Welcome to my tech and software engineering channel where I'll be sharing tutorials and projects across a range of technologies including: Python, JavaScript, Web Development, Unity, Game Development and more.
Learn to code with me by building projects big and small!
Пікірлер
So sad that you didn't mention that AWS need to be installed on the machine. The snippet below is giving me this error message: "Could not load credentials to authenticate with AWS client." I had to do a lot of research to find out that AWS CLI need to be installed. I will try your other tutorial. hope it will work. embeddings = BedrockEmbeddings( credentials_profile_name="default", region_name="us-east-1" )
Does this work if we use json files as input data (instead of PDFs, markdown files, etc.) ?
Bah all of these libs... It just depends on ppl...type mastrubation😂😂😂
Great work
Great video! Love the way you simplified the concept. Are you thinking of making videos on the topics fine-tuning, function-calling, Agents? If so, that would be a great series of videos. I am sure all your subscribers including me would greatly benefit from them. Meanwhile, can you share any resources on these topics? (fine-tuning, function-calling, Agents)
Amazing tutorial. Thankyou!
@pixelgami this does not work anymore
I get a Connection refused error when I run populate_database.py. Any pointers on what may be wrong and how to fix?
Verry cool but do you know the limit to pdf’s you can upload. The limit seems s bit low unfortinately. I just tried creating a Plug in but this is the same right?
whenever i include the function it doesnt work
nevermind i forgot the quotation marks
Thanks for this great Video, but chroma has been deprecated... :(, maybe a new video? :)
What version of python, pip and the libraries are you using. on you first RAG video i had issues with version. i had to play around with it. Thanks
Valeu!
This is awesome information. I have a script I'm looking do download on a Windows system and a Linux system. Are you able to run this packages on a CronJob for Linux and task scheduler for Windows Machines?
Thank you
Great video, really helpful. Please can you create a video that covers the other 3 features you suggested i.e. adding a Web UI (e.g. React & Next.js), Authentication (e.g. Clerk) and Payments (e.g. Stripe). Thanks.
I just subbed, amazing video and it was great to get a quick refresh with! thank you! also, you should make a paid course like leetcode has done. you are one of the best teachers on the platform.
Best video! Thank you!
I hate the way you voice sound at the end of each sentence Great video thought
The code doesnt work when you try to save more than 99 chunks / embeddings. Any idea what the problem is and how to resolve it?
Thanks for sharing this! I've used whisper and LLMs for similar applications (e.g. automating game dialogue captions and localization). Automating video editing is no small task - but one I've been considering doing. I'm lucky to have found your video! I appreciate you sharing. Going to save me a lot of time.
hey, it says that there is not module named discord. can you help?
nevermind i got it working
finally got it to work, had to pull nomic-embed-text as well and update the langchain imports to langchain_community since I got errors when using langchain, it was deprecated.
Hi I am unable to retrieve the data from chroma db i am getting saved this much chunks in the database message in my create database code but still when i am accessing the same in query_data.py i am not able to get the data its showing unable to find the match and the result is empty
Thanks for your video, really good. One question: What are your resource? are running with gpus? I test your apps on vps on AWS with 4 vcpus 16 gb of memory running ollama3 but it is too slow.. .
This is an absolutely fantastic tutorial. Thanks for this!
We need a Langrapgh Project please
Great tutorial ! I see you have good knowledge about AWS. Just curious what are the most benefits of choosing AWS for serverless backend instead of Vercel? Vercel seems way easier to configure and it uses by default serverless functions for API routes handling. Any particular reason for not using it for the backend, as it seems you're using for the frontend ? Also, would you want to do a video about using Figma to code and bootstrap a NextJs/React UI ?
Awesome! You just got a new follower
Great tuturial, well explained!!!
Hi, thank you for video and info. This video one of the best videos about AI, ML, Rag. Your video was so helpful) thank you again)
retrieval is not showing on my screen...what do I need to do?
I love your videos and wanted to know which software do you use for representing your architecture diagrams, they look wonderful?
I love your videos and wanted to know which software do you use for representing your architecture diagrams, they look wonderful?
w/ graphrag?
Amazing video!
awesome customization
Error: Could not load credentials to authenticate with AWS client. Please check that credentials in the specified profile name are valid. Bedrock error: The config profile (default) could not be found (type=value_error)
I did a code that read a unique CVS file with abstracts and title information from scientific papers (800), so I received the RAG with LLMs advice to read them and receive a feedback. The code return me the title based on a query that I give, however, some of this title has almost zero, if not zero relationship with my query, so I think that something is wrong. Your video is a good way to come back and see what can I change in my code, however, it is possible to have your feedback about my code? Please, that will be really helpful
This is the best practical tutorial came across llms, RAG, langchain. Also can you make one about agents and their use
where could i get the link precedente of video
I don't get the handler part and how it applied to the long ass code I have uploaded there
What happens in the database if the info on the pdf was wrong? Is it easy to correct? Is it easy to delete the wrong info and populate with the new one?
This is a great video and I love all your tutorials. You should call out which models you are using. It took me a long time to figure out which model was used for the embeddings since you did not pass the Model ID as a parameter there.
I'm was a Business Intelligence for a 2.4 BILLION entity. worked there 9 years. Also worked in a top 3% global qs University in Business Intelligence Analytics and Data Science. Been outta the game for 2 years - wanted a break. Bro, shits changed so much in 2 years. I'm going to nuke digital. If you knew who I was and took the time to reference check me, the industry would freak. Look at my handle.MULTIDIMENSIONAL. I am going to create systems to automate everything through AI Agents. And I'm going to give them away for free to large entities. Collapse white collar. I am an expert in TSQL, PL/SQL, DAX, SSIS, SSRS, PowerBI, MULTIDIMENSIONAL CUBES. LLM's are new to me. Give me 2 years and I'll be on the news as the guy who was responsible for automating everything. Edit: It's my life mission. I'm going to automate everything. WYSIWYG Agents that are flawless and can be integrated to an organizations local or dedicated servers. Everything from phone switch Realtime voice analytics for AI Agents to handle phone calls through to raw data aggregation and analysis, system administration. Managing routing, switches. National Power Grid Electricity Distribution and load regulation, spot pricing, law, accountancy, medical. Just everything imaginable. Trust me. it will happen. And I will run it all and have the globe by the nuts. Then I am going to redistribute wealth to the people arahahahahahahahahahaha. Get all these greedy corporations on my platform "Open Source", then charge them through the teeth and hold governments at ransom to institute universal incomes that are equitable. I swear my life, I took over a 2.4 BILLION $NZD ELECTRICITY GENERATION AND RETIAL COMPANIES MOST BUSINESS CRITICAL DATA SET FOR FUN. HAD THEM BY THE CURLIES FOR 6 OUTTA 9 YEARS. They didn't fuck with people while I was there. POWER TO THE PEOPLE!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
I wants to check my resume pdf if I made any spelling mistakes
WHAT IF WE DINDT MADE ANY PREDEFINED RULES?
Great video thanks :)
Hello! Mighty pleased and thank you very much!
i use any llm it says max token limit reached, why is that ? is it paid or something?