Complete Tutorial on Vector Database - Learn ChromaDB, Pinecone & Weaviate | Generative AI

Code: github.com/entbappy/Complete-...
Welcome to this comprehensive tutorial on Vector Databases! In this video, we dive deep into three powerful vector database solutions: ChromaDB, Pinecone, and Weaviate. Whether you're a beginner or an experienced developer, this tutorial will provide you with valuable insights and hands-on guidance.
Check out my other playlists:
► Complete Python Programming: • Complete Python Progra...
► 100 Days of Machine Learning playlist: • 100 Days Of Machine Le...
► Statistics For Machine Learning: • Statistics For Machine...
► Object Detection Using YOLO v6: • YOLO v6 | Object Detec...
► Object Detection Using YOLO v7: • YOLO v7 | Object Detec...
► Sign Language Detection Using YOLO v5: • Sign Language Detectio...
►ONNX (Open Neural Network Exchange): • ONNX (Open Neural Netw...
😀Please donate if you want to support the channel through Buy me a coffee: www.buymeacoffee.com/dswithbappy
This channel focuses on providing content on Data Science, Artificial Intelligence, Machine Learning, Deep Learning, Computer Vision, Natural language processing, Python programming, etc. in Bangla and English.
My mission is to provide inspiration, motivation & good quality education to students for learning and human development, and to become an expert in Artificial Intelligence, Machine Learning, Deep Learning, Computer Vision, Natural language processing, Python programming, and so on.
#dswithbappy aims to change this education system of Bangladesh.
I believe that high-quality education is not just for the privileged few. It is the right of everyone who seeks it. My aim is to bring quality education to every single student. All I need from you is intent, a ray of passion to learn.
Thanks!
#dswithbappy
Connect with me here:
Twitter: / bappy913873
Facebook: / dswithbappy
instagram: / entbappy
linkedin : / boktiarahmed73
Github: github.com/entbappy
🙏🙏🙏🙏🙏🙏🙏🙏
YOU JUST NEED TO DO
3 THINGS to support my channel
LIKE
SHARE
&
SUBSCRIBE
TO MY KZbin CHANNEL

[@PuneetSharma-fb7oz]

Use an index with timestamps, if you publish hour long videos. Much easier to find relevant content that way. Not everybody will be interested in everything.

[@mahikhan5716]

i must have to say that content is fantastic , very commendable ur explaining each term

[@catschangepond217]

Good teaching 🤩

[@ManojNair-ff7wo]

Hi Bro, I just wanted to let you know that I find your content training to be the best.

[@ganesarul]

Great One.

[@mukulnamagiri8160]

💝💝 thanks a lot sir

[@postmanpatpat]

The way you explain is really worth it brother I really want to say I fell in love with your content you think deep and make everything easy and interesting to understand I didn't get bored in your video love you brother I am your student now love and respect from Karachi

[@dswithbappy]

Thank you so much :)

[@user-es2re7jo1z]

Sir I appreciate you efforts, I have learnt alot from your MLOps end to end projects. Would be thankful if you please upload such kind of end to end projects videos on mlops

[@TaranKalaa]

Whats the difference between MLOps and mlops? 😂

[@parthivpatel3139]

Sir you are genius and how you learn this type of content in very easy manner and from where to learn this things please share with us its helpful to us as a data scientist please sir

[@singhamrinder50]

Hi Bappy - I am getting "You exceeded your current quota, please check your plan and billing details" error on calling the below method vectordb = Chroma.from_documents(documents = text_splitter, embedding = embedding, persist_directory = persist_directory) I followed your tutorial and this error pops up during first call to OpenAIEmbeddings() method. any suggestions to resolve it.

[@KOTAGIRISIVAKUMAR]

how to append or delete some embeddings from the already existed database?

[@user-ll6mn8ky8d]

bro you teach really good. I'm kinda exploring something similar. Wondering if we can work together on something or any way to collaborate?

[@randomdude79404]

Please do end to end project which use MLOps and Vector Database , (CI/CD) etc...

[@hiteshyerekar9810]

Hi @DSwithBappy how to access your other GENAI private videos.

[@world40123]

i'm getting this ValueError: An instance of Chroma already exists for ephemeral with different settings while executing vectordb = Chroma.from_documents(documents=texts, embedding=HFIembeddings, persist_directory="db") is someone have soluction ?

[@rvraghvender]

While creating chunks, although you have given the parameter `chunk_overlap=200`. But in the following the chunks, I don't see the overlap. Second, you github link doesn't seems to work.

[@MitraPlaylist]

Can you please do a video with Milvus as a vector database?

[@ManojNair-ff7wo]

Cloud you share the Lanchain playlist here. Thanks

[@utkarshtripathi9118]

AttributeError: init is no longer a top-level attribute of the pinecone package.

[@shakilkhan-sx7bc]

What is the drawing tool he has used. Anyone having any idea. Thanks in advance.

[@ishvarlalpatel1867]

Text is not showing in my pinecone console..

[@rutvikchauhan1572]

Hello, your content is good, but I and many others have same query In your medical chatbot project people have been facing issue --> AttributeError: init is no longer a top-level attribute of the pinecone package. after thorough research on pinecone ducumentaion and in this video, we still facing issue please provide solution of this.

[@sivatelugugamer4837]

sir your github link not working

[@damuGaming505]

from_texts is not working ?

[@damuGaming505]

Please reply?

[@rraviteja]

Please use free resources from next time like you used openai for embedding you said there are free embeddings as well so.

[@silent1975]

Initialisation not working

[@alfrede.newman1838]

Good explanation but a simple request for other explanations, please speak much slower. You came across like you were 'playing on 78 rpm' when we normally listen 'on 45 rpm'. Many thanks

[@pizzalot]

Run the video at 0.75X.

[@alfrede.newman1838]

@@pizzalot Seems to work, thanks. FWIW run the video at 0.5 and he sounds drunk!

[@dswithanand]

docsearch = Pinecone.from_texts([t.page_content for t in text_chunks], embeddings, index_name=index_name) This line is giving error - AttributeError: type object 'Pinecone' has no attribute 'from_texts'

[@narendrasinghrawat2298]

I am also struggling from last 1 week. Recently Pinecone have updated the library and some methods are outdated.Request babby to check and provide alternatives.

[@dswithanand]

@@faruqshaikh2099 share the code or github repository

[@naveenpatidar889]

I also have error

[@naveenpatidar889]

You find something solutions about this

[@narendrasinghrawat2298]

@@naveenpatidar889 bro see pinecone documentation we have to use upsert method to send vectors to pineconde database

[@p00o07]

not the initialisation has change can you make the videos on that i am following the tutorial from you had teach in community session i am not able torun that medical chat bot project due to change in the proecss of piecone @dswithbappy