Видео

You could try to say improve the ux or from the start "make sure to follow the best practices of ux"

Great video and explanations. Do you know whether there is a limit to the number or size of documents you can import into the database? Do they need to be certain formats or can you use PDFs and Word docs?

How you managed to install it so easily? You didn't even install search engine (searsng) and you still manages to search info... I tried to install in on windows using models from ollama and it didn't work. I even tried to install image of searsng and connect to it and it still didn't work. Has anyone managed to successfully install and run it on windows 10 using docker? Upd. I managed to install it on Windows 10! There was a problem with searsng (solved after build and rebuild several times) and conflicts with open-webui (which also work on 3000 port) and also there was problems with browser cache.

You are probably the first channel to cover this tool. Let’s see how this tool survives in a market where Cursor, Windsurf and Trae are out with a head start

I tried this, but Anything says 404 Failed to load model "nomic-ai/nomic-embed-text-v1.5-GGUF". Error: Model is not llm.

is it possible to use claude 3.5 sonet v2 in with GCP vertex ai? can you make video on this?

Great one , seriously a proper human teaching us ai😅, subbed

Thanks for the content. I'm looking forward to more.

I'm having this issue no video so far explains this Shell Integration Unavailable Roo won't be able to view the command's output. Please update VSCode (CMD/CTRL + Shift + P → "Update") and make sure you're using a supported shell: zsh, bash, fish, or PowerShell (CMD/CTRL + Shift + P → "Terminal: Select Default Profile")

Thanks. Could you also do something very similar to open in Cline or Roo-Code? Feel free to ask "But why would you want to do that?" and elaborate.

So the way this works is: AnythingLLM does the API query to vector database which has your files and pipes it through LLama server ? Let me know if I stated it right 😂

How can you check the model performance in the anything llm gui ? Like tokens per second I know LMStudio interface has it

How can you check the model performance in the anything llm gui ? Like tokens per second I know LMStudio interface has it but anything did not

Thanks for such a great video, Can I use this method to read construction documents (pdf) and have it answer questions about the content relevant to specific trades? I understand it can't read Autocad construction drawings but can it do take-offs? (enumerate quantities across multiple drawings labeled with text). Can it count or do addition? Can I load multiple files? What are my limitations; total token count of the docs (4096) or is that the question-response size limit? Or must total size of doc loaded be no greater than some certain amount? Which LLMs are best for reading docs; Vision models, Coding models, Math models, or Instruct models? Why can't LLM studio handle this on its own? If it CAN do all of this how much longer before I'm forced into retirement? Got any more vids about this?

OK, Windsurf may be good for Mickey Mouse apps. But when you try some more experienced multi platform apps with cloud kit and core data this app produces more and more spaghetti code and lost complete the overview. it produces code that left behind all rules of good software development and experience of the last 30 years.

Do you know how to install everything into a docker's container?

wizard coding

currently using lovable. then opening roo-cline and optimising. working well

hey what happen if i trun off the server .can you explain how close these safely and restart

Thx! very useful for personal projects with very specific information. Amazing video, great work

Wow the sandbox auto testing is insane, is this only applicable to Claude models?

how can I transfer my project from .new to .diy? can you help me?

WHY DOES THAT ERROR OCCUR ON ANDROID STUDIO? :(

I hope Roo and Cline continue to push each other for our benefit :)

I keep getting API Request failed message: 429 {"type":"error","error":{"type":"rate_limit_error","message":"This request would exceed your organization’s rate limit of 40,000 input tokens per minute Whenever I tried to use Cline. I tried to sign up for Claude for personal use but apparently I have to contact sales in order to remove this quota restriction? Could there be other ways to solve this issue that I am not aware of?

hi and thanks for the info, quick question why using llm studio while you can run ollama and anythingllm?

pnpm not working will npm install work ?

im a newbie in andriod dev ; can you give me a proper road map with kotlin , please ; btw awesome content🍉❤‍🔥

More such videos please!!

Thx great video, very clear it worked perfect.

I added a comment earlier but it's vanished - I want to thank you for posting such a clear and informative video. I do have a question: Can you tell us how much space is taken up with Bolt.DIY and how much memory is needed to run it (I have 16GB)? I did also suggest you might consider a video on how to deploy your project onto your own web hosting provider. I spent days trying to learn git and github and got into a real mess! I finally figured it out but it wasn't simple and you'd probably be much better at explaining it than I could. Anyway, thanks again for posting. With best wishes, Rob

Nice tutorial BUT I have done it on 2 systems and my webpage is all white not black. Any suggestions would be appreciated

very detailed tutorial

Great video, thanks for sharing the info. Jay

I'm generally curious about what your actual Android development experience is. I chuckled through this entire video. lol

Do you believe that with this method I can ask Claude (cline) to help me finish my website, and "him" to save the files?

the user had removed the fork

Is anyone having issues with Anything LLM? I enter the LM studio base URL and max tokens. However, under LM Studio Mode. it says "Loading available models" I am running the server on LM studio. but the models do not load on Anything LLM. Thanks!

Ifollowed all the steps but at the end when I try pnpm preview I get ELIFECYCLE command failed with exit code 1. when I try to run it, I get the page but its not working

te felicito amigo... muy buen video

Thanks ❤

No eye straining editing no talking so fast that you don't understand what he's saying, explaining everything too, man you have a new subscriber+ try write more professional script❤

Try idogram for ai thumbnails its will be more butter than this style in thumbnails because its not the Best + thanks you for you video and idea its really helpful❤

Not working for me I got: There was an error processing your request: An error occurred.

Android app next please. First to comment

Great teaching style. Please also share more tutorials on model finetuning and agents.

Please slow down and be deliberate because people are following your footsteps................

You could make some money on the side doing voice over as Bob Odenkirk, aka Saul Goodman.

What mac do you use ?

I am planning on building an ovulation and period tracking app for Android using windsurf ai.