Dependency Injection for AI Components
Register .NET AI clients, tools, prompts, and retrieval services with explicit lifetimes, safe request state, and clear disposal ownership.
Csharp
Treat the model finish reason as a control signal
Check why generation stopped before accepting model output, and give incomplete responses an explicit application outcome.
Persist ingestion checkpoints at source boundaries
Track progress per consumer and source ordering boundary, and advance each checkpoint only after the corresponding ingestion work succeeds.
Treat provider throttling as a shared capacity signal
Let one throttling response reduce pressure from every caller sharing the affected capacity pool.
`await foreach` does not automatically use your cancellation token
A CancellationToken in scope does nothing unless the async enumeration receives and observes it.
Preserve the stack trace with `throw`, not `throw ex`
Rethrow the current exception with throw; so the original failure location remains visible.
Store a source checksum to skip unchanged documents
Compare a document’s source checksum, metadata, and ingestion profile before repeating extraction, chunking, embedding, and index writes.
Pin culture and time zone in tests that depend on them
Make culture and time zone explicit inputs when parsing, formatting, or local-time conversion depends on them.
Keep tool results inside a token budget
Bound every model-visible tool result before it enters the next prompt.
Your First Qdrant Collection
Run Qdrant locally, connect with the official .NET client, and create a collection whose vector size and distance match the embedding model.