Files

T

Developer 0a9588abb7 feat: implement QuestionBank CRUD with pagination and template query

- Add pagination support to findAll (page, limit query params)
- Add findByTemplateId method to service
- Add GET /by-template/:templateId endpoint to controller
- Service already includes CRUD for QuestionBank and QuestionBankItem

2026-04-23 17:19:11 +08:00

3.2 KiB

Raw Permalink Blame History

Design: Cross-Document Comparison (Agentic Workflow)

1. Background & Problem

Users often need to compare multiple documents (e.g., "Compare the financial reports of Q1 and Q2" or "Differences between Product A and Product B specs"). Standard RAG retrieves chunks based on semantic similarity to the query. While "Multi-Query" helps, standard RAG might:

Retrieve too many chunks from one document and miss the other.
Fail to align comparable attributes (e.g., comparing "revenue" in Doc A with "profit" in Doc B).
Produce a generic text answer instead of a structured comparison.

2. Solution: Agentic Comparison Workflow

We will implement a specialized workflow (or "Light Agent") that:

Analyzes the Request: Identifies the subjects to compare (e.g., "Q1 Report", "Q2 Report") and the dimensions (e.g., "Revenue", "Risks").
Targeted Retrieval:
- Explicitly filters/searches for Doc A.
- Explicitly filters/searches for Doc B.
Structured Synthesis: Generates the answer, potentially forcing a Markdown Table format for clarity.

3. Technical Architecture

3.1 Backend (`ComparisonService` or extension to `RagService`)

Intent Detection: Modify ChatService or RagService to detect comparison intent (can utilize LLM or simple heuristics + keywords).
Planning: If comparison is detected:
1. Identify Target Files: Resolve file names/IDs from the query (e.g., "Q1" -> matches file "2024_Q1_Report.pdf").
2. Dimension Extraction: What to compare? (e.g., "summary", "key metrics").
3. Execution:
  - Run Search on File A with query "key metrics".
  - Run Search on File B with query "key metrics".
  - Combine context.
Prompting: Use a prompt optimized for comparison (e.g., "Generate a comparison table...").

3.2 Frontend (`ChatInterface`)

UI Trigger: (Optional) specific "Compare" button, or just natural language.
Visuals: Render the response standard markdown (which supports tables).
Source Attribution: Ensure citations map back to the correct respective documents.

4. Implementation Steps

Intent & Entity Extraction (Simple Version):
- In RagService, add a step detectComparisonIntent(query).
- Return subjects: string[] (approximate filenames) and dimensions: string.
Targeted Search:
- Use elasticsearchService to search specifically within the resolved file IDs (if we can map names to IDs).
- Fall back to broad search if file mapping fails.
Comparison Prompt:
- Update rag.service.ts to use a comparisonPromise if intent is detected.

5. Risks & limitations

File Name Matching: Mapping user spoken "Q1" to "2024_Q1_Report_Final.pdf" is hard without fuzzy matching or LLM resolution.
- Mitigation: Use a lightweight LLM call or fuzzy search on the file list to resolve IDs.
Latency: Two searches + entity resolution might add latency.
- Mitigation: Run searches in parallel.

6. MVP Scope

Automated detection of "Compare A and B".
Attempt to identify if A and B refer to specific files in the selected knowledge base.
If identified, restrict search scopes accordingly (or boost them).
Generate a table response.

3.2 KiB Raw Permalink Blame History