Such a wonderful presentation. Great people always explains a complex topic as if it is very simple. You seems to be one of them.
@14XavecoАй бұрын
Actually pretty good content.. great job my man!
@alexandermoev9395Ай бұрын
amazing man!
@shukrantpatilАй бұрын
Hi, I had a question, is it possible to feed a pdf to the AI agent as a part of its content ? For example can i feed a science text book pdf since i want to create an ai agent which can teach students science.
@surendars265622 күн бұрын
Answer this question anyone please
@ayushjha5360Ай бұрын
@venkatathota633 4 months ago could you please provide git repo for the above code?
@bharanidharanm2653Ай бұрын
Really helpful
@AbhishekPorwal-h8x2 ай бұрын
While invoking bedrok, I am getting error AttributeError: 'Bedrock' object has no attribute 'invoke_model', how to solve this
@digiplouxinc.66882 ай бұрын
In your video you say "sentence_file_path". However shouldn't it be "embed_file_path" ? create_tree_ah_index function should have the GCS bucket of the embedded data and not the text with teh ids right ?
@ravirajasekharuni2 ай бұрын
Can you provide GitHub repo for this app for me to tryout. Also please provide step by step instructions to build and deploy the rag in docker/kubenetes
@Ahsan_Akhtar12 ай бұрын
really helpful I have question i have multiple pdf files how i handel with them?
@imransaid10262 ай бұрын
Is there an inherent benefit to using Vertex Ai rather than AI Studio?
@ScottJohnson-d3x2 ай бұрын
Very excellent Learning session Janakiram!
@captainmcduckyYT2 ай бұрын
Very helpful. Thank you so much good sir.
@jagatmohansarvari56812 ай бұрын
really helpful for understanding the concept of embedding and retrieval. Thanks.
@anilaknb12 ай бұрын
Great video & playlist ! Can you please share the source code ?
@dhananjaypathak152 ай бұрын
i want same thing in nodej can some one please help on which library to use
@kaushikdas51152 ай бұрын
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!
@Manish693 ай бұрын
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
@birolyildiz3 ай бұрын
❤🙏
@AyushMandloi3 ай бұрын
No voice
@wanderlust83674 ай бұрын
the code link u have shared is incomplete, load_file is missing and other few stuffs,
@ShaliniMohan-vr4rb4 ай бұрын
Good Content and explanation for all the beginners
@jeffpowell8604 ай бұрын
Why is Chroma such hot garbage?
@shaktipawar53724 ай бұрын
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...
@brenoav994 ай бұрын
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!
@shaktipawar53724 ай бұрын
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 !!
@tubasweb4 ай бұрын
Can you make an update video onnx?
@IanMcAleer-op1xj4 ай бұрын
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)
@AaronNicholsonAI4 ай бұрын
Super helpful! Thank you so much.
@ainanirina7584 ай бұрын
Awesome work as always! Do you have a link for the collab? Thanks
@awakenwithoutcoffee4 ай бұрын
can we make our own "online" models with the Brave-API ?
@VijayKumar-ws3gv4 ай бұрын
Nice Explanation Anna :) expecting Enterprise Gen AI on AWS/AZURE/GCP
@larsfrommiddle21625 ай бұрын
Do the online models also give back the source of the websites or papers it uses, when asked?
@Statsjk4 ай бұрын
Did you figure it out?
@suryarp5 ай бұрын
What a pleasure to see Priyanka on your show! Awesum❤❤
@suryarp5 ай бұрын
Teaser really teased😊
@MarceloFerreira-rl6hh5 ай бұрын
Great job! Thanks a lot. What’s the difference between this approach and using langchain?
@softreviewed5 ай бұрын
perplexity now supports mixtral-8x22b-instruct so if we uses can we get more accurate answers ?
@GAURAVRAUT0075 ай бұрын
Excellent video - can u please do same with Langchain with retrieval
@tavishi38845 ай бұрын
Sir Can we use this gemini 1.5 pro with Langchian ..?
@fusionxfitness_5 ай бұрын
you didn't shared the pdf
@vikasbammidi13405 ай бұрын
Can you please do a video on "How to use the same in Langchain with retrieval"
@GAURAVRAUT0075 ай бұрын
+1
@ammvr5 ай бұрын
how can we deploy this to the web?
@elibessudo5 ай бұрын
Thanks for sharing. Do you have any insight on how to incorporate the feature where the response includes citation URL's?
@harishankar75875 ай бұрын
impressive slide show
@AlaGalai-m9l5 ай бұрын
why always python is there any way to use js?
@venkatathota6335 ай бұрын
could you please provide git repo for the above code?
@AIWithShrey5 ай бұрын
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.