Update app.py

app.py

@@ -24,30 +24,7 @@ SERVICE_ACCOUNT_FILE = r"C:\Users\bhagy\AI\credentials.json"
 
 csv_file_path = r"C:\Users\bhagy\OneDrive\Desktop\INFOSYS PROJECT\900_products_dataset.csv"
 
-
-class CustomEmbeddingFunction:
-    def __init__(self, model_name="sentence-transformers/all-MiniLM-L6-v2"):
-        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
-        self.model = AutoModel.from_pretrained(model_name)
-
-    def __call__(self, text):
-        inputs = self.tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
-        with torch.no_grad():
-            outputs = self.model(**inputs)
-        embeddings = outputs.last_hidden_state.mean(dim=1).squeeze().numpy()
-        return embeddings
-
-# Initialize components
-sentiment_pipeline = pipeline("sentiment-analysis")
-chroma_client = Client(Settings(persist_directory="chromadb_storage"))
-embedding_fn = CustomEmbeddingFunction()
-collection_name = "crm_data"
-
-try:
-    collection = chroma_client.get_collection(collection_name)
-except Exception:
-    collection = chroma_client.create_collection(collection_name)
-
+# sentiment_pipeline = pipeline("sentiment-analysis")
 def get_google_sheets_service():
     creds = Credentials.from_service_account_file(
         SERVICE_ACCOUNT_FILE,
@@ -176,7 +153,27 @@ def query_crm_data_with_context(prompt, top_k=3):
         return ["Error in querying recommendations."]
 
 
+class CustomEmbeddingFunction:
+    def __init__(self, model_name="sentence-transformers/all-MiniLM-L6-v2"):
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModel.from_pretrained(model_name)
 
+    def __call__(self, text):
+        inputs = self.tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+        with torch.no_grad():
+            outputs = self.model(**inputs)
+        embeddings = outputs.last_hidden_state.mean(dim=1).squeeze().numpy()
+        return embeddings
+
+chroma_client = Client(Settings(persist_directory="chromadb_storage"))
+embedding_fn = CustomEmbeddingFunction()
+collection_name = "crm_data"
+
+try:
+    collection = chroma_client.get_collection(collection_name)
+except Exception:
+    collection = chroma_client.create_collection(collection_name)
+    
 sentence_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
 faiss_index = faiss.IndexFlatL2(384)