The requirement has two key phrases: indexing information and knowledge mining by extracting insights from documents . The Microsoft service purpose-built for this is Azure AI Search (formerly Azure Cognitive Search), which provides a search index over your content and supports "AI enrichment" workflows to extract and structure insights from documents during indexing.
Azure AI Search can ingest content from common enterprise sources (files, blobs, databases), build searchable indexes, and enrich the indexed content using built-in skills or integrated AI capabilities-such as entity recognition, key phrase extraction, language detection, and OCR (depending on the pipeline). This is exactly what "knowledge mining" refers to: turning large volumes of unstructured documents into structured, searchable knowledge that applications and users can query.
The other choices are partial fits: Azure Vision focuses on image/video analysis, not general document indexing. Azure Document Intelligence is excellent for extracting fields/tables from forms and documents, but on its own it does not provide the full indexing/search and knowledge mining layer across a corpus.
Microsoft Foundry is an overarching platform for building AI apps/agents; it can incorporate search, but the specific service that directly delivers indexing + knowledge mining is Azure AI Search .