use only E5 multilingual small

app.py

@@ -14,64 +14,41 @@ import pickle
 import re
 import unicodedata
 
-
+# Setup Qdrant Client
 qdrant_client = QdrantClient(
     url=os.environ.get("Qdrant_url"),
     api_key=os.environ.get("Qdrant_api"),
 )
 
+# Airtable Config
 AIRTABLE_API_KEY = os.environ.get("airtable_api")
 BASE_ID = os.environ.get("airtable_baseid")
-TABLE_NAME = "Feedback_search"  # หรือเปลี่ยนชื่อให้ชัดเช่น 'Feedback'
+TABLE_NAME = "Feedback_search"
 api = Api(AIRTABLE_API_KEY)
 table = api.table(BASE_ID, TABLE_NAME)
 
-# โมเดลที่โหลดล่วงหน้า
-models = {
-    "E5 (intfloat/multilingual-e5-small)": SentenceTransformer('intfloat/multilingual-e5-small'),
-    "E5 large instruct (multilingual-e5-large-instruct)": SentenceTransformer("intfloat/multilingual-e5-large-instruct"),
-    "Kalm (KaLM-embedding-multilingual-mini-v1)": SentenceTransformer('HIT-TMG/KaLM-embedding-multilingual-mini-v1')
-}
-
-model_config = {
-    "E5 (intfloat/multilingual-e5-small)": {
-        "func": lambda query: models["E5 (intfloat/multilingual-e5-small)"].encode("query: " + query),
-        "collection": "product_E5",
-    },
-    "E5 large instruct (multilingual-e5-large-instruct)": {
-        "func": lambda query: models["E5 large instruct (multilingual-e5-large-instruct)"].encode(
-            "Instruct: Given a product search query, retrieve relevant product listings\nQuery: " + query, convert_to_tensor=False, normalize_embeddings=True),
-        "collection": "product_E5_large_instruct",
-    },
-    "Kalm (KaLM-embedding-multilingual-mini-v1)": {
-        "func": lambda query: models["Kalm (KaLM-embedding-multilingual-mini-v1)"].encode(query, normalize_embeddings=True),
-        "collection": "product_kalm",
-    }
-}
-
-# Global memory to hold feedback state
-latest_query_result = {"query": "", "result": "", "model": "", "raw_query": "", "time": ""}
+# Load model
+model = SentenceTransformer('intfloat/multilingual-e5-small')
+collection_name = "product_E5"
 
+# Load whitelist
 with open("keyword_whitelist.pkl", "rb") as f:
     keyword_whitelist = pickle.load(f)
 
+# Utils
 def normalize(text: str) -> str:
     text = unicodedata.normalize("NFC", text)
-    text = text.replace("เแ", "แ").replace("เเ", "แ")
-    return text.strip().lower()
+    return text.replace("เแ", "แ").replace("เเ", "แ").strip().lower()
 
 def smart_tokenize(text: str) -> list:
     tokens = word_tokenize(text.strip(), engine="newmm")
-    if not tokens or len("".join(tokens)) < len(text.strip()) * 0.5:
-        return [text.strip()]
-    return tokens
+    return tokens if tokens and len("".join(tokens)) >= len(text.strip()) * 0.5 else [text.strip()]
 
 def correct_query_merge_phrases(query: str, whitelist, threshold=80, max_ngram=3):
     query_norm = normalize(query)
     tokens = smart_tokenize(query_norm)
     corrected = []
     i = 0
-
     while i < len(tokens):
         matched = False
         for n in range(min(max_ngram, len(tokens) - i), 0, -1):
@@ -85,22 +62,17 @@ def correct_query_merge_phrases(query: str, whitelist, threshold=80, max_ngram=3
         if not matched:
             corrected.append(tokens[i])
             i += 1
+    return "".join([word for word in corrected if len(word) > 1 or word in whitelist])
 
-    # ✅ ตัดคำที่มีความยาว 1 ตัวอักษรและไม่ได้อยู่ใน whitelist
-    cleaned = [word for word in corrected if len(word) > 1 or word in whitelist]
-    return "".join(cleaned)
+# Global state
+latest_query_result = {"query": "", "result": "", "raw_query": "", "time": ""}
 
-# 🌟 Main search function
-def search_product(query, model_name):
+# Main Search
+def search_product(query):
     start_time = time.time()
-    if model_name not in model_config:
-        return "<p>❌ ไม่พบโมเดล</p>"
-
     latest_query_result["raw_query"] = query
-    corrected_query = correct_query_merge_phrases(query,keyword_whitelist)
-
-    query_embed = model_config[model_name]["func"](corrected_query)
-    collection_name = model_config[model_name]["collection"]
+    corrected_query = correct_query_merge_phrases(query, keyword_whitelist)
+    query_embed = model.encode("query: " + corrected_query)
 
     try:
         result = qdrant_client.query_points(
@@ -118,60 +90,52 @@ def search_product(query, model_name):
     if corrected_query != query:
         html_output += f"<p>🔧 แก้คำค้นจาก: <code>{query}</code> → <code>{corrected_query}</code></p>"
 
-    html_output += """
-    <div style="display: grid; grid-template-columns: repeat(auto-fill, minmax(220px, 1fr)); gap: 20px;">
-    """
+    html_output += '<div style="display: grid; grid-template-columns: repeat(auto-fill, minmax(220px, 1fr)); gap: 20px;">'
 
-    result_summary = ""
-    found = False
+    result_summary, found = "", False
     for res in result:
-      if res.score > 0.8:
-        found = True
-        name = res.payload.get("name", "ไม่ทราบชื่อสินค้��")
-        score = f"{res.score:.4f}"
-        img_url = res.payload.get("imageUrl", "")
-        price = res.payload.get("price", "ไม่ระบุ")
-        brand = res.payload.get("brand", "")
-
-        html_output += f"""
-        <div style="border: 1px solid #ddd; border-radius: 8px; padding: 10px; text-align: center; box-shadow: 1px 1px 5px rgba(0,0,0,0.1); background: #fff;">
-            <img src="{img_url}" style="width: 100%; max-height: 150px; object-fit: contain; border-radius: 4px;">
-            <div style="margin-top: 10px;">
-                <div style="font-weight: bold; font-size: 14px;">{name}</div>
-                <div style="color: gray; font-size: 12px;">{brand}</div>
-                <div style="color: green; margin: 4px 0;">฿{price}</div>
-                <div style="font-size: 12px; color: #555;">score: {score}</div>
+        if res.score > 0.8:
+            found = True
+            name = res.payload.get("name", "ไม่ทราบชื่อสินค้า")
+            score = f"{res.score:.4f}"
+            img_url = res.payload.get("imageUrl", "")
+            price = res.payload.get("price", "ไม่ระบุ")
+            brand = res.payload.get("brand", "")
+
+            html_output += f"""
+            <div style="border: 1px solid #ddd; border-radius: 8px; padding: 10px; text-align: center; box-shadow: 1px 1px 5px rgba(0,0,0,0.1); background: #fff;">
+                <img src="{img_url}" style="width: 100%; max-height: 150px; object-fit: contain; border-radius: 4px;">
+                <div style="margin-top: 10px;">
+                    <div style="font-weight: bold; font-size: 14px;">{name}</div>
+                    <div style="color: gray; font-size: 12px;">{brand}</div>
+                    <div style="color: green; margin: 4px 0;">฿{price}</div>
+                    <div style="font-size: 12px; color: #555;">score: {score}</div>
+                </div>
             </div>
-        </div>
-        """
-        result_summary += f"{name} (score: {score}) | "
+            """
+            result_summary += f"{name} (score: {score}) | "
 
     html_output += "</div>"
 
     if not found:
-      html_output += """
-      <div style="text-align: center; font-size: 18px; color: #a00; padding: 30px;">
-          ❌ ไม่พบสินค้าที่เกี่ยวข้องกับคำค้นนี้
-      </div>
-      """
-      return html_output
-
-    latest_query_result["query"] = corrected_query
-    latest_query_result["result"] = result_summary.strip()
-    latest_query_result["model"] = model_name
-    latest_query_result["time"] = elapsed
+        html_output += '<div style="text-align: center; font-size: 18px; color: #a00; padding: 30px;">❌ ไม่พบสินค้าที่เกี่ยวข้องกับคำค้นนี้</div>'
+        return html_output
 
-    return html_output
+    latest_query_result.update({
+        "query": corrected_query,
+        "result": result_summary.strip(),
+        "time": elapsed,
+    })
 
+    return html_output
 
-# 📝 Logging feedback
+# Feedback logging
 def log_feedback(feedback):
     try:
         now = datetime.now().strftime("%Y-%m-%d")
         table.create({
             "timestamp": now,
             "raw_query": latest_query_result["raw_query"],
-            "model": latest_query_result["model"],
             "query": latest_query_result["query"],
             "result": latest_query_result["result"],
             "time(second)": latest_query_result["time"],
@@ -181,20 +145,12 @@ def log_feedback(feedback):
     except Exception as e:
         return f"❌ Failed to save feedback: {str(e)}"
 
-
-# 🎨 Gradio UI
+# Gradio UI
 with gr.Blocks() as demo:
     gr.Markdown("## 🔎 Product Semantic Search (Vector Search + Qdrant)")
 
-    with gr.Row():
-        model_selector = gr.Dropdown(
-            choices=list(models.keys()),
-            label="เลือกโมเดล",
-            value="E5 (intfloat/multilingual-e5-small)"
-        )
-        query_input = gr.Textbox(label="พิมพ์คำค้นหา")
-
-    result_output = gr.HTML(label="📋 ผลลัพธ์")  # HTML แสดงผลลัพธ์พร้อมรูป
+    query_input = gr.Textbox(label="พิมพ์คำค้นหา")
+    result_output = gr.HTML(label="📋 ผลลัพธ์")
 
     with gr.Row():
         match_btn = gr.Button("✅ ตรง")
@@ -202,9 +158,9 @@ with gr.Blocks() as demo:
 
     feedback_status = gr.Textbox(label="📬 สถานะ Feedback")
 
-    query_input.submit(search_product, inputs=[query_input, model_selector], outputs=result_output)
+    query_input.submit(search_product, inputs=[query_input], outputs=result_output)
     match_btn.click(lambda: log_feedback("match"), outputs=feedback_status)
     not_match_btn.click(lambda: log_feedback("not_match"), outputs=feedback_status)
 
-# Run app
-demo.launch(share=True)
+# Run
+demo.launch(share=True)