Тёмный

Build Multi-Agent AI Teams with RAG & Custom Tools! (No-Code) | FlowiseAI 

Leon van Zyl
Подписаться 19 тыс.
Просмотров 5 тыс.
50% 1

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/EK...
📑 Useful Links:
Make.com: www.make.com/en/register?pc=l...
💬 Chat with Like-Minded Individuals on Discord:
/ discord
🧠 I can build your chatbots for you!
www.cognaitiv.ai
🕒 TIMESTAMPS:
00:00 - Intro
02:16 - Creating the Agent Team
04:55 - Writing Worker Prompts (Pro Tip)
08:22 - Adding Vector Retrieval Tool (RAG)
11:34 - Improving Team Behavior
13:00 - Custom Tool (Email Sender)
15:13 - Make.com
18:29 - Setting up Gmail Connection
22:29 - Testing our Team
-----------------------------------------------
🧑‍💻 Custom Tool Code Snippet:
-----------------------------------------------
const fetch = require('node-fetch');
const url = '';
const options = {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({
message: $message
})
};
try {
const response = await fetch(url, options);
const data = await response.json();
return data.message;
} catch (error) {
console.error(error);
return '';
}

Наука

Опубликовано:

 

30 июн 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 101   
@ZAR3RX
@ZAR3RX 3 дня назад
Lekker dat ek jou kanaal ontdek het. Goeie materiaal, netjies uiteengesit, aangenaam om te leer. Sien uit na jou volgende aflewering!
@leonvanzyl
@leonvanzyl 3 дня назад
Dankie Drikus!
@WayneBruton
@WayneBruton 2 дня назад
Awesome video Leon. That prompt engineering was particularly nice, that is a weakness of mine.
@dimosroumpalas4693
@dimosroumpalas4693 6 дней назад
Can you make a video where you connect to a MySql DB and ask in natural language questions and retrieve data from the DB?
@zarzawiki
@zarzawiki 4 дня назад
If you could mention how to connect to a SQL Postgres DB I would appreciate it!!
@RoniBliss
@RoniBliss 4 дня назад
OOOOOOOh sheeeet! This changed the game I built a new SAAS using crewAI , which works out 100x easier and more effective than Autogen, but still its code its not so easy to quickly test drive flows / different models, EXTRA tools!!! This is FKN UNREAL! Thank so much for bringing this to the table! You da best, learnt so much from you right at the start with the early Flowise tutorials you put out, I then learnt to make app with bubble, now with a no-code "crewAI" I can make any AI app imaginable! I owe you one Leon!!!
@leonvanzyl
@leonvanzyl 4 дня назад
Awesome feedback!! Thank you 🙏
@RoniBliss
@RoniBliss 14 часов назад
Leon, I have a problem where the flow never ends, it loops through the all the agents then starts again, looping infinitely... Do you have any ideas on that?
@BadBite
@BadBite 6 дней назад
You've truly made my day! Your remarkable effort in putting it all together is appreciated. Thank you!
@leonvanzyl
@leonvanzyl 6 дней назад
You're welcome 🤗
@engelification85
@engelification85 6 дней назад
Just what i needed right now. Good timing :)
@leonvanzyl
@leonvanzyl 6 дней назад
Hehe, you're welcome 🤗
@juliocesarvcardoso
@juliocesarvcardoso 6 дней назад
You solved the problem that I had witk Gmail API and Make before. Thank you very much!
@leonvanzyl
@leonvanzyl 6 дней назад
Haha, glad I could help
@seanyork6220
@seanyork6220 5 дней назад
Awesome video Leon! Love the use of the prompt engineering team! So helpful - My workers are working overtime :D
@kyunglee1924
@kyunglee1924 6 дней назад
video showing calls with n8n would great to keep it all self hosted and open
@leonvanzyl
@leonvanzyl 6 дней назад
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?
@RoniBliss
@RoniBliss 7 часов назад
@@leonvanzyl I use AWS , or Render if I want a quick easy deployment
@texzes
@texzes 4 дня назад
Thank you for what you do. I eagerly await the notification for the new video. May I ask for a hint about the optimal flow? Can data be processed iteratively or in batches using loops in Flowise? For instance, when transferring numerous articles from one DB column, having LLM handle it, and then writing it to another column in the DB, can this be done sequentially in batches?
@Karnadagan
@Karnadagan 2 дня назад
thanks for the video, you are only gem to enlighten us on flowise.
@leonvanzyl
@leonvanzyl 2 дня назад
You're welcome
@ricardofernandez2286
@ricardofernandez2286 День назад
Hi Leon, I hope you are doing great!! I'm glad to see that these new technologies are evolving and enabling solutions for more complex use cases. I will suggest 3 enhancements to the use case you presented that might take it a step further. And of course I kindly ask you to bring some light to the point by sharing your thoughts. So, how would you add: 1. The ability to get the list of target e-mails from a spreadsheet or database. (and/or pass it as a list in the prompt) 2. The ability to hide the process output to the end user (great for us to see what's happening but not very relevant to the end user that only wants the task done 😁) 3. The ability to use an e-mail template to format the e-mail in a very specific (corporate) way. And here I'm thinking about generating e-mails as well as other kinds of documents that might require following a pre-defined format. I hope you find these ideas interesting, and that you are able to bring some suggestions/guidelines to the table on how to achieve them. Thank you very much for your great work!!! Ricardo
@leonvanzyl
@leonvanzyl День назад
Thank you for the suggestions!
@ricardofernandez2286
@ricardofernandez2286 9 часов назад
@@leonvanzyl My pleasure!! Do you believe that any of these can be implemented with the currently existing features in Flowise/Make?
@josealdeavaldeolmillos2105
@josealdeavaldeolmillos2105 6 дней назад
Really useful, as always, Thanks so much, Lyon!!
@leonvanzyl
@leonvanzyl 6 дней назад
You're welcome 🤗
@myandrobox3427
@myandrobox3427 6 дней назад
This is Gold❤ Thank you, Leon!! Excellent as always! ❤👌🙏🥇
@leonvanzyl
@leonvanzyl 6 дней назад
Thank you! 😊
@cgm593
@cgm593 6 дней назад
So useful. Thanks!
@leonvanzyl
@leonvanzyl 6 дней назад
You're welcome 🤗
@docdanoderm
@docdanoderm 6 дней назад
Another great job!
@leonvanzyl
@leonvanzyl 6 дней назад
Thank you 😊
@micbab-vg2mu
@micbab-vg2mu 6 дней назад
great video - thank you for sharing - Claude 3.5 is now available :) - I will try to do some mix diffrent models agents:)
@leonvanzyl
@leonvanzyl 6 дней назад
Sounds awesome!
@juliocesarvcardoso
@juliocesarvcardoso 6 дней назад
Your presentatiom is so perfect that makes me feel really lucky! Very well done, Leon!!! Congratulations!!!
@leonvanzyl
@leonvanzyl 6 дней назад
Wow, thank you!!
@maniecronje
@maniecronje 4 дня назад
Baie dankie! Great content!
@seshasaimudumba2413
@seshasaimudumba2413 3 дня назад
Great to see this video. And I have been going through all your videos and I have created a few chatbots. Can you also make a video on creating Conversational Website chatbot using Web scraper(fire crawl).
@waynenunn7319
@waynenunn7319 5 дней назад
Excellent presentation, thank you.
@leonvanzyl
@leonvanzyl 5 дней назад
Thank YOU
@CreatewwwPl
@CreatewwwPl 5 дней назад
Awsome!
@HA-nh3qd
@HA-nh3qd 5 дней назад
Awesome, you came through!
@leonvanzyl
@leonvanzyl 5 дней назад
You're welcome 😁
@HA-nh3qd
@HA-nh3qd 4 дня назад
@@leonvanzyl btw I am seeing a "Message Stopped" error. Am on Render - any way to solve this?
@HA-nh3qd
@HA-nh3qd 4 дня назад
Am seeing that it's something to do with Docker updates; do we have to update the Docker settings on Render?
@GilbertMizrahi
@GilbertMizrahi 5 дней назад
Great video
@leonvanzyl
@leonvanzyl 5 дней назад
Thank you
@Leonid.Shamis
@Leonid.Shamis 6 дней назад
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?
@leonvanzyl
@leonvanzyl 6 дней назад
I know that conditional edges are coming soon. Will definitely create videos as these features roll out 👍
@jeremybristol4374
@jeremybristol4374 6 дней назад
Thanks for making this! Have you had much success with other models besides ChatGPT?
@leonvanzyl
@leonvanzyl 6 дней назад
Yes, the Anthropic models are brilliant!
@thesvenni
@thesvenni 4 дня назад
Hey Leon, will you be doing a tutorial on how to use exported Chatgpt history to create long term memory flowise bot? Thanks for the great content btw. :)
@leonvanzyl
@leonvanzyl 4 дня назад
I'll see what I can do 🙂
@leongodwin69
@leongodwin69 6 дней назад
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.
@Ghosheh135
@Ghosheh135 5 дней назад
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?
@leonvanzyl
@leonvanzyl 5 дней назад
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?
@Ghosheh135
@Ghosheh135 5 дней назад
​@@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.
@LuisOrtizFX
@LuisOrtizFX 2 дня назад
The "Prompt Engineering Team" isn't in the marketplace. Do I need to add/install it via other means? I'm using the latest version 1.8.3 Other than that, I've been able to follow your tutorials flawlessly. They're succinct and awesome. Thanks Leon!
@leonvanzyl
@leonvanzyl День назад
You know what, I think you might need to follow the "developer setup" to see this. Check out my Getting Started video for instructions.
@celsodeccache6268
@celsodeccache6268 6 дней назад
Great video!!! How can I create a worker that access a database? Thanks a lot!!
@cyberSecurity-qo2gw
@cyberSecurity-qo2gw 2 дня назад
nice video , just wanted to get some demo on paid membership , i mean content topic and business use case studies , can get assistance on tech issues etc?
@10points56
@10points56 6 дней назад
Need more videos on Agents
@leonvanzyl
@leonvanzyl 6 дней назад
Will do
@practical-skills-school
@practical-skills-school 6 дней назад
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?
@leonvanzyl
@leonvanzyl 6 дней назад
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.
@thereal_JMT_
@thereal_JMT_ 6 дней назад
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
@practical-skills-school
@practical-skills-school 6 дней назад
@@leonvanzyl Thank you!
@danielafonso9926
@danielafonso9926 6 дней назад
Thanks a lot !
@The-ism-of-isms
@The-ism-of-isms 6 дней назад
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
@leonvanzyl
@leonvanzyl 6 дней назад
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.
@The-ism-of-isms
@The-ism-of-isms 6 дней назад
@@leonvanzyl Thank you , That sounds perfect. Can't wait for that video 😃👌
@Ragnar-roblok
@Ragnar-roblok День назад
@@leonvanzyl I second it, it would be great to get a transcript emails of the chats sent to the costumer and client.
@simarpreetsingh6604
@simarpreetsingh6604 5 дней назад
Hi Leon. Great video. Can I use azure instead of openai?
@leonvanzyl
@leonvanzyl 5 дней назад
Yes, you can use any model that supports function calling
@RolandoLopezNieto
@RolandoLopezNieto 6 дней назад
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?
@leonvanzyl
@leonvanzyl 6 дней назад
Will do 👍. Not possible to create human in the loop [yet].
@RolandoLopezNieto
@RolandoLopezNieto 6 дней назад
@@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.
@CarlaMoreira-l5r
@CarlaMoreira-l5r 5 дней назад
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
@leonvanzyl
@leonvanzyl 5 дней назад
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.
@CarlaMoreira-l5r
@CarlaMoreira-l5r 4 дня назад
@@leonvanzyl I will do that, thank you 🙏😊
@brylie
@brylie 6 дней назад
How can we keep the human in the loop to review and steer the output of the agents at each step?
@MariushAI
@MariushAI 3 дня назад
Which is the better choice for agent-based workflows - Flowise or VectorShift?
@WayneBruton
@WayneBruton 20 часов назад
Hi Leon, Quick question.When you deploy the multi agent team to a website, it does not show the individual agents at work. Is this by design? When I run the same question in flowise I see the agents working but on a site, I only see the final result.
@leonvanzyl
@leonvanzyl 18 часов назад
Apparently Flowise added the reasoning steps to the Web Embed in the latest release. Haven't tested it myself, but check out this X post. x.com/FlowiseAI/status/1805986577887224124
@WayneBruton
@WayneBruton 16 часов назад
@@leonvanzyl Thanks
@WayneBruton
@WayneBruton 16 часов назад
No, it does not seem to display the steps at all.. perhaps a bug they working on
@leonvanzyl
@leonvanzyl 15 часов назад
@@WayneBruton yeah, could very well be a bug. Just tested myself and I also don't see the reasoning. Will log a message with them.
@KratomSyndicate
@KratomSyndicate 6 дней назад
i wish like comfy ui you can just drop a file into empty canvas and it populates all these nodes
@leonvanzyl
@leonvanzyl 6 дней назад
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.
@KratomSyndicate
@KratomSyndicate 6 дней назад
@@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
@marksmith8056
@marksmith8056 6 дней назад
@Leon Van Zyl, how do I get in touch, sent email via website, and discord is dead?
@leonvanzyl
@leonvanzyl 6 дней назад
I'll see if I can find your mail. Inbox is quite busy 😜
@marksmith8056
@marksmith8056 5 дней назад
@@leonvanzyl appreciate it
@amrpyt
@amrpyt 6 дней назад
Flowise or langgraph or crewai ?
@toi500
@toi500 5 дней назад
Agentflow is LangGraph
@alfideklerk8790
@alfideklerk8790 4 дня назад
Ek sal graag kontak met jou wou maak Leon!
@leonvanzyl
@leonvanzyl 4 дня назад
My email is in die about section van channel, asook n link na my agentskap in description.
@AiLevate
@AiLevate 5 дней назад
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...
@AiLevate
@AiLevate 5 дней назад
first of all thanks for the amazing content :*
@leonvanzyl
@leonvanzyl 5 дней назад
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.
@AiLevate
@AiLevate 5 дней назад
@@leonvanzyl yep spacing.... no spacing in the title 🙈 thaaaaaaaanks
Далее
How ChatGPT Built My App in Minutes 🤯
8:28
Просмотров 2 млн
How the hell is this done#joker #shorts
00:14
Просмотров 2,4 млн
Claude 3.5 Sonnet vs GPT-4o: Side-by-Side Tests
25:10
YOTAPHONE 2 - СПУСТЯ 10 ЛЕТ
15:13
Просмотров 123 тыс.
Main filter..
0:15
Просмотров 12 млн