[modify] QA pair

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

@@ -149,13 +149,14 @@ def qa_proposal(chat_mdl, content, topn=3, custom_prompt=None):
     """
     if custom_prompt:
         template = PROMPT_JINJA_ENV.from_string(custom_prompt)
+        rendered_user = template.render(content=content, topn=topn)
+        msg = [{"role": "user", "content": rendered_user}]
+        sys_prompt = ""
     else:
-        template = PROMPT_JINJA_ENV.from_string(QUESTION_PROMPT_TEMPLATE)
+        sys_prompt = QUESTION_PROMPT_TEMPLATE
-    rendered_prompt = template.render(content=content, topn=topn)
+        msg = [{"role": "user", "content": f"## Text Content (topn: {topn})\n\n{content}"}]
-
+    _, msg = message_fit_in([{"role": "system", "content": sys_prompt}] + msg, getattr(chat_mdl, 'max_length', 8096))
-    msg = [{"role": "system", "content": rendered_prompt}, {"role": "user", "content": "Output: "}]
+    raw = chat_mdl.chat(sys_prompt, msg, {"temperature": 0.2})
-    _, msg = message_fit_in(msg, getattr(chat_mdl, 'max_length', 8096))
-    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)

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

@@ -2,23 +2,19 @@
 You are a text analyzer and knowledge extraction expert.
 
 ## Task
-Generate {{ topn }} question-answer pairs from the given text content.
+Generate question-answer pairs from the given text content.
 
 ## Requirements
-- Understand and summarize the text content, and generate the top {{ topn }} important question-answer pairs.
+- Understand and summarize the text content, then generate up to {{ 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 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.
+- If the text is too short or lacks substantive content, generate fewer pairs rather than padding.
+- Output question-answer pairs ONLY, no extra explanation or commentary.
 
 ## 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 }}