Agent Harness Tutorial · Tech stack
18 · Knowledge & retrieval
Finds sourced passages, filtered by what this user may see. Family: Think · one turn, in order.
Why our choiceOne store, one backup, one access model; the entitlement check is just a SQL filter.
| Option | Where from | Verdict | Why |
|---|---|---|---|
| pgvector on the same PostgreSQL | ours | ✓ chosen | not built yet: phase 2 |
| Azure AI Search | Azure | · considered | fallback if the corpus outgrows pgvector |
| Content Understanding | Azure | · considered | |
| pgvector | open source | ◐ planned | chosen |
| Qdrant on Container Apps | open source | · considered | alternative |
Not built yet in the claims assistant; designed in the Series.
Compared: Where do knowledge passages live and get searched?
| Option | From | Verdict | Where it runs | Hybrid keyword + vector | Entitlement filter | Extra infrastructure | When to pick |
|---|---|---|---|---|---|---|---|
| pgvector in Azure PostgreSQL | open source | chosen | inside our PostgreSQL | yes, with Postgres full text | a SQL filter before ranking | none: one store, one backup | default |
| Azure AI Search | Azure | later | managed search service | yes, plus semantic ranker | filters on indexed fields | a search service | corpus outgrows Postgres |
| Qdrant on Container Apps | open source | alternative | a container we run | yes, dense plus sparse | payload filters | a service plus its storage | dedicated vector store needed |
| Pinecone | vendor | not evaluated | managed SaaS | yes, sparse-dense | metadata filters | a SaaS outside Azure | named only |
DecisionPassages live in pgvector in the same PostgreSQL, so entitlement is a SQL filter applied before ranking and there is one store to back up. We would switch to Azure AI Search when the corpus outgrows Postgres or we need its semantic ranker.