Update app.py

app.py

@@ -1,66 +1,50 @@
-
+import spaces
 import gradio as gr
-from langchain.llms import HuggingFaceHub
 from huggingface_hub import InferenceClient
-from langchain.agents import load_tools, initialize_agent
-#from langchain.schema.agent import AgentType
-from langchain.agents import AgentType, initialize_agent,load_tools
-import wikipedia
-
 
-# Initialize Hugging Face inference client
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
 client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
-
-# Initialize the LLM using LangChain's HuggingFaceHub
-llm = HuggingFaceHub(
-    repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
-    huggingfacehub_api_token=HUGGINGFACE_API_TOKEN
-)
-# Load Wikipedia tool and initialize the agent
-tools = load_tools(["wikipedia"], llm=llm)
-agent = initialize_agent(
-    tools,
-    llm,
-    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
-    verbose=False
-)
-
+# llm = HuggingFaceHub(repo_id="meta-llama/Meta-Llama-3-8B-Instruct", model_kwargs={"temperature": 1})
 
 
 @spaces.GPU
-
 def respond(
-    message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p,
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
 ):
     messages = [{"role": "system", "content": system_message}]
-    for user, assistant in history:
-        if user:
-            messages.append({"role": "user", "content": user})
-        if assistant:
-            messages.append({"role": "assistant", "content": assistant})
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
     messages.append({"role": "user", "content": message})
 
-    # Use LangChain to obtain the model's response
-    chat_input = {
-        "messages": messages,
-        "max_tokens": max_tokens,
-        "temperature": temperature,
-        "top_p": top_p,
-        "stream": True,
-    }
+    response = ""
 
- # Get response from the agent using Wikipedia
-    wikipedia_response = agent.run(message)
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
 
-    # Use Hugging Face LLM to elaborate on the Wikipedia response
-    chat_input["messages"].append({"role": "assistant", "content": wikipedia_response})
-    response = wikipedia_response
-    for message in client.chat_completion(**chat_input):
-        token = message["choices"][0]["delta"]["content"]
         response += token
         yield response
 
-
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -79,5 +63,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.queue()
     demo.launch(share=True)