initial commit

src/streamlit_app.py

@@ -27,7 +27,7 @@ from pathlib import Path
 # === CONFIG ===
 # Set the API key
 client = openai.OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
-#openai.api_key = os.getenv("OPENAI_API_KEY")
+# openai.api_key = os.getenv("OPENAI_API_KEY")
 # REMEDI_PATH = "ReMeDi-base.json"
 BASE_DIR = Path(__file__).parent
 REMEDI_PATH = BASE_DIR / "ReMeDi-base.json"
@@ -40,11 +40,13 @@ if not REMEDI_PATH.exists():
 with open(REMEDI_PATH, "r", encoding="utf-8") as f:
     data = json.load(f)
 
+
 # === LOAD MODEL ===
 @st.cache_resource
 def load_model():
     return SentenceTransformer("all-MiniLM-L6-v2")
-    #return model
+    # return model
+
 
 @st.cache_resource
 def load_data():
@@ -53,20 +55,22 @@ def load_data():
     dialogue_pairs = []
     for conversation in data:
         turns = conversation["information"]
-        for i in range(len(turns)-1):
-            if turns[i]["role"] == "patient" and turns[i+1]["role"] == "doctor":
+        for i in range(len(turns) - 1):
+            if turns[i]["role"] == "patient" and turns[i + 1]["role"] == "doctor":
                 dialogue_pairs.append({
                     "patient": turns[i]["sentence"],
-                    "doctor": turns[i+1]["sentence"]
+                    "doctor": turns[i + 1]["sentence"]
                 })
     return dialogue_pairs
 
+
 @st.cache_data
 def build_embeddings(dialogue_pairs, _model):
     patient_sentences = [pair["patient"] for pair in dialogue_pairs]
     embeddings = _model.encode(patient_sentences, convert_to_tensor=True)
     return embeddings
 
+
 # === TRANSLATE USING GPT ===
 def translate_to_english(chinese_text):
     prompt = f"Translate the following Chinese medical response to English:\n\n{chinese_text}"
@@ -78,10 +82,11 @@ def translate_to_english(chinese_text):
         )
         return response.choices[0].message.content
 
-        #return response.choices[0].message["content"].strip()
+        # return response.choices[0].message["content"].strip()
     except Exception as e:
         return f"Translation failed: {str(e)}"
 
+
 def gpt_direct_response(user_input):
     prompt = f"You are a knowledgeable and compassionate medical assistant. Answer the following patient question clearly and concisely:\n\n{user_input}"
     try:
@@ -99,6 +104,8 @@ def gpt_direct_response(user_input):
 def chatbot_response(user_input, _model, dialogue_pairs, patient_embeddings, top_k=1):
     user_embedding = _model.encode(user_input, convert_to_tensor=True)
     similarities = util.cos_sim(user_embedding, patient_embeddings)[0]
+    top_score, top_idx = torch.topk(similarities, k=1)
+    top_score = top_score.item()
     top_idx = torch.topk(similarities, k=top_k).indices[0].item()
 
     match = dialogue_pairs[top_idx]
@@ -108,8 +115,10 @@ def chatbot_response(user_input, _model, dialogue_pairs, patient_embeddings, top
         "matched_question": match["patient"],
         "original_response": match["doctor"],
         "translated_response": translated
+        # "similarity_score": top_score
     }
 
+
 # === MAIN APP ===
 st.set_page_config(page_title="Dr_Q_bot", layout="centered")
 st.title("🩺 Dr_Q_bot - Medical Chatbot")
@@ -128,6 +137,12 @@ if st.button("Submit") and user_input:
         result = chatbot_response(user_input, model, dialogue_pairs, patient_embeddings)
         gpt_response = gpt_direct_response(user_input)
 
+        st.markdown("## ✅ GPT-4 Doctor's Response")
+        st.success(gpt_response)
+
+        # if torch.max(similarities).item() < 0.4:
+
+        st.markdown("## 🔁 Example Historical Dialogue")
         st.markdown("### 🧑‍⚕️ Closest Patient Question")
         st.write(result["matched_question"])
 
@@ -136,10 +151,14 @@ if st.button("Submit") and user_input:
 
         st.markdown("### 🌐 Translated Doctor Response (English)")
         st.success(result["translated_response"])
+        # else:
+        #    st.warning("No close match found in dataset. Using GPT response only.")
 
-        st.markdown("### 💬 GPT Doctor Response (AI-generated)")
-        st.info(gpt_response)
+        # st.markdown("### 💬 GPT Doctor Response (AI-generated)")
+        # st.info(gpt_response)
 
+        # Skip dataset result
 
         st.markdown("---")
-        st.warning("This chatbot uses real dialogue data for research and educational use only. Not a substitute for professional medical advice.")
+        st.warning(
+            "This chatbot uses real dialogue data for research and educational use only. Not a substitute for professional medical advice.")