brilliant video!! Much better than the marketing ones from microsoft :)
@ambarishg9 ай бұрын
Wow, thanks!
@UmairMateenKhan5 ай бұрын
Awesome tutorial Ambarish. Keep up the good work.
@limjuroy70786 ай бұрын
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? 😅😅😅
@ambarishg6 ай бұрын
Great suggestion!
@xyz-vv5tg5 ай бұрын
Please. I need it. I have no idea on Azure or any of its services. I'm just exploring and getting confused
@JohnPatrickGallagher3 ай бұрын
I’ll second this, I’m getting Started and it’s a great tutorial so far!
@samosertogo8 ай бұрын
Well done! Brilliant work and very replicable. Thanks a lot!
@ambarishg8 ай бұрын
Many thanks!
@paullopez_ai9 ай бұрын
Great video! Thanks for sharing the code too, greatly appreciated.
@ambarishg9 ай бұрын
Glad to help!
@VivekGupta-zc1ueАй бұрын
Awesome content. Here is the question -- can we upload the confluence page url and get the results from same origin.
@Momentum_Option_Buyer3 ай бұрын
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.
@KenGarff-zp1mh4 ай бұрын
Thanks for the video!
@murtuza.chawala7 ай бұрын
Awesome Video I tried it too wanted to know any way we can do reinforcement learning making the bot train on our feedback
@mohammadsohail65349 ай бұрын
Hi @ambarishg Great video Will the Azure Search AI store the indexed data or it is stored in StorageAcount
@ambarishg9 ай бұрын
In Azure AI Search
@saideepj69983 ай бұрын
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
@Melophile_Gaurav2 ай бұрын
Hey, this was helpful! :)
@shashanksagar48783 ай бұрын
Do we not require any embeddings and vector database here? Also, is vector search not required? If so when is it required? Thank you
@andonii467 ай бұрын
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!
@ambarishg7 ай бұрын
The data is stored in the Azure AI Search index. Please note that if we have to remove a document from the index, we have to delete it from the index. Please also note that in the file upload_docs.ipynb, the function remove_from_index can remove documents from the index
@akankshamakkar85382 ай бұрын
So here we need 3 services, right? azure openai, azure ai search and azure blob storage?
@italoaguiar9 ай бұрын
thanks! very informative video!
@ambarishg9 ай бұрын
Glad it was helpful!
@limjuroy70786 ай бұрын
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?
@ambarishg6 ай бұрын
Yes it is possble
@pooblock40924 ай бұрын
Does this work with files with size large than 16mb?
@indrayne18407 ай бұрын
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?
@pedromoraes51978 ай бұрын
Great video, Man!! Thanks for sharing.
@ambarishg8 ай бұрын
Thanks for watching!
@ankan549 ай бұрын
have you tried creating a vector index in ACS? will vector search be better than semantic search?
@ambarishg9 ай бұрын
Good suggestion will try. Usually Hybrid search is better
@ambarishg8 ай бұрын
@ankan54 . Please have a look at the video kzbin.info/www/bejne/p3vPZHyaeLCZrKc where we discuss the following RAG with Azure AI Search with Azure OpenAI with different search techniques and Langchain with Conversation Chain, Prompt Template and Conversation Buffer 📍 Vector Search 📍 Hybrid Search 📍 Exhaustive KNN Search 📍 Hybrid Search with Semantic reranking 📍 RAG with Azure AI Search with Azure OpenAI 📍 Use Langchain with Conversation Chain 📍 Use Langchain with Prompt Template 📍 Use Langchain with Conversation Buffer
@Momentum_Option_Buyer3 ай бұрын
You didn't use vector database in this specific video (use case) to check data into vectors?
@ambarishg3 ай бұрын
Please watch the following for VECTORS 1. kzbin.info/www/bejne/eICzh5tjZbOAbrc - Vector , Hybrid, Semantic search with Azure AI Search in 11 minutes 2. kzbin.info/www/bejne/p3vPZHyaeLCZrKc -RAG With Azure AI Search using Vector/ Hybrid / Exhaustive KNN / Semantic Reranker in 15 minutes
@sarak84678 ай бұрын
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?
@ambarishg8 ай бұрын
In the code we have added metadata while putting data into the search index. Please add your customized metadata while putting the data into the search index. While doing the Search on Azure AI , we should provide the filter with the proper metadata and it should filter accordingly. Hope this helps. May be I should so a followup video explaining this in detail. Thanks again for your questions.
@sarak84678 ай бұрын
@@ambarishg Thank you so muh for your reply! IT would be perfect if you could show us how to do it. If you can, please show us how to do it on Azure and through code. (I use either Python or C#) Thanks again!
@krishnavasu34997 ай бұрын
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?
@ambarishg7 ай бұрын
Yes you can! kzbin.info/www/bejne/Y2aWqYyIa96Ed7s This shows RAG with QDRANT [ RAG with Opensource Tools - Qdrant and Mistral in 6 minutes ]. You may please modify this for Azure Open AI
@ambarishg7 ай бұрын
kzbin.info/www/bejne/nmWpYWycjM2snsk This shows RAG with LlamaIndex - Qdrant and Azure OpenAI in 9 minutes
@abhinavanand66604 ай бұрын
hey in the section of env where could i find the index name of the ai search
@ambarishg4 ай бұрын
index = "" This is in github.com/ambarishg/AZURE-AI-SEARCH/blob/main/.env.sample
@user-pm1lh3kr9k8 ай бұрын
hey can you please put sample env file and explain the parameters
@ambarishg8 ай бұрын
Sure.I will add the ENV File
@ambarishg8 ай бұрын
Added the .env.sample file in the repository.Hope this helps