fix

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 import os
-from langchain.callbacks.base import BaseCallbackHandler
+from callback_handler import QueueCallback
 from collections.abc import Generator
 from queue import Queue, Empty
 from threading import Thread
@@ -12,9 +12,6 @@ load_dotenv()
 
 from call_openai import call_openai
 
-from langchain import PromptTemplate
-from langchain.chains import LLMChain
-from langchain.chat_models import ChatOpenAI
 import pinecone
 from langchain.embeddings import OpenAIEmbeddings
 from langchain.vectorstores import Pinecone
@@ -25,37 +22,8 @@ PINECONE_API_KEY=os.environ["PINECONE_API_KEY"]
 PINECONE_ENV=os.environ["PINECONE_ENV"]
 PINECONE_INDEX=os.environ["PINECONE_INDEX"]
 
-class QueueCallback(BaseCallbackHandler):
-    """Callback handler for streaming LLM responses to a queue."""
-
-    def __init__(self, q):
-        self.q = q
-
-    def on_llm_new_token(self, token: str, **kwargs: any) -> None:
-        self.q.put(token)
-
-    def on_llm_end(self, *args, **kwargs: any) -> None:
-        return self.q.empty()
-
 # TOOL
 #####################################################################
-llm = ChatOpenAI(model_name="gpt-4-1106-preview", temperature=0)
-
-template = """
-You are an expert research assistant. You can access information about articles via your tool. 
-Use information ONLY from this tool. Do not invent or add any more knowladge, be strict for the articles.
-{instuction}
-User: {user}
---------
-{content}
-"""
-
-prompt = PromptTemplate(
-    input_variables=["instuction", "user", "content"],
-    template=template,
-)
-
-
 pinecone.init(
     api_key=PINECONE_API_KEY, 
     environment=PINECONE_ENV
@@ -124,9 +92,7 @@ def stream(input_text, history, user_prompt, topic, topk) -> Generator:
     job_done = object()
 
     # Create a funciton to call - this will run in a thread
-    def task():
-        #chain = LLMChain(llm=llm, prompt=prompt, callbacks=[QueueCallback(q)])
-        
+    def task():        
         tool_resp = query_tool(topic, topk, input_text)
 
         response = call_openai(