@bobward436 I have created a index with SQL through wizard and adding fields manually. Tried adding the vector profile. But still i am not able to vectorize the data. Vector index size remains 0 size and not able to vectorize the data. Am i missing any step here.
Can you please explain on how did you create single field "embedding" and store all the columns data into it? I am able to generate and store single column data only into single embedding field. Not able to store all the columns data into single embeddings.
Also curious if there's an entirely on-prem scenario that could be supported, perhaps using one of the various Open Source vector databases [installed locally] and something like Phi-3 or Llama as a locally executing SLM. I have a high-profile scenario using on-prem SQL that could really use that kind of functionality but there is no option to connect to Azure.
Hi are you looking for something that enables you to chat with your databases? There's two options I have tried, AskYourDatabase and Insightbase, the first one is going to support fully on-premise solutions.
Are all the fields in the Azure AI Search index (productdataindex) created automatically, or do we need to manually create them ourselves? I assume that these fields are generated automatically when connecting Azure AI Search to our SQL Database data source.
You can use an import wizard with Azure AI Search with your SQL Data but to get embeddings to be created correctly in this case I manually created the index, put in my field names to match the columns in the source table, and then when creating the index (indexer) I specified the index definition, the data source table from SQL, and the skillset with OpenAI to generate embeddings.
@@bobward436 I see. So, you manually created the index (productdataindex) and all its fields in the Azure AI Search, except for the embeddings field. Is that correct?
@@bobward436 Like others suggested in the comments, it would be nice to see how you did this. Specifically where/how did you create the indexer and skillset. I used the Import Data Wizard to connect to an Azure SQL data source and create an index, but it isn't populated by anything. Glossing over this in the video leaves a big gap in implementation. A link to a tutorial or specific content addressing this is needed.
can you ask Microsoft SQL team to make "SQL Server & Studio" keep a log of performance & query, as to allow us to look back to see if the server is running low on RAM, IOPs or Network? then ask the Microsoft PowerToys teams to create an App to monitor the SQL Server for said performance. With this info, they can use SQL AI to help the user get better SQL performance.
Have you looked into Azure Monitor and App Insights? These alerts can be instrumented into your reporting with alerts set based on memory, IOPS, network and other conditions. See learn.microsoft.com/en-us/azure/azure-monitor/alerts/alerts-create-activity-log-alert-rule?tabs=activity-log
At 13:18 that is because you are using the TFS wrong. Learn how to properly use TFS and don't spend money on Azure AI Search. Oh, by the way, Azure uses TFS to do the text search.
How did you add the index with embeddings?
@bobward436 I have created a index with SQL through wizard and adding fields manually. Tried adding the vector profile. But still i am not able to vectorize the data. Vector index size remains 0 size and not able to vectorize the data. Am i missing any step here.
Hi, AskYourDatabase does not require you to do any embeddings and it works out-of-the-box.
Can you please explain on how did you create single field "embedding" and store all the columns data into it?
I am able to generate and store single column data only into single embedding field. Not able to store all the columns data into single embeddings.
Also curious if there's an entirely on-prem scenario that could be supported, perhaps using one of the various Open Source vector databases [installed locally] and something like Phi-3 or Llama as a locally executing SLM. I have a high-profile scenario using on-prem SQL that could really use that kind of functionality but there is no option to connect to Azure.
The demo where I used Azure AI Search can work with an existing on-premises SQL Server
@@bobward436is there still a dependency on Azure AI? I need the whole thing to run disconnected from the cloud.
Hi are you looking for something that enables you to chat with your databases? There's two options I have tried, AskYourDatabase and Insightbase, the first one is going to support fully on-premise solutions.
Is there any additional cost involved for using copilot inside query editor of azure sql?
Today this is in preview so there is no cost
Are all the fields in the Azure AI Search index (productdataindex) created automatically, or do we need to manually create them ourselves? I assume that these fields are generated automatically when connecting Azure AI Search to our SQL Database data source.
You can use an import wizard with Azure AI Search with your SQL Data but to get embeddings to be created correctly in this case I manually created the index, put in my field names to match the columns in the source table, and then when creating the index (indexer) I specified the index definition, the data source table from SQL, and the skillset with OpenAI to generate embeddings.
@@bobward436 I see. So, you manually created the index (productdataindex) and all its fields in the Azure AI Search, except for the embeddings field. Is that correct?
@@bobward436 Like others suggested in the comments, it would be nice to see how you did this. Specifically where/how did you create the indexer and skillset. I used the Import Data Wizard to connect to an Azure SQL data source and create an index, but it isn't populated by anything. Glossing over this in the video leaves a big gap in implementation. A link to a tutorial or specific content addressing this is needed.
The part to trust that my data is queried but not used for training models or something else is ...
Given this is SQL and data often changes, what is the mechanism for making sure your embeddings are updated?
The Azure AI Search index will stay in sync with data changes.
You set a refresh schedule basically..
Can it be used against SQL Server database instead of Azure SQL?
@@adilmajeed8439 This can be used for any SQL Server database
Hi Ken, there's another work around towards this, tools like AskYourDatabase directly interacts with your databases without any syncing issues.
Your Copilot looks smarter than the one i'm using...
insn't it a better prompt?
How much?
Can it does the same with MS Access like SQL databases? Thank you.
I don't know of any solution like this for MS Access
“That’s really cool. Is there a way I can set up everything as shown in the video and try these out on my own?”
can you ask Microsoft SQL team to make "SQL Server & Studio" keep a log of performance & query, as to allow us to look back to see if the server is running low on RAM, IOPs or Network?
then ask the Microsoft PowerToys teams to create an App to monitor the SQL Server for said performance.
With this info, they can use SQL AI to help the user get better SQL performance.
Have you looked into Azure Monitor and App Insights? These alerts can be instrumented into your reporting with alerts set based on memory, IOPS, network and other conditions. See learn.microsoft.com/en-us/azure/azure-monitor/alerts/alerts-create-activity-log-alert-rule?tabs=activity-log
This is great new tech howeever some of us i still using on Prepm SQL 2016 due Application limitation , we still got a long way to go.
For Azure AI Search your data source could be an on-premises SQL Server 2016 database
Hi, if you use on-premise db you can use tools like AskYourDatabase, they can connect to private db.
At 13:18 that is because you are using the TFS wrong. Learn how to properly use TFS and don't spend money on Azure AI Search. Oh, by the way, Azure uses TFS to do the text search.
❤❤❤