true collection

app.py

@@ -5,63 +5,63 @@ import pandas as pd
 from sentence_transformers import SentenceTransformer
 from qdrant_client import QdrantClient
 from qdrant_client.models import Filter, FieldCondition, MatchValue
-
 import os
-from qdrant_client import QdrantClient
+
 
 qdrant_client = QdrantClient(
     url=os.environ.get("Qdrant_url"),
-    api_key=os.environ.get("Qdrant_api")
+    api_key=os.environ.get("Qdrant_api"),
 )
 
 # โมเดลที่โหลดล่วงหน้า
 models = {
     "E5 (intfloat/multilingual-e5-small)": SentenceTransformer('intfloat/multilingual-e5-small'),
-    "MiniLM (paraphrase-multilingual-MiniLM-L12-v2)": SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2'),
-    "DistilUSE (distiluse-base-multilingual-cased-v1)": SentenceTransformer('sentence-transformers/distiluse-base-multilingual-cased-v1')
+    "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": ""}
 
-
-# 🔍 Search Functions
-def search_with_e5(query):
-    embed = models["E5 (intfloat/multilingual-e5-small)"].encode("query: " + query)
-    return embed
-
-def search_with_minilm(query):
-    embed = models["MiniLM (paraphrase-multilingual-MiniLM-L12-v2)"].encode(query)
-    return embed
-
-def search_with_distiluse(query):
-    embed = models["DistilUSE (distiluse-base-multilingual-cased-v1)"].encode(query)
-    return embed
-
-
 # 🌟 Main search function
 def search_product(query, model_name):
     start_time = time.time()
 
-    # Choose encoder function
-    if "E5" in model_name:
-        query_embed = search_with_e5(query)
-    elif "MiniLM" in model_name:
-        query_embed = search_with_minilm(query)
-    elif "DistilUSE" in model_name:
-        query_embed = search_with_distiluse(query)
-    else:
+    if model_name not in model_config:
         return "❌ ไม่พบโมเดล"
 
+    query_embed = model_config[model_name]["func"](query)
+    collection_name = model_config[model_name]["collection"]
+    
+
     # Query Qdrant
-    result = qdrant_client.query_points(
-        collection_name="product_E5",
-        query=query_embed.tolist(),
-        with_payload=True,
-        query_filter=Filter(
-            must=[FieldCondition(key="type", match=MatchValue(value="product"))]
-        )
-    ).points
+    try:
+      result = qdrant_client.query_points(
+          collection_name=collection_name,
+          query=query_embed.tolist(),
+          with_payload=True,
+          query_filter=Filter(
+              must=[FieldCondition(key="type", match=MatchValue(value="product"))]
+          )
+      ).points
+    except Exception as e:
+      return f"❌ Qdrant error: {str(e)}"
 
     elapsed = time.time() - start_time