Update app.py

app.py

@@ -20,18 +20,24 @@ llm = ChatGoogleGenerativeAI(model="gemini-pro",
 
 
 
-template = """You are a friendly chatbot called "CRETA" who give clear an well having a conversation with a human and you are created by suriya an AI Enthusiastic.
-provied_url_extracted_text:
-{extracted_text}
-provided document:
-{provided_docs}
-previous_chat:
+template = """
+You are CRETA, a friendly and knowledgeable chatbot created by Suriya, an AI enthusiast. You can access and understand the content from provided documents and websites to help answer questions.
+
+Previous Conversation:
 {chat_history}
+
+Provided Document Content:
+{provided_docs}
+
+Extracted URL Text:
+{extracted_text}
+
 Human: {human_input}
-Chatbot:"""
+Chatbot: """
 
 prompt = PromptTemplate(
-    input_variables=["chat_history", "human_input", "provided_docs","extracted_text"], template=template
+    input_variables=["chat_history", "human_input", "provided_docs", "extracted_text"], 
+    template=template
 )
 
 llm_chain = LLMChain(
@@ -44,22 +50,17 @@ llm_chain = LLMChain(
 previous_response = ""
 provided_docs = ""
 def conversational_chat(query):
-    global previous_response, provided_docs
-    for i in st.session_state['history']:
-        if i is not None:
-            previous_response += f"Human: {i[0]}\n Chatbot: {i[1]}"
-    docs = ""
-    for j in st.session_state["docs"]:
-        if j is not None:
-            docs += j
-    text = ""
-    for k in st.session_state["extracted_text"]:
-        if k is not None:
-            docs += k
+    global previous_response, provided_docs, extracted_text
+    previous_response = "".join([f"Human: {i[0]}\nChatbot: {i[1]}" for i in st.session_state['history'] if i is not None])
+    provided_docs = "".join([doc for doc in st.session_state["docs"] if doc is not None])
+    extracted_text = "".join([text for text in st.session_state["extracted_text"] if text is not None])
     
-    # ex_text = st.session_state["extracted_text"]
-    provided_docs = docs
-    result = llm_chain.predict(chat_history=previous_response, human_input=query, provided_docs=provided_docs,extracted_text=text)
+    result = llm_chain.predict(
+        chat_history=previous_response, 
+        human_input=query, 
+        provided_docs=provided_docs, 
+        extracted_text=extracted_text
+    )
     st.session_state['history'].append((query, result))
     return result