Update app.py

app.py

@@ -16,11 +16,9 @@ from langchain_text_splitters import CharacterTextSplitter
 import serpapi
 import requests
 
-# Initialize logging
+# Initialize logging and load environment variables
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
-
-# Load environment variables
 load_dotenv()
 
 # Define and validate API keys
@@ -31,7 +29,6 @@ if not openai_api_key or not serper_api_key:
     logger.error("API keys are not set properly.")
     raise ValueError("API keys for OpenAI and SERPER must be set in the .env file.")
 
-# Initialize OpenAI client
 openai.api_key = openai_api_key
 
 # Load knowledge base
@@ -53,7 +50,7 @@ knowledge_base = load_knowledge_base()
 embeddings = OpenAIEmbeddings()
 db = FAISS.from_documents(knowledge_base, embeddings)
 
-# Define search function for knowledge base
+# Define search functions
 def search_knowledge_base(query):
     try:
         output = db.similarity_search(query)
@@ -62,21 +59,14 @@ def search_knowledge_base(query):
         logger.error(f"Error searching knowledge base: {e}")
         return ["Error occurred during knowledge base search"]
 
-# SERPER API Google Search function
 def google_search(query):
     try:
         search_client = serpapi.Client(api_key=serper_api_key)
-        results = search_client.search({
-            "engine": "google",
-            "q": query,
-        })
+        results = search_client.search({"engine": "google", "q": query})
         snippets = [result["snippet"] for result in results.get("organic_results", [])]
         return snippets
-    except requests.exceptions.HTTPError as http_err:
-        logger.error(f"HTTP error occurred: {http_err}")
-        return ["HTTP error occurred during Google search"]
     except Exception as e:
-        logger.error(f"General Error: {e}")
+        logger.error(f"Error in Google search: {e}")
         return ["Error occurred during Google search"]
 
 # RAG response function
@@ -107,10 +97,10 @@ tools = [knowledge_base_tool, google_search_tool]
 
 # Create the prompt template
 prompt_message = """
-Act as an expert copywriter who specializes in creating compelling marketing copy using AI technologies.
-Engage in a friendly and informative conversation based on the knowledge base.
-Only proceed to create sales materials when the user explicitly requests it.
-Work together with the user to update the outcome of the sales material.
+Act as an expert copywriter who specializes in identifying and explaining trust builders for companies.
+Focus on finding and detailing trust builders for the specified company or topic.
+Organize the trust builders into categories such as Vision, Development, Benefit, Competence, Stability, and Relationship.
+Provide specific examples and data points when available to support each trust builder.
 """
 
 prompt_template = ChatPromptTemplate.from_messages([
@@ -140,7 +130,7 @@ agent = (
 agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
 
 # Streamlit app
-st.title("AI Copywriting Assistant")
+st.title("Trust Builders Finder")
 
 # Initialize chat history
 if 'chat_history' not in st.session_state:
@@ -152,7 +142,7 @@ for message in st.session_state.chat_history:
         st.markdown(message["content"])
 
 # Chat input
-if prompt := st.chat_input("Type your message here..."):
+if prompt := st.chat_input("Enter a company name or topic to find trust builders"):
     # Add user message to chat history
     st.session_state.chat_history.append({"role": "user", "content": prompt})
     
@@ -168,15 +158,12 @@ if prompt := st.chat_input("Type your message here..."):
         try:
             # Generate response using the agent executor
             output = agent_executor.invoke({
-                "input": prompt,
+                "input": f"{prompt}",
                 "chat_history": st.session_state.chat_history
             })
             full_response = output["output"]
             
-            # Display the response word by word
-            for chunk in full_response.split():
-                full_response += chunk + " "
-                message_placeholder.markdown(full_response + "▌")
+            # Display the response
             message_placeholder.markdown(full_response)
         except Exception as e:
             logger.error(f"Error generating response: {e}")