N8N. Although the latest update to Flowise does have the ability to call existing chatflows. I haven't tried it yet however it might be something to check out.
How to buy course , I want to buy using paypal , there is no option over there
I can see the channel video is good and the content quality is good. Your TH-cam channel subscribers are enough. Compared to that you not getting subscribers and video views. Your video views are very low. Could you please permit me? I would like to share some tips with you, which will give you very effective results in growing your channel. you get lots of subscribers and views. Thank you.