Video

Very helpful. Thank you so much good sir.

really helpful for understanding the concept of embedding and retrieval. Thanks.

Great video & playlist ! Can you please share the source code ?

i want same thing in nodej can some one please help on which library to use

Sir, I have a long text which contains five bidder details and their financial values such as turnover, revenue etc. and that is stored in a variable, bidders_data. could you pls let me know how can I create a tool or function to draw a bar chart for the bidder names and turnover or any other financial parameters, when I give a prompt such as ''draw a bar chart for bidders (bidder names) and their turnover", so it should draw a bar chart as response. Awaiting for you reply sir!

great work sir , this was very useful but throughout the whole video the audio was coming only from left side of headphones i hope you will fix this issue next time

❤🙏

No voice

the code link u have shared is incomplete, load_file is missing and other few stuffs,

Good Content and explanation for all the beginners

Why is Chroma such hot garbage?

Hi Janakiram. Can you explain Self attention and Feed forwarder layer in more detail plz ? Example what are the fundamental purpose / responsibility of each of them...

Thank you for the useful video. I'm having a problem using the chroma and google embedding (new versions): >>> vectordb=Chroma.from_documents(pages,embeddings) ValueError: Expected each embedding in the embeddings to be a list, got ['Repeated'] Do you have any ideas? Thanks in advance!

Janakiram, This is one of the best Fine Tuning Video I have came across. I need to thank you for getting this concept clear in such a simple manner. Keeping making such videos, it helps community to grow. Thank you !!

Can you make an update video onnx?

Thanks, this is tremendously helpful One point to note - you need to upload the embed file, not the sentence file -> upload_file(bucket_name,embed_file_path)

Super helpful! Thank you so much.

Awesome work as always! Do you have a link for the collab? Thanks

can we make our own "online" models with the Brave-API ?

Nice Explanation Anna :) expecting Enterprise Gen AI on AWS/AZURE/GCP

Do the online models also give back the source of the websites or papers it uses, when asked?

What a pleasure to see Priyanka on your show! Awesum❤❤

Teaser really teased😊

Great job! Thanks a lot. What’s the difference between this approach and using langchain?

perplexity now supports mixtral-8x22b-instruct so if we uses can we get more accurate answers ?

Excellent video - can u please do same with Langchain with retrieval

Sir Can we use this gemini 1.5 pro with Langchian ..?

you didn't shared the pdf

Can you please do a video on "How to use the same in Langchain with retrieval"

how can we deploy this to the web?

Thanks for sharing. Do you have any insight on how to incorporate the feature where the response includes citation URL's?

impressive slide show

why always python is there any way to use js?

could you please provide git repo for the above code?

Any reason why you chose BAAI and not any other Embedding model? What are the impacts of mix and matching the Embedding model and the LLM? My current app works just fine with GPT4ALL Embeddings, and Gemma 1.1 7B. Another note: Deploying a quantized LLM will significantly reduce VRAM usage, Gemma 7B Q8_0 quantized takes up 12 gigs of VRAM for me. Implementing KEDA and using Quantization in tandem will be a game-changer.

To whoever is experiencing problems with the following lines of code: URI='http:...' client = InferenceClient(model=URI) Do this instead: find a model that you want to use on huggingface, such as Mistral 7B, create an access token, save the model URL and use the following code: API_URL = "your_chosen_model_url" headers = {"Authorization": "Bearer your_created_token"} inference_client = InferenceClient(model=API_URL, headers=headers)

Concise and to the point. Superbly explain! Thank you...

Thanks for the tutorial. I am bit confused which file to be uploaded to bucket. sentence file or embedding file

This was a great close encounter and looking forward for the GenAI courses from Jani sir in collab with kode kloud way of doing 😃

Thanks for the tutorial! Instead of going through the ids in the json file to fetch the sentences, is it possible to integrate those directly as metadata in the index?

Great video! What is the difference between Vertex Search service VS Vector Search for RAG application? which one is better in terms of handling better retrieval of relevant documents for RAG application where we deal with 100+ PDF documents? Can you share some insights?

What is the confusion at 14:23? What are meta data files? What are these phrases in a realtime scenario? You are doing good but please give examples that are actually possible in realtime scenarios

is oscer-index file saved in s3?

Thank you for putting all the content in a very simple and understandable way!

Source code please

is this on sagemaker?

Can we add two different documents in collection ?

Great Video. One question, I noticed you used a different model (gecko) to Gemini Pro for the embeddings. Is this ok to do? I assumed the models needed to be the same for both training and inference? Thanks again

Great!

Great Video, thank you soo much........