adding refactored prompts

agent.py

@@ -14,10 +14,23 @@ from langchain.agents.react.base import DocstoreExplorer
 from langchain import LLMMathChain
 from typing import Union
 from langchain.memory import ConversationBufferWindowMemory
+import random
+from pydantic import Extra
+
+
+import promptlayer
+from langchain.callbacks import PromptLayerCallbackHandler
+
 
 load_dotenv()
 #os.environ = dotenv_values(".env")
 
+promptlayer.api_key = os.environ["PROPTLAYER_API_KEY"]
+
+assistant_name = os.environ["ASSISTANT_NAME"]
+topic = os.environ["TOPIC"]
+course_name = os.environ["COURSE_NAME"]
+institution = os.environ["INSTITUTION"]
 
 
 class CalculatorTool(BaseTool):
@@ -32,10 +45,30 @@ class CalculatorTool(BaseTool):
     def _run(self, question: str):
         return exec(question)
     
-    def _arun(self, value: Union[int, float]):
+    def _arun(self, question: str):
         raise NotImplementedError("This tool does not support async")
 
 
+class GetrandomTool(BaseTool):
+    name = "GetrandomTool"
+    
+    description = f"""
+    Useful for when you need to get any randomly chosen piece of document regarding {topic} 
+    from the study material. This is especially useful if the student wants tutoring,
+    that is, he/she wants {assistant_name} to ask him/her questions about the study material.
+    To use this tool, just call it with the constant text RANDOM.
+    """
+    class Config:
+        extra = Extra.allow
+
+    def _run(self, question: str):
+        rand_id = str(random.randint(0,self.index_max))
+        text = self.indexer.fetch([rand_id])["vectors"][rand_id]["metadata"]["context"]
+        
+        return text
+
+    def _arun(self, value: Union[int, float]):
+        raise NotImplementedError("This tool does not support async")
 
 class QMLAgent():
 
@@ -57,24 +90,32 @@ class QMLAgent():
             index=index, 
             top_k=os.environ["TOP_K"])
 
-        llm = ChatOpenAI(model_name=os.environ["CHAT_MODEL"])
+        llm = ChatOpenAI(model_name=os.environ["CHAT_MODEL"], callbacks=[PromptLayerCallbackHandler(pl_tags=["langchain"])])
 
         math_tool = CalculatorTool()
 
+        random_tool = GetrandomTool()
+        random_tool.indexer = index
+        random_tool.index_max = index.describe_index_stats()["total_vector_count"] 
+
+
         tools = [
             Tool(
                 name="Search",
                 func=retriever.get_relevant_documents,
-                description="You have to use this to search for knowledge about quantum computing and quantum machine learning.",
+                description=f"You have to use this to search for knowledge about {topic}.",
             ),
             Tool.from_function(
-                name="Match calculation",
+                name="Math calculation",
                 func=math_tool._run,
-                description="""
-            Useful for when you need to execute specific math calculations.
-            This tool is only for math calculations and nothing else.
-            Formulate the input as python code, always use explicit printing for results!.
-            """
+                description=math_tool.description
+                #return_direct=False
+
+            ),
+            Tool.from_function(
+                name="Random document",
+                func=random_tool._run,
+                description=random_tool.description
                 #return_direct=False
 
             ),
@@ -82,14 +123,17 @@ class QMLAgent():
 
         memory = ConversationBufferWindowMemory(k=os.environ["MEMORY_LENGTH"], memory_key="chat_history", return_messages=True)
 
-        PREFIX = """Assistant is called Quantie, a large language model with a knowledge base about Quantum Machine Learning (QML) trained for the Summer 2023 QML class at Frankfurt School of Finance and Management or short FS.
+        PREFIX = f"""Assistant is called {assistant_name}, a large language model with a knowledge base about {topic} trained for the {course_name} class at {institution}.
 
-Quantie is designed to be able to assist with a range of tasks specifically for the QML class, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Quantie is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.
+{assistant_name} is designed to be able to assist the students with a range of tasks specifically for the {course_name}, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, {assistant_name} is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.
 
-Quantie is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Quantie is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.
+{assistant_name} is willing to serve the students all the time, but always sticks to the academic context.
 
-Overall, Quantie is a powerful system that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Quantie is here to assist."""
+It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, {assistant_name} is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.
 
+Whether you need help with a specific question or just want to have a conversation about a particular topic, {assistant_name} is here to assist.
+"""
+#{assistant_name} is especially helpful in tutoring. If the student explicitly asks for tutoring, {assistant_name} can come up with relevant and interesting questions, pose it to the student and help him/her to discover the answer step by step. 
 
         self.agent_chain = initialize_agent(
             tools,