RAG with Azure AI Search and Azure Open AI in 9 minutes

Equipment used

RAG [ Retrieval-Augmented Generation ] concept explained
📍 How we do we ingest data into our RAG architecture?
📍 How we do we query from our RAG architecture?
📍 Detailed use of Azure AI Search and Azure OpenAI in RAG
📍 Demo of our built in RAG application

[UmairMateenKhan]

Awesome tutorial Ambarish. Keep up the good work.

[paullopez_ai]

Great video! Thanks for sharing the code too, greatly appreciated.

[samosertogo]

Well done! Brilliant work and very replicable. Thanks a lot!

[murtuza.chawala]

Awesome Video I tried it too wanted to know any way we can do reinforcement learning making the bot train on our feedback

[indrayne]

Sir I have one doubt, like we are using Azure Cognitive search and the index updates everyday midnight. So we have both new content and old content with us. Now what I want is to retrieve the most recent content first and than old content. How can I implement it?

[saideepj]

Thanks for such a detailed content. Is the uploaded data going to private ? will that data be trained with open source LLM's . How to add extra layer of security to make sure that the uploaded data is within my private GPT

[pedromoraes]

Great video, Man!! Thanks for sharing.

[akankshamakkar]

So here we need 3 services, right? azure openai, azure ai search and azure blob storage?

[shashanksagar]

Do we not require any embeddings and vector database here? Also, is vector search not required? If so when is it required? Thank you

[pooblock]

Does this work with files with size large than 16mb?

[davemcshane]

brilliant video!! Much better than the marketing ones from microsoft :)

[Momentum_Option_Buyer]

1:01 Is Azure search is or acts like a vector database that keeps the knowledge? Please clarify I have seen several videos but confused on this question.

[limjuroy]

Here is my little 2 cents', can you do an end-to-end tutorial on how you do this, including creating Azure AI Service, Azure Storage as well as the coding part? 😅😅😅

[andonii]

Amazing video! One question, if you have the data source a blob storage, if you delete a pdf file from that blob storage, when you run the indexer is the reference and information about this deleted document deleted from the index as well? thanks!

[sarak]

Hi Ambarish, thank you for the very helpful video! I have an enquiry and I hope you could help me with it. So, on the Azure Platform, I have created a a Search Service and an OpenAI Service and connected both in order to be able to ask questions about the data stored on an index. The data is in a Blob Storage container that has multiple folders in it. What I want to do when searching for information, is to filter the folders; I want to choose the folder (either by name or path), so that the search service only returns the content of that folder, and then the openAI service uses that content as a reference to generate an answer to my question. Do you know how I could do that?

[mohammadsohail]

Hi @ambarishg Great video
Will the Azure Search AI store the indexed data or it is stored in StorageAcount

[limjuroy]

What if I want the app "also" has the ability to upload our own PDF file and query the content of the just uploaded file through UI?

[ankan]

have you tried creating a vector index in ACS? will vector search be better than semantic search?

[krishnavasu]

Great video! Very helpful. Instead of azure AI search, if I wanted my retriever to be Qdrant, would it be possible? I have a few files in Qdrant and would like to use Azure open AI to get the output from Qdrant and give the result to the user. If possible, how could I do it?

[abhinavanand]

hey in the section of env where could i find the index name of the ai search