Using Azure Search With Azure OpenAI & Langchain (End-to-End Flow Using Non-Semantic Search)

Do you want to know how to utilize Azure Cognitive Search With Azure OpenAI and Langchain, then check out this video to know more about it and understand how to create an end-to-end flow.

** REFERRAL LINK *************
** REFERRAL LINK *************

###### MORE PLAYLISTS ######

#openai #chatbot #chatgpt

[csalaberry]

Amazing tutorials Shweta! Thank you so much for sharing your knowledge.

[smart-sgcs]

hey shweta this is one video i am looking forward to.
you are simply great and ur way of explaining the concept is superb
keep it up
thanks

[VijayKumar-pdmu]

fantastic, excellent explanation and easy to understand

[jatinderarora]

Thanks for sharing. This is exactly what I was looking for.

[akashvijay]

First of all great content with simplicity of explanation that everyone can understand.
I had a doubt How can we do a cognitive search on the Azure Dataverse, while cognitive search doesn't support data type as Dataverse / sharepoint connect directly

[chetansameer]

Hi Shweta,
This is indeed fantastic..Can you do a same video using semantic search as well.

[hariram-pzuz]

Hi Mam This tutorial is awesome, I am having few doubts, 1. Can we use it as an api and integrate with an Application, 2. whether it will run a training kind of thing when each time we try to get output, 3. can we ingest multiple documents including pdf

[theagsdiaries]

hi Shweta Lodha, can you do a video on with semantic search full video with azure search/azure openai/langchain

[jyqslpi]

I got a error without metadata, who can you tell me why?
when I excuted "
vectordb = Chroma.from_documents(documents=docs, embedding=embeddings, persist_directory='Store') "

[learningthings]

Hi Shweta, when I am doing vectordb = Chroma.from_documents(documents=docs, embedding=embeddings, persist_directory='Store')
I am getting the error: resource not found.
I have tried with both text-embedding-ada-002 and gpt-35-turbo models. What could be the reason?

[kevinsusanto]

Hello Shewta, thank you for your great tutorial. I want to ask you,
When I run this code: vectordb = Chroma.from_documents(documents=docs, embedding=embeddings, persist_directory='Store')
I got this error: Must provide an 'engine' or 'deployment_id' parameter to create a <class

Do you know what should I do about this? I hope that you could help.

Thank you so much!

[manojselvakumar]

Great content!
Can we host vector databases such as Chrome within Azure ecosystem?

[maysamtk]

Can we use just Azure Cognitive Search indexes to store embedding? and Not using Chroma?
From what I see we are just reading data from Azure Search and we are not benefitting from the search engine itself. Same way as we are reading data from a file or storage account

[ChrisadaSookdhis]

If already using ChromaDB for vector storage and similarity search, what does Azure Cognitive Search actually needed for?

[krunalthakkar]

Hello @shweta-lodha,

I am not able to find "text-davinci-002" model in the model list of deployment. any suggestions for that?

[shaikshavalivali]

I have one doubt Does Azure cognitive service provides vector db service too or not? please help me.

[sathishramalingam]

HI, i got error in (content_key ) i enter the correct key but it does not run

[narayangouda]

Hi, How can we use PDF files with Azure Openai embeddings for QA as we can use gpt-index and langchain with Openai LLM.

[rameshramaswamy]

Getting error while defining vectordb = Chroma.from_documents(docs, embeddings). "The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again". Any help?