Update app.py

app.py

@@ -5,14 +5,14 @@ from langchain.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import Chroma
 from langchain.schema import Document
 
-# ✅ Load the Sentence Transformer Embedding Model
+# Load the Sentence Transformer Embedding Model
 model_name = "intfloat/e5-small"
 embedding_model = HuggingFaceEmbeddings(model_name=model_name)
 
-# ✅ Set up OpenAI API Key (Replace with your own API key)
+# Set up OpenAI API Key (Replace with your own API key)
 openai.api_key = os.getenv("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")  # Add in Hugging Face Secrets
 
-# ✅ Load ChromaDB with RunGalileo Dataset
+# Load ChromaDB with RunGalileo Dataset
 persist_directory = "./docs/chroma/"
 vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding_model)
 
@@ -27,10 +27,10 @@ embedding_model = HuggingFaceEmbeddings(model_name=model_name)
 # Define the ChromaDB persist directory
 persist_directory = "./docs/chroma/"
 
-# ✅ Load ChromaDB (or create if empty)
+#  Load ChromaDB (or create if empty)
 vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding_model)
 
-# ✅ Check if documents exist
+# Check if documents exist
 if vectordb._collection.count() == 0:
     print("⚠️ No documents found in ChromaDB. Re-indexing dataset...")
 
@@ -43,15 +43,15 @@ if vectordb._collection.count() == 0:
         Document(page_content="Smart thermostats improve energy efficiency through AI-based control.")
     ]
 
-    # ✅ Insert documents into ChromaDB
+    #  Insert documents into ChromaDB
     vectordb.add_documents(documents)
 
-    print("✅ Documents successfully indexed into ChromaDB.")
+    print(" Documents successfully indexed into ChromaDB.")
 else:
-    print(f"✅ ChromaDB contains {vectordb._collection.count()} documents.")
+    print(f" ChromaDB contains {vectordb._collection.count()} documents.")
 
 
-# ✅ Function to Retrieve Top-K Relevant Documents
+# Function to Retrieve Top-K Relevant Documents
 def retrieve_documents(question, k=5):
     """Retrieve top K relevant documents from ChromaDB"""
     docs = vectordb.similarity_search(question, k=k)
@@ -62,7 +62,7 @@ def retrieve_documents(question, k=5):
     return [doc.page_content for doc in docs]
 
 
-# ✅ Function to Generate AI Response
+#  Function to Generate AI Response
 import openai
 
 def generate_response(question, context):
@@ -89,14 +89,14 @@ def generate_response(question, context):
         return f"Error generating response: {str(e)}"
 
 
-# ✅ Full RAG Pipeline
+#  Full RAG Pipeline
 def rag_pipeline(question):
     retrieved_docs = retrieve_documents(question, k=5)
     context = " ".join(retrieved_docs)
     response = generate_response(question, context)
     return response, "\n\n".join(retrieved_docs)
 
-# ✅ Gradio UI Interface
+#  Gradio UI Interface
 iface = gr.Interface(
     fn=rag_pipeline,
     inputs=gr.Textbox(label="Enter your question"),