Update app.py

app.py

@@ -1,120 +1,64 @@
-# import gradio as gr
-# from huggingface_hub import InferenceClient
-
-# """
-# 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("HuggingFaceH4/zephyr-7b-beta")
-
-
-# def respond(
-#     message,
-#     history: list[tuple[str, str]],
-#     system_message,
-#     max_tokens,
-#     temperature,
-#     top_p,
-# ):
-#     messages = [{"role": "system", "content": system_message}]
-
-#     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})
-
-#     response = ""
-
-#     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
-
-#         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=[
-#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-#         gr.Slider(
-#             minimum=0.1,
-#             maximum=1.0,
-#             value=0.95,
-#             step=0.05,
-#             label="Top-p (nucleus sampling)",
-#         ),
-#     ],
-# )
-
-
-# if __name__ == "__main__":
-#     demo.launch()
-
-# from fastapi import FastAPI, HTTPException
-# from fastapi.responses import JSONResponse
-# import ollama
-
-# app = FastAPI()
-
-# MODEL_NAME = "llama3.2"
-
-# @app.post("/")
-# async def query_model(request: dict):
-#     """Queries the model with user input."""
-#     user_input = request.get("user_input", "")
-#     prompt = f"You are a helpful assistant. Here is the user question: {user_input}"
-
-#     try:
-#         # Directly using ollama to send the message and get the response.
-#         response = ollama.chat(MODEL_NAME, messages=[{"role": "user", "content": prompt}])
-#         assistant_response = response['text']  # Assuming the response contains 'text' key
-#         return JSONResponse(content={"assistant_response": assistant_response})
-#     except Exception as e:
-#         return JSONResponse(content={"error": str(e)}, status_code=500)
-
-
-from fastapi import FastAPI
-from fastapi.responses import JSONResponse
+import gradio as gr
 from huggingface_hub import InferenceClient
 
-app = FastAPI()
+"""
+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("HuggingFaceH4/zephyr-7b-beta")
 
-# Hardcoded parameters
-SYSTEM_MESSAGE = "You are a friendly Chatbot."
-MAX_TOKENS = 512
-TEMPERATURE = 0.7
-TOP_P = 0.95
 
-@app.post("/")
-async def chat(request: dict):
-    user_input = request.get("user_input", "")
-    prompt = f"You are a helpful assistant. Here is the user question: {user_input}"
-    
-    messages = [
-        {"role": "system", "content": SYSTEM_MESSAGE},
-        {"role": "user", "content": prompt},
-    ]
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
 
-    response = client.chat_completion(
-        messages,
-        max_tokens=MAX_TOKENS,
-        temperature=TEMPERATURE,
-        top_p=TOP_P,
-    ).choices[0].message.content
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
-    return JSONResponse(content={"assistant_response": response})
+    messages.append({"role": "user", "content": message})
 
+    response = ""
+
+    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
+
+        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=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()