update

app.py

@@ -1,12 +1,15 @@
-from langchain import HuggingFaceHub, PromptTemplate
+from langchain import HuggingFaceHub, PromptTemplate, LLMChain
 from langchain.memory import ConversationBufferMemory
 from langchain.agents import AgentType, initialize_agent
 from langchain.chains import AgentChain
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 import gradio as gr
+from getpass import getpass
 import os
 
-os.environ["HUGGINGFACEHUB_API_TOKEN"] = "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"
+
+HUGGINGFACEHUB_API_TOKEN = getpass()
+os.environ["HUGGINGFACEHUB_API_TOKEN"] = HUGGINGFACEHUB_API_TOKEN
 
 template = """Question: {history}
 ------------------
@@ -19,19 +22,18 @@ memory = ConversationBufferMemory(max_capacity=1000)
 # Callbacks support token-wise streaming
 callbacks = [StreamingStdOutCallbackHandler()]
 # Instantiate the Hugging Face model
-llm = HuggingFaceHub(repo_id="gpt2")
+repo_id = "google/flan-t5-xl"  # Replace with the desired model
+llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature": 0, "max_length": 64})
 
 # Define the tools
 tools = []
 
-# Initialize the agent chain
-agent_chain = initialize_agent(tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)
-
-conversation = AgentChain(agent_chain, callbacks=callbacks, prompt=prompt)
+# Initialize the  chain
+llm_chain = LLMChain(prompt=prompt, llm=llm)
 
 # Define the Gradio interface
 def chatbot_interface(input_text):
-    response = conversation.predict(input_text)
+    response = llm_chain.run(input_text)
     return response
 
 # Define the Gradio app