Update app.py

app.py

@@ -2,6 +2,7 @@ import os
 import time
 import base64
 import requests
+from collections import defaultdict
 from typing import List, Dict, Tuple, Optional
 
 import gradio as gr
@@ -285,6 +286,50 @@ def log_event(data: Dict):
         print("GSheet log exception:", e)
 
 
+# ===== Reference Formatting Helper =====
+def format_references(
+    rag_chunks: List[Dict], max_files: int = 2, max_sections_per_file: int = 3
+) -> str:
+    """
+    根据当前使用的 rag_chunks，生成一个简短的 reference 列表：
+    - 按文件名分组
+    - 每个文件列出若干个 section
+
+    期望 rag_engine 在每个 chunk 中填入:
+        chunk["source_file"]  -> 文件名
+        chunk["section"]      -> 段落 / section 描述（如 "Section 3.2 – Risk taxonomy"）
+    若未提供，将回退为 "Unknown file" / "Related section"。
+    """
+    if not rag_chunks:
+        return ""
+
+    refs_by_file: Dict[str, List[str]] = defaultdict(list)
+
+    for chunk in rag_chunks:
+        file_name = chunk.get("source_file") or "Unknown file"
+        section = chunk.get("section") or "Related section"
+        if section not in refs_by_file[file_name]:
+            refs_by_file[file_name].append(section)
+
+    if not refs_by_file:
+        return ""
+
+    lines = ["**References (RAG context used):**"]
+    for i, (file_name, sections) in enumerate(refs_by_file.items()):
+        if i >= max_files:
+            break
+        short_sections = sections[:max_sections_per_file]
+        if short_sections:
+            section_str = "; ".join(short_sections)
+            lines.append(f"- *{file_name}* — {section_str}")
+        else:
+            lines.append(f"- *{file_name}*")
+
+    if len(lines) == 1:
+        return ""
+    return "\n".join(lines)
+
+
 # ================== Gradio App ==================
 with gr.Blocks(
     title="Clare – Hanbridge AI Teaching Assistant", css=CUSTOM_CSS
@@ -299,6 +344,7 @@ with gr.Blocks(
     # 用户状态（登录）
     user_name_state = gr.State("")
     user_id_state = gr.State("")
+
     # --- Header ---
     with gr.Row(elem_classes="header-container"):
         with gr.Column(scale=3):
@@ -422,7 +468,6 @@ with gr.Blocks(
                 """
             )
 
-
         # === Center Main ===
         with gr.Column(scale=3):
 
@@ -504,7 +549,6 @@ with gr.Blocks(
                         )
                         session_status = gr.Markdown(visible=False)
 
-
         # === Right Sidebar ===
         with gr.Column(scale=1, min_width=180):
             with gr.Group(elem_classes="login-panel"):
@@ -803,6 +847,16 @@ with gr.Blocks(
         end_ts = time.time()
         latency_ms = (end_ts - start_ts) * 1000.0
 
+        # === 在这里附上 References ===
+        ref_text = format_references(rag_context)
+        if ref_text and new_history:
+            last_user, last_assistant = new_history[-1]
+            if "References (RAG context used):" not in (last_assistant or ""):
+                last_assistant = f"{last_assistant}\n\n{ref_text}"
+                new_history[-1] = [last_user, last_assistant]
+                answer = last_assistant  # 同步给日志
+        # ==============================
+
         student_id = user_id_val or "ANON"
         experiment_id = "RESP_AI_W10"
 
@@ -872,33 +926,32 @@ with gr.Blocks(
             )
 
         quiz_instruction = (
-        "We are running a short micro-quiz session based ONLY on **Module 10 – "
-        "Responsible AI (Alto, 2024, Chapter 12)** and the pre-loaded materials.\n\n"
-        "Step 1 – Before asking any content question:\n"
-        "• First ask me which quiz style I prefer right now:\n"
-        "  - (1) Multiple-choice questions\n"
-        "  - (2) Short-answer / open-ended questions\n"
-        "• Ask me explicitly: \"Which quiz style do you prefer now: 1) Multiple-choice or 2) Short-answer? "
-        "Please reply with 1 or 2.\"\n"
-        "• Do NOT start a content question until I have answered 1 or 2.\n\n"
-        "Step 2 – After I choose the style:\n"
-        "• If I choose 1 (multiple-choice):\n"
-        "  - Ask ONE multiple-choice question at a time, based on Module 10 concepts "
-        "(Responsible AI definition, risk types, mitigation layers, EU AI Act, etc.).\n"
-        "  - Provide 3–4 options (A, B, C, D) and make only one option clearly correct.\n"
-        "• If I choose 2 (short-answer):\n"
-        "  - Ask ONE short-answer question at a time, also based on Module 10 concepts.\n"
-        "  - Do NOT show the answer when you ask the question.\n\n"
-        "Step 3 – For each answer I give:\n"
-        "• Grade my answer (correct / partially correct / incorrect).\n"
-        "• Give a brief explanation and the correct answer.\n"
-        "• Then ask if I want another question of the SAME style.\n"
-        "• Continue this pattern until I explicitly say to stop.\n\n"
-        "Please start by asking me which quiz style I prefer (1 = multiple-choice, 2 = short-answer). "
-        "Do not ask any content question before I choose."
+            "We are running a short micro-quiz session based ONLY on **Module 10 – "
+            "Responsible AI (Alto, 2024, Chapter 12)** and the pre-loaded materials.\n\n"
+            "Step 1 – Before asking any content question:\n"
+            "• First ask me which quiz style I prefer right now:\n"
+            "  - (1) Multiple-choice questions\n"
+            "  - (2) Short-answer / open-ended questions\n"
+            "• Ask me explicitly: \"Which quiz style do you prefer now: 1) Multiple-choice or 2) Short-answer? "
+            "Please reply with 1 or 2.\"\n"
+            "• Do NOT start a content question until I have answered 1 or 2.\n\n"
+            "Step 2 – After I choose the style:\n"
+            "• If I choose 1 (multiple-choice):\n"
+            "  - Ask ONE multiple-choice question at a time, based on Module 10 concepts "
+            "(Responsible AI definition, risk types, mitigation layers, EU AI Act, etc.).\n"
+            "  - Provide 3–4 options (A, B, C, D) and make only one option clearly correct.\n"
+            "• If I choose 2 (short-answer):\n"
+            "  - Ask ONE short-answer question at a time, also based on Module 10 concepts.\n"
+            "  - Do NOT show the answer when you ask the question.\n\n"
+            "Step 3 – For each answer I give:\n"
+            "• Grade my answer (correct / partially correct / incorrect).\n"
+            "• Give a brief explanation and the correct answer.\n"
+            "• Then ask if I want another question of the SAME style.\n"
+            "• Continue this pattern until I explicitly say to stop.\n\n"
+            "Please start by asking me which quiz style I prefer (1 = multiple-choice, 2 = short-answer). "
+            "Do not ask any content question before I choose."
         )
 
-
         resolved_lang = lang_pref
 
         start_ts = time.time()