Extracted content should feed a RAG app. What is the usual next step?
Why B is the answer
Index it for search
Structured output goes into an index so that agents can retrieve it.
In detail
- Extracted content is indexed for search.
- The RAG app can then retrieve it.
- Keep the source link for citations.
Use case
An illustrative scenario, not a real incident.
A team extracts its documents, then indexes the text in Azure AI Search, so its RAG app can retrieve it.
See it in different ways
sequenceDiagram participant U as User participant A as App participant S as Search index participant M as Model U->>A: Question A->>S: Search S-->>A: Relevant passages A->>M: Question with passages M-->>U: Grounded answer
stateDiagram-v2 [*] --> Extract Extract --> Review: low confidence Extract --> Index: high confidence Review --> Index: corrected Index --> [*]
flowchart LR S0["Extract content"] --> S1["Chunk"] --> S2["Index"] --> S3["RAG app retrieves"]
Key point: Extracted content is indexed for search.
Why the other options are wrong
- A. Convert it to speech
- Speech has nothing to do with RAG.
- C. Train a new image model
- An image model is unrelated.
- D. Delete the original source
- Keep the source for traceability.