Update appDeepseekCoder.py

appDeepseekCoder.py

@@ -1,33 +1,44 @@
-#Reference : https://medium.com/@tahreemrasul/building-a-chatbot-application-with-chainlit-and-langchain-3e86da0099a6
-#Reference : https://platform.deepseek.com/api-docs/api/create-chat-completion 
+from fastapi import FastAPI, Request
+from fastapi.responses import JSONResponse
+from langchain_openai import ChatOpenAI
 from langchain.chains import LLMChain
 from prompts import maths_assistant_prompt_template
 from langchain.memory.buffer import ConversationBufferMemory
-from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
-import torch
+from dotenv import load_dotenv
+import os
 import chainlit as cl
-#from chainlit import Button  # Import Button component
-# Load the model and tokenizer
-model_name = "deepseek-ai/deepseek-math-7b-instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
-model.generation_config = GenerationConfig.from_pretrained(model_name)
-model.generation_config.pad_token_id = model.generation_config.eos_token_id
+import uvicorn
 
+# Load environment variables from .env file
+load_dotenv()
 
-@cl.on_chat_start
-async def start_llm():
+api_key = os.getenv('OPENAI_API_KEY')
+print(f"api key is {api_key}")
+
+app = FastAPI()
 
-    conversation_memory = ConversationBufferMemory(memory_key="chat_history",
-                                                   max_len=50,
-                                                   return_messages=True,
-                                                   )
-    llm_chain = LLMChain(llm=model, prompt=maths_assistant_prompt_template, memory=conversation_memory)
+@app.on_event("startup")
+async def startup_event():
+    print("Initializing llm...")
+    llm = ChatOpenAI(model='gpt-4o-mini', temperature=0.5, api_key=api_key)
+    print("llm initialized!")
+    conversation_memory = ConversationBufferMemory(memory_key="chat_history", max_len=50, return_messages=True)
+    llm_chain = LLMChain(llm=llm, prompt=maths_assistant_prompt_template, memory=conversation_memory)
     cl.user_session.set("llm_chain", llm_chain)
 
-    #Send initial message to the user
-    #await cl.Message("What is your topic of interest?").send()
-    # Send initial message with selectable buttons
+@app.post("/query/")
+async def query_llm(request: Request):
+    data = await request.json()
+    message = data.get("message")
+    llm_chain = cl.user_session.get("llm_chain")
+    response = await llm_chain.ainvoke({
+        "chat_history": llm_chain.memory.load_memory_variables({})["chat_history"],
+        "question": message
+    }, callbacks=[cl.AsyncLangchainCallbackHandler()])
+    return JSONResponse(content={"response": response["text"]})
+
+@cl.on_chat_start
+async def on_chat_start():
     actions = [
         cl.Action(name="Probability", value="Probability", description="Select Quiz Topic!"),
         cl.Action(name="Linear Algebra", value="Linear Algebra", description="Select Quiz Topic!"),
@@ -36,57 +47,17 @@ async def start_llm():
     ]
     await cl.Message(content="**Pick a Topic and Let the Quiz Adventure Begin!** 🎉📚", actions=actions).send()
 
-
-
-@cl.on_message
-async def query_llm(message: cl.Message):
-    llm_chain = cl.user_session.get("llm_chain")
-    #selected_topic = cl.user_session.get("selected_topic", "probability")  # Default to probability if not set
-    print("Message being sent to the LLM is")
-    print(message.content)
-    #response = await llm_chain.ainvoke(message.content,
-    #                                 callbacks=[
-    #                                     cl.AsyncLangchainCallbackHandler()])
-
-    response = await llm_chain.ainvoke({
-        "chat_history": llm_chain.memory.load_memory_variables({})["chat_history"],
-        "question": message.content
-    }, callbacks=[
-        cl.AsyncLangchainCallbackHandler()
-    ])
-    await cl.Message(response["text"]).send()
-
-
-async def send_good_luck_message():
-    await cl.Message(content="Good luck! 🍀", align="bottom").send()
-  
-async def handle_topic_selection(action: cl.Action):
-    llm_chain = cl.user_session.get("llm_chain")
-    #cl.user_session.set("selected_topic", action.value)
-    #await cl.Message(content=f"Selected {action.value}").send()
-    response = await llm_chain.ainvoke({
-        "chat_history": llm_chain.memory.load_memory_variables({})["chat_history"],
-        "question": f"Quiz me on the topic {action.value}."
-    }, callbacks=[
-        cl.AsyncLangchainCallbackHandler()
-    ])
-    await cl.Message(response["text"]).send()
-
 @cl.action_callback("Linear Algebra")
-async def on_action(action: cl.Action):
-    await handle_topic_selection(action)
-
 @cl.action_callback("Probability")
-async def on_action(action: cl.Action):
-    await handle_topic_selection(action)
-
 @cl.action_callback("Accounts")
-async def on_action(action: cl.Action):
-    await handle_topic_selection(action)
-
 @cl.action_callback("Calculus")
 async def on_action(action: cl.Action):
-    await handle_topic_selection(action)
-
-
+    llm_chain = cl.user_session.get("llm_chain")
+    response = await llm_chain.ainvoke({
+        "chat_history": llm_chain.memory.load_memory_variables({})["chat_history"],
+        "question": f"Quiz me on the topic {action.value}."
+    }, callbacks=[cl.AsyncLangchainCallbackHandler()])
+    await cl.Message(response["text"]).send()
 
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)