qwen_agent/skills/linggan/ragflow-loader/hooks/retrieval-policy.md

Retrieval Policy

0. Task Classification

Classify the request before acting:

• Knowledge retrieval (facts, summaries, comparisons, lists, timelines, extraction, etc.): follow this policy strictly.
• Codebase engineering (modify/debug/inspect code): normal tools (Glob, Read, Grep, Bash) allowed.
• Mixed: use retrieval tools for the knowledge portion, code tools for the code portion only.
• Uncertain: default to knowledge retrieval.

1. Critical Enforcement

For knowledge retrieval tasks, this policy overrides generic codebase exploration behavior.

• Prohibited tools: Glob, Read, LS, Bash (ls, find, cat, head, tail, grep, etc.) — these are forbidden even when retrieval results are empty/insufficient, even if local files seem helpful.
• Allowed tool only: rag_retrieve. No other source for factual answering.
• Local filesystem is a prohibited knowledge source, not merely non-recommended.
• Exception: user explicitly asks to read a specific local file as the task itself.

2. Retrieval Order

• rag_retrieve is the only knowledge source.
• Do NOT answer from model knowledge first.

3. Query Preparation

• Do NOT pass the raw user question unless it already works well for retrieval.
• Rewrite for recall: extract entity, time scope, attributes, and intent.
• Add useful variants: synonyms, aliases, abbreviations, related titles, historical names, and category terms.
• Expand list-style, extraction, overview, historical, roster, timeline, and archive queries more aggressively.
• Preserve meaning. Do NOT introduce unrelated topics.

4. Retrieval Breadth (top_k)

• Apply top_k only to rag_retrieve. Use the smallest sufficient value, then expand only if coverage is insufficient.
• Use 30 for simple fact lookup.
• Use 50 for moderate synthesis, comparison, summarization, or disambiguation.
• Use 100 for broad recall, such as comprehensive analysis, scattered knowledge, multiple entities or periods, or list / catalog / timeline / roster / overview requests.
• Raise top_k when keyword branches are many or results are too few, repetitive, incomplete, sparse, or too narrow.
• Use this expansion order: 30 → 50 → 100. If unsure, use 100.

5. Result Evaluation

Treat as insufficient if: empty, Error:, off-topic, missing core entity/scope, no usable evidence, partial coverage, or truncated results.

6. Fallback and Sequential Retry

On insufficient results, follow this sequence:

1. Rewrite query, retry rag_retrieve (once)
2. Expand top_k: 30 → 50 → 100
3. Say "no relevant information was found" only after exhausting all retries.

• Do NOT switch to local filesystem inspection at any point.

7. Image Handling

• The content returned by the rag_retrieve tool may include images.
• Each image is exclusively associated with its nearest text or sentence.
• If multiple consecutive images appear near a text area, all of them are related to the nearest text content.
• Do NOT ignore these images, and always maintain their correspondence with the nearest text.
• Each sentence or key point in the response should be accompanied by relevant images when they meet the established association criteria.
• Avoid placing all images at the end of the response.

8. Controlled Self-Knowledge Supplement

This section applies only when self-knowledge is enabled.

• Retrieval remains the primary source.
• If retrieval is sufficient, answer from retrieval only.
• If retrieval is partially sufficient, answer the supported parts first.
• The model may supplement only the missing parts that are general knowledge, conceptual explanation, or common background.
• The model must not use self-knowledge to invent private, internal, current, precise, or source-sensitive facts.
• The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications.
• Retrieved facts and self-knowledge supplements must be clearly separated in the response.
• If self-knowledge may be uncertain or time-sensitive, state the uncertainty explicitly.

9. Pre-Reply Self-Check

Before replying to a knowledge retrieval task, verify:

• Used only rag_retrieve — no local filesystem inspection?
• Exhausted retrieval flow (rewritten query + expanded top_k) before concluding "not found"?
• If self-knowledge was used, was it clearly separated from retrieved facts and limited to allowed supplement scope?

If any answer is "no", correct the process first.