Azure AI Search
by Microsoft
Azure AI Search, previously Azure Cognitive Search, powers search and retrieval for many RAG applications. Its REST APIs return indexes, documents, indexers with their run status, and service statistics on storage and document counts. In the Lake, indexer failures and document counts can be compared with source systems to confirm that what assistants retrieve is complete and current.
- Category
- Cloud & Data Platforms
- Type
- Search engine
- Interface
- REST API
- Built with
- Connect Any API
- Credentials
- API key, OAuth 2.0
02Data
What you can sync.
- Indexes
- Documents
- Indexers
- Indexer status
- Service statistics
Load Azure AI Search indexes into your Lake and model it in the Warehouse with the rest of your stack.
Need more? Name any other Azure AI Search data the API returns, and the AI adds it to the connector.
03Credentials
Credentials you will need.
- An API key
- OAuth 2.0 (client ID, client secret, refresh token)
Azure AI Search uses an API key or OAuth 2.0 (client ID, client secret, refresh token). You add the credentials once, when the AI asks for them, and it tells you where to create them in Microsoft if you need help.
04Questions
Questions you can answer.
Once Azure AI Search data is in your Lake, ask an AI Mind in plain words or build the answer in DataPrism BI.
- Which indexers failed or skipped documents in the last week, and from which data sources?
- How do document counts in each index compare with the source tables they come from?
- How fast is index storage growing against the service tier quota?
- When was each index last refreshed by its indexer?
05How it works
How it works in DataMind.
-
Pick Azure AI Search.
Open Lake, pick Azure AI Search in the source picker and name the connection. Connect Any API opens with a ready prompt that points the AI at the Azure AI Search API docs.
-
Answer a few questions.
The AI reads the Azure AI Search documentation, then asks which credentials you will use, which data to sync (for example indexes and documents), whether you want a one-time load or a recurring sync, and which accounts or filters apply.
-
Your data lands in Lake.
It builds the connector, tests it and shows you sample rows. Then Azure AI Search data loads into your Lake on your schedule, ready for the Warehouse, DataPrism BI and AI Minds.
06Pairs
Works well with Azure AI Search.
Sources teams join with Azure AI Search in the Warehouse, each one connected the same way.
