Відео

Either there is something wrong with Gemini 2.0 or how n8n uses Tools. Almost everytime I have issues where the LLM does not call tools in n8n. Whereas when I use the same LLMs in LangChain and LangGraph, they work seamlessly. I tried a github repo in Live Agent Studio of the n8n GitHUb assistant. It was able to get the repo structure. But when I asked it about the contents of a particular file, it did not call the tool, rather it made up the answer. The question I asked was "What are the contents of the file resume_analyzer.py". I literally mentioned the file name and still it did not trigger the tool I tried the Pydantic GitHub Assistant and it worked well. It was able to call the tool when asked the same question and did not make up the answer

It is one of the best builds out there! Amazing!

Problem loading credential Credentials could not be decrypted. The likely reason is that a different "encryptionKey" was used to encrypt the data.

Im stuck with no API key generated from qdrant=/~feeling failed=(

future upgrade ideas have niinx-proxy-manager & comfyui install with the kit :)

is there a way to upgrade from original starter kit to yours?

Awesome video. New to n8n. Can you share your video where you talk about setting up supabase and postgres. Getting an error here. Thanks!

Awesome. This video and your upcoming series are what I’m looking for. Among all of the people posting videos about building AI agents, I found your videos are the best: simple enough for non tech people to understand, also have in-depth technical details. Can’t wait to see your new videos.

you are amazing. thank you thank you

Thank you so much Cole, always ❤. Can I suggest that you put the series into a playlist? It can be quite confusing to pickout the particular videos and in their order. I understand the 1st ever video is not a post-prod video but a stream, took me a while to figure that out.

Does live agent studio accept file uploads? Like my agent accepts a pdf file. How do I do that with live agent studio

Recently, I learned about MCP (model context protocol) from Claude and it makes me a bit confused about what is the most up-to-date way to implement tool call in AI agents. Because even before MCP was introduced, AI agents already be able to call 3rd party API or do many interesting things outside of the LLM. So from now on, when developing a new AI agent, should we use MCP or not? Thanks a lot

Awesome video! I’m curious if you ever do consulting for businesses. I’m currently working on a startup and I plan on using this technique but I’d love to pay a consultant who actually knows what they’re doing to make sure it’s set up properly from the get go. If you don’t take on new clients I’d also be interested in anyone you might recommend!

Perfect Video, really really good Job ;-) Only Question from me, it is locally except Google Docs, can we do this also with local files? I have tried it, but did not succed. That would be perfect for private data....

Your channel is extremely helpful in the new AI race, I am surprised not many subs are here. LLMs are at least as large as bitcoins but not many people have caught on the craze, not at least in the AI producer space yet.

alot of info in a quick pace! I like it and am subscribing. WebUI is awesome, so the n8n aspect will be cool to learn. love your intensity. looking for more.

Hi Cole. Is there a way to play audio responses or show AI generated images on the Live Agent Studio? Also, could you give some general ideas on what type of problems the Live Agent Studio interface can solve for its users? Asking to help come up with ideas for the hackathon 😅

Two questions: Does it have the ability to ai generate images? Also, is it possible to use in a Java Program?

What is the default api used in bolt.new like Google, anthropic, open ai.

bro go touch grass

Are the tokens are limited?

great guide! One issue I am having is my docs keep coming out in unicode on my rag upload. My extract text method keeps yieleding unicode... [Problem in node ‘Insert into Supabase Vectorstore‘ Error inserting: unsupported Unicode escape sequence 400 Bad Request] I can see my data from the extraction is all corrupt, tried a few documents, any ideas? Fixed my first issue with txt file. How do I make sure PDFs and DOCX get parsed correctly? Seems to be an encoding issue. Also any suggestions to deal with a large volume of docs needed to add to the vector store? If I try to drop a few files into drive it breaks obviously. How can I look through these items and process them in batch?

amazing, thanks, just what I was looking for

You are the best, Cole. It's like you read my mind and made my dream come true. Thanks a lot. Please keep posting.

My god man you are a full time job just to keep up ... keep going .. love the material and the examples.

Hey bro, I recall you previously mentioned that Flowise isn't recommended for production due to limitations in logging, monitoring, and error handling, making it better suited for rapid prototyping. However, Flowise offers integration with several analytics tools - like LangSmith and others. Which solves the issue you raised right ? . I'm torn between your expert opinion and Flowise's capabilities. Can you help me out, bro?

Simply Amazing Brother, Thank you sooo much! And of course, it will be great to see more content related to RAG implementations using this setup.

Could you create a video on how to containerize an AI Agent via Docker in an API with n8n?

ua-cam.com/video/cHDCCSr1YRI/v-deo.html

hi, just downloaded this workflow and replaced openai with anthropic plugin and it doesnt work. Is there some specific setup to use different model tha openAI?

Love your work, passion, and perspective. Curious about your video production process and workflow.

I saw your comment saying flowise is not production ready but are you sure the new verison of flowise is super updated . And also i got an idea for you that will be gane changing, why dont you develope a no code open source platform like flowise but for pydantic AI😍 i beleive only you can do that ❤u have that passion bro. Isnt this crazy good idea ?

Yo boss can you make n example a customer support rag chatbot with pydantic AI framework in this series or like tell us how to customize github pydantic ai agent code you created to a customer support rag agent what all codes to change in it atleast.

Hey Cole, I recently asked you the question about local setups and getting a MacBook with how much RAM, I wanna know your thoughts on the NVDIA DIGITS, you think it’s worth it?

Hey man is it possible to create a ai agent that can help me with daily private task like wich groserys to buys if my energy contracts ends it seeks new alteratives etc. To save time money?

U of M ❤ I didn't go there, I live down the street though!

hello, my "insert into Supabase Vectorstore" step is not working. Could someone help me please?

i cannot use openai api key somehow i get a error

I like his videos about n8n, but this here is chaos to me. Building agents was so easy, but here he starts to make it difficult. His road map threatened this already. No code now seems to be way more difficult than coding. :-)

There is a problem in VITE while previewing please solve it

I'm using Intel i3 - 6th gen along with windows 10 pro

A normal URL never includes a 'backslash'. Ever.

Your naming is terrible! I thought you were going to hook it onto the actual agent zero 😕 you need to really start coming up with your own unique names instead of ripping off other names

Thank you once agian👏

Did you also consider just doing a post to the qdrant API /collections/imdb/points/delete with the filter in the body, would be a lot more simple.

why do i not see any agents when i visit the ottomator studio? "No Agents Found"

Might want to add smolagents to the blueprint..

Agent 0? That name is already taken by @agentzero 😅

Ou wow using Prezi! How do you like it? :D

Pure gold! 🤘