Master RAG on Vertex AI with Vector Search and Gemini Pro

[@IanMcAleer-op1xj]

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)

[@ScottJohnson-d3x]

Very excellent Learning session Janakiram!

[@jagatmohansarvari5681]

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

[@edubr2011]

Excelent video! Thanks for sharing the code too.

[@Janakirammsv]

Glad it was helpful!

[@thecopt11]

Best tutorial. Big thanks for your shared.

[@sureshkumarselvaraj8911]

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?

[@ShahidGhetiwala-dg3ol]

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

[@Ahsan_Akhtar1]

really helpful I have question i have multiple pdf files how i handel with them?

[@digiplouxinc.6688]

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 ?

[@MarceloFerreira-rl6hh]

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

[@GAURAVRAUT007]

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

[@AhmedBesbes]

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?

[@Hitish99999]

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

[@arvindmathur6574]

Great!

[@vikasbammidi1340]

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

[@GAURAVRAUT007]

+1

[@JulianHarris]

Nice. Are you ok to share the colab notebook?

[@Janakirammsv]

Yes, sure. Please check the description. I have added the links.

[@dhananjaypathak15]

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

[@TomFord-mv2mx]

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

[@Janakirammsv]

Text embedding models are independent of LLMs. You only have to ensure that the same embedding model is used for indexing the documents and the query. This is critical to retrieving the context based on the similarity.

[@wanderlust8367]

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

[@tarunrey619]

Thanks for sharing knowledge. Can you share the notebook

[@Janakirammsv]

Please check the description. I have added the links.

[@AlaGalai-m9l]

why always python is there any way to use js?

[@khondakersajid1138]

Possible to share the notebook?

[@Janakirammsv]

The code is available at gist.github.com/janakiramm/55d2d8ec5d14dd45c7e9127d81cdafcd and gist.github.com/janakiramm/7dd73e83c92a0de0c683ed27072cdde2