Відео

Hola, quisiera saber si al momento de recuperar esa información o base de conocimiento de los blobs, esos archivos tambien consumen tokens junto con la prompt?

which method will be better? also need a an idea on comparing with auto merging retrieval.

no code in github

Very good explanation! Thank you!

the way explanation was awesome

I will try to rag by my single pdf please help , i am using thr blog storage for upload the file and after that i get the files from blob and extract text after i take azure openai model text embedded ada 002 for embedding all the extract the text which i get from pdf after that 12 embedding is create now i want to azure ai search can you tell me how we can do using python code , I will try to upload the documents by combining text chunk and embedding after i upload in indexes but only goes last file so please help me related the correct way

Thank you sir

Super Fantastic demo sir, the way you articulated the information is just Awesome, happy to share in learning community. Thanks !!

thanks, 9 months and still very informative.

Could you make a video on how can we reference the documents on the answers? I mean, showing which documents where found and used to generate a response

This video is really informative and well-structured. Understanding vector and hybrid search in such a short time is impressive. I recently came across Myko Assistant, and it's helped me find detailed professional profiles quickly without the complexity of other tools. It’s great for getting accurate info efficiently.

Really great video thanks so much for taking the time ❤

Awesome content. Here is the question -- can we upload the confluence page url and get the results from same origin.

Very nice explanation. Short & easy to understand. It helped me understanding how AI search works.

Nice session.. Can we boot up that vector - qardent db in windows 10 - os environment with docker sw ? Can we connect qardent - docker service with paython code in locally setting up ?

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

Great explanation and simple . Good that you focused on search without the hurdles of CosmosDB

Hey, this was helpful! :)

Thanks...this simplified langchain. but code is not in the shared github link.

This is perfect sir, you are already ahead of industry implementation era.. great stuff..

I have created an index for a CSV file and i had few custom fields and also i have enabled Semantic reranker for the AI Search. Now i want to use this in my code but unable to get any fruitfl results. Can you please help ? And I am using Langchain as orchestrator

Very informative.

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.

You didn't use vector database in this specific video (use case) to check data into vectors?

thanks for the info, great explanation

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

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

can you do one between llama-index and azure ai search?

Thank you for this lovely video. I am interested in how you created those indexes within Azure AI Search. What if I have data in json format?

Thanks for the video!

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

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

below is my vector store creation code without using RBAC but if i want to use RBAC what should i have to change in below code vector_store: AzureSearch = AzureSearch( azure_search_endpoint=os.environ.get("SEARCH_ENDPOINT"), azure_search_key=os.environ.get("SEARCH_API_KEY"), index_name=index_name, embedding_function=embeddings.embed_query, )

Really nice stuff to start with.. than you

Is it acceptable to perform all these tasks directly from the portal, using the no-code option?

Useful stuff. Thanks for the video!!

Do you mind sharing the repo for this talk ?

Do you know how can we retrieve access token from AWS secret manager instead putting it in profile.yml ?

When I do Vector/Hybrid search, the content that is returned are just references. I want it to answer the question also. Am I doing something wrong?

Awesome tutorial Ambarish. Keep up the good work.

A quick question....Using a single project ....can we write tables in different catalogs in databricks? I see that catalog is defined at a project level and wondering if we can use different catalogs for a single project

It's really helpful. I'm facing a problem local image in accessible through localhost, but pods are not accessible through local host. does the port need to be same a local image?

Hi Sir any tutorial for recommendation service using azure search

Love that you were recording the video just a few minutes before a new year😅

Can you do data drift for LLmops on azure

thank you so much for this. this sis very helpful. am gonna modify this a little in order to add to my portfolio. big thanks again , sir.

Hi bro please respond

i dont know weather it is right to ask or not ,can you please tell keys in microsoft azure about this project for my final year project

i wanted to know that give text and images as input for this project at a time please help me me also doing similar project in jupyter notebook,but we are unable give new images as input only predefined images it takes. can you help me more

bro how can i contact you bro for this project more details