add custom prompt

app.py

@@ -1,7 +1,7 @@
 import os
 import gradio as gr
 import pinecone
-from llama_index import GPTIndexMemory, GPTPineconeIndex
+from llama_index import GPTIndexMemory, GPTPineconeIndex,QuestionAnswerPrompt
 from langchain.agents import Tool
 from langchain.chains.conversation.memory import ConversationBufferMemory
 from langchain import OpenAI
@@ -15,16 +15,31 @@ pinecone.init(api_key=PINECONE_API_KEY, environment="us-east1-gcp")
 pindex=pinecone.Index("sejarah")
 indexed_pinecone=GPTPineconeIndex([], pinecone_index=pindex)
 
+
+QA_PROMPT_TMPL = (
+    "Answer each question truthfully using the Malaysia's Form 1 History textbook data provided."
+    "Your answers should be concise and straight to the point.For questions that are open-ended, which require subjective judgment or opinion, you may not find a definitive answer in the textbook."
+    "However, you should still address the question's directive based on the data's context. Ideally, your answer should provide 3 points that support your response. You are encouraged to better provide positive suggestions for concepts that are less ethical.Please keep in mind that the scope of the data provided is limited to the content covered in the Malaysia's Form 1 History textbook."
+    "If you do not know the answer please say 'I don't know, Please rephrase the question'\n"
+    "---------------------\n Context:\n"
+    "{context_str}"
+    "\n---------------------\n"
+    "Given this information, please answer the question: {query_str}\n"
+)
+
+
+QA_PROMPT = QuestionAnswerPrompt(QA_PROMPT_TMPL)
+
 tools = [
     Tool(
         name = "GPT Index",
-        func=lambda q: str(indexed_pinecone.query(q)),
-        description="useful for when you want to answer questions about the author. The input to this tool should be a complete english sentence.",
+        func=lambda q: str(indexed_pinecone.query(q,text_qa_template=QA_PROMPT)),
+        description="Asking questions to Pandai AI",
         return_direct=True
     )
 ]
 memory = GPTIndexMemory(index=indexed_pinecone, memory_key="chat_history", query_kwargs={"response_mode": "compact"})
-llm=OpenAI(temperature=0, model_name="gpt-3.5-turbo")
+llm=OpenAI(temperature=0, model_name="text-davinci-003",max_tokens=1000)
 agent_chain = initialize_agent(tools, llm, agent="conversational-react-description", memory=memory, verbose=True)
 
 def predict(input, history=[]):
@@ -34,7 +49,7 @@ def predict(input, history=[]):
     # response = [response] 
     # return response, response
     return response, response
-#test edit
+
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot()
     state = gr.State([])