Update app.py

app.py

@@ -36,35 +36,118 @@ openai.api_key = openai_api_key
 
 # Load knowledge base
 def load_knowledge_base():
-    loader = TextLoader("./data_source/time_to_rethink_trust_book.md")
-    documents = loader.load()
-    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-    return text_splitter.split_documents(documents)
+    try:
+        loader = TextLoader("./data_source/time_to_rethink_trust_book.md")
+        documents = loader.load()
+        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+        return text_splitter.split_documents(documents)
+    except Exception as e:
+       
+
+
+
+
+You said:
+fix the erros and return me good code
+ChatGPT said:
+ChatGPT
+Sure! I'll provide a revised version of your Streamlit code with improvements, including better error handling, consistent configurations, and logging.
+
+Revised Streamlit Code
+python
+Copy code
+import logging
+import os
+from dotenv import load_dotenv
+import openai
+from langchain_openai import ChatOpenAI
+from langchain_community.vectorstores import FAISS
+from langchain_openai import OpenAIEmbeddings
+from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain.agents import tool, AgentExecutor
+from langchain.agents.output_parsers.openai_tools import OpenAIToolsAgentOutputParser
+from langchain.agents.format_scratchpad.openai_tools import format_to_openai_tool_messages
+from langchain_core.messages import AIMessage, HumanMessage
+from langchain_community.document_loaders import TextLoader
+from langchain_text_splitters import CharacterTextSplitter
+import serpapi
+import streamlit as st
+
+# Initialize logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Define and validate API keys
+openai_api_key = os.getenv("OPENAI_API_KEY")
+serper_api_key = os.getenv("SERPER_API_KEY")
+
+if not openai_api_key or not serper_api_key:
+    st.error("API keys for OpenAI and SERPER must be set in the .env file.")
+    logger.error("API keys for OpenAI and SERPER must be set in the .env file.")
+    st.stop()
+
+# Initialize OpenAI client
+openai.api_key = openai_api_key
+
+# Load knowledge base
+def load_knowledge_base():
+    try:
+        loader = TextLoader("./data_source/time_to_rethink_trust_book.md")
+        documents = loader.load()
+        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+        return text_splitter.split_documents(documents)
+    except Exception as e:
+        logger.error(f"Error loading knowledge base: {e}")
+        st.error("Error loading knowledge base.")
+        st.stop()
 
 knowledge_base = load_knowledge_base()
 
 # Initialize embeddings and FAISS index
-embeddings = OpenAIEmbeddings()
-db = FAISS.from_documents(knowledge_base, embeddings)
+try:
+    embeddings = OpenAIEmbeddings()
+    db = FAISS.from_documents(knowledge_base, embeddings)
+except Exception as e:
+    logger.error(f"Error initializing FAISS index: {e}")
+    st.error("Error initializing FAISS index.")
+    st.stop()
 
 # Define search function for knowledge base
 def search_knowledge_base(query):
-    return db.similarity_search(query)
+    try:
+        return db.similarity_search(query)
+    except Exception as e:
+        logger.error(f"Error searching knowledge base: {e}")
+        return ["Error occurred during knowledge base search"]
 
 # SERPER API Google Search function
 def google_search(query):
-    search_client = serpapi.Client(api_key=serper_api_key)
-    results = search_client.search({"engine": "google", "q": query})
-    return [result["snippet"] for result in results.get("organic_results", [])]
+    try:
+        search_client = serpapi.Client(api_key=serper_api_key)
+        results = search_client.search({"engine": "google", "q": query})
+        return [result["snippet"] for result in results.get("organic_results", [])]
+    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"Error during Google search: {e}")
+        return ["Error occurred during Google search"]
 
 # RAG response function
 def rag_response(query):
-    retrieved_docs = search_knowledge_base(query)
-    context = "\n".join(doc.page_content for doc in retrieved_docs)
-    prompt = f"Context:\n{context}\n\nQuestion: {query}\nAnswer:"
-    llm = ChatOpenAI(model="gpt-4o", temperature=0.5, api_key=openai_api_key)
-    response = llm.invoke(prompt)
-    return response.content
+    try:
+        retrieved_docs = search_knowledge_base(query)
+        context = "\n".join(doc.page_content for doc in retrieved_docs)
+        prompt = f"Context:\n{context}\n\nQuestion: {query}\nAnswer:"
+        llm = ChatOpenAI(model="gpt-4o", temperature=0.5, api_key=openai_api_key)
+        response = llm.invoke(prompt)
+        return response.content
+    except Exception as e:
+        logger.error(f"Error generating RAG response: {e}")
+        return "Error occurred during RAG response generation"
 
 # Define tools using LangChain's `tool` decorator
 @tool
@@ -112,37 +195,51 @@ prompt_template = ChatPromptTemplate.from_messages(
     ]
 )
 
-llm = ChatOpenAI(model="gpt-4o", temperature=0.5)
-llm_with_tools = llm.bind_tools(tools)
-
-agent = (
-    {
-        "input": lambda x: x["input"],
-        "agent_scratchpad": lambda x: format_to_openai_tool_messages(x["intermediate_steps"]),
-        "chat_history": lambda x: x["chat_history"],
-    }
-    | prompt_template
-    | llm_with_tools
-    | OpenAIToolsAgentOutputParser()
-)
+# Create Langchain Agent with specific model and temperature
+try:
+    llm = ChatOpenAI(model="gpt-4o", temperature=0.5)
+    llm_with_tools = llm.bind_tools(tools)
+except Exception as e:
+    logger.error(f"Error creating Langchain Agent: {e}")
+    st.error("Error creating Langchain Agent.")
+    st.stop()
 
-agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+# Define the agent pipeline to handle the conversation flow
+try:
+    agent = (
+        {
+            "input": lambda x: x["input"],
+            "agent_scratchpad": lambda x: format_to_openai_tool_messages(x["intermediate_steps"]),
+            "chat_history": lambda x: x["chat_history"],
+        }
+        | prompt_template
+        | llm_with_tools
+        | OpenAIToolsAgentOutputParser()
+    )
+    agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+except Exception as e:
+    logger.error(f"Error defining agent pipeline: {e}")
+    st.error("Error defining agent pipeline.")
+    st.stop()
 
 # Initialize chat history
 chat_history = []
 
 def chatbot_response(message, history):
-    output = agent_executor.invoke({"input": message, "chat_history": chat_history})
-    chat_history.extend(
-        [
-            HumanMessage(content=message),
-            AIMessage(content=output["output"]),
-        ]
-    )
-    return output["output"]
+    try:
+        output = agent_executor.invoke({"input": message, "chat_history": chat_history})
+        chat_history.extend(
+            [
+                HumanMessage(content=message),
+                AIMessage(content=output["output"]),
+            ]
+        )
+        return output["output"]
+    except Exception as e:
+        logger.error(f"Error generating chatbot response: {e}")
+        return "Error occurred during response generation"
 
 # Streamlit app
-st.title("Chatbot")
 
 user_input = st.text_input("You:", "")
 if st.button("Submit"):
@@ -150,4 +247,4 @@ if st.button("Submit"):
         response = chatbot_response(user_input, chat_history)
         st.write("AI:", response)
     else:
-        st.warning("Please enter a message.")
+        st.warning("Please enter a message."