[modify] rag qa chunk

api/app/core/rag/prompts/generator.py

@@ -131,18 +131,43 @@ def keyword_extraction(chat_mdl, content, topn=3):
 
 
 def question_proposal(chat_mdl, content, topn=3):
+    """生成问题（向后兼容，返回纯文本问题列表）"""
+    pairs = qa_proposal(chat_mdl, content, topn)
+    if not pairs:
+        return ""
+    return "\n".join([p["question"] for p in pairs])
+
+
+def qa_proposal(chat_mdl, content, topn=3):
+    """生成 QA 对，返回 [{"question": ..., "answer": ...}, ...]"""
     template = PROMPT_JINJA_ENV.from_string(QUESTION_PROMPT_TEMPLATE)
     rendered_prompt = template.render(content=content, topn=topn)
 
     msg = [{"role": "system", "content": rendered_prompt}, {"role": "user", "content": "Output: "}]
     _, msg = message_fit_in(msg, getattr(chat_mdl, 'max_length', 8096))
-    kwd = chat_mdl.chat(rendered_prompt, msg[1:], {"temperature": 0.2})
-    if isinstance(kwd, tuple):
-        kwd = kwd[0]
-    kwd = re.sub(r"^.*</think>", "", kwd, flags=re.DOTALL)
-    if kwd.find("**ERROR**") >= 0:
-        return ""
-    return kwd
+    raw = chat_mdl.chat(rendered_prompt, msg[1:], {"temperature": 0.2})
+    if isinstance(raw, tuple):
+        raw = raw[0]
+    raw = re.sub(r"^.*</think>", "", raw, flags=re.DOTALL)
+    if raw.find("**ERROR**") >= 0:
+        return []
+    return parse_qa_pairs(raw)
+
+
+def parse_qa_pairs(text: str) -> list:
+    """解析 LLM 返回的 QA 对文本，格式: Q: xxx A: xxx"""
+    pairs = []
+    for line in text.strip().split("\n"):
+        line = line.strip()
+        if not line:
+            continue
+        # 匹配 Q: ... A: ... 格式
+        match = re.match(r'^Q:\s*(.+?)\s+A:\s*(.+)$', line, re.IGNORECASE)
+        if match:
+            q, a = match.group(1).strip(), match.group(2).strip()
+            if q and a:
+                pairs.append({"question": q, "answer": a})
+    return pairs
 
 
 def graph_entity_types(chat_mdl, scenario):

api/app/core/rag/prompts/question_prompt.md

@@ -1,19 +1,24 @@
 ## Role
-You are a text analyzer.
+You are a text analyzer and knowledge extraction expert.
 
 ## Task
-Propose {{ topn }} questions about a given piece of text content.
+Generate {{ topn }} question-answer pairs from the given text content.
 
 ## Requirements
-- Understand and summarize the text content, and propose the top {{ topn }} important questions.
+- Understand and summarize the text content, and generate the top {{ topn }} important question-answer pairs.
+- Each question-answer pair MUST be on a single line, formatted as: Q: <question> A: <answer>
 - The questions SHOULD NOT have overlapping meanings.
 - The questions SHOULD cover the main content of the text as much as possible.
-- The questions MUST be in the same language as the given piece of text content.
-- One question per line.
-- Output questions ONLY.
+- The answers MUST be concise, accurate, and directly derived from the text content.
+- The answers SHOULD be self-contained and understandable without additional context.
+- Both questions and answers MUST be in the same language as the given text content.
+- Output question-answer pairs ONLY, no extra explanation.
+
+## Example Output
+Q: What is the capital of France? A: The capital of France is Paris.
+Q: When was the Eiffel Tower built? A: The Eiffel Tower was built in 1889.
 
 ---
 
 ## Text Content
 {{ content }}
-