Update app.py

app.py

@@ -1,10 +1,35 @@
 import gradio as gr
-import os
+from langchain import PromptTemplate, LLMChain
+from langchain.llms import GPT4All
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
-os.system("wget https://huggingface.co/TheBloke/Nous-Hermes-13B-GGML/resolve/main/nous-hermes-13b.ggmlv3.q4_0.bin")
 
-def greet(name):
-    return "Hello " + name + "!!"
+def func(prompt):
+        
+    template = """Question: {question}
+    
+    Answer: Let's think step by step."""
+    
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+    
+    local_path = (
+        "https://tommy24-llm.hf.space/file=nous-hermes-13b.ggmlv3.q4_0.bin"  # replace with your desired local file path
+    )
+    
+    # Callbacks support token-wise streaming
+    callbacks = [StreamingStdOutCallbackHandler()]
+    
+    # Verbose is required to pass to the callback manager
+    llm = GPT4All(model=local_path, callbacks=callbacks, verbose=True)
+    
+    # If you want to use a custom model add the backend parameter
+    # Check https://docs.gpt4all.io/gpt4all_python.html for supported backends
+    llm = GPT4All(model=local_path, backend="gptj", callbacks=callbacks, verbose=True)
+    
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    question = prompt
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+    return llm_chain.run(question)
+
+iface = gr.Interface(fn=func, inputs="text", outputs="text")
 iface.launch()