Update app.py

app.py

@@ -1,64 +1,71 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import pipeline
+import uuid
 
-"""
-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")
+# Use Hugging Face hosted pipeline (won't need to load heavy model)
+generator = pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.1")
 
+# Session state store
+user_sessions = {}
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def get_session(session_id):
+    if session_id not in user_sessions:
+        user_sessions[session_id] = {"chat": []}
+    return user_sessions[session_id]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def build_prompt(history):
+    prompt = "You are a helpful assistant.\n"
+    for turn in history:
+        prompt += f"User: {turn[0]}\nAssistant: {turn[1]}\n"
+    return prompt
 
-    messages.append({"role": "user", "content": message})
+def chat_fn(user_input, session_id):
+    session = get_session(session_id)
+    history = session["chat"]
+    prompt = build_prompt(history + [[user_input, ""]]) + "Assistant:"
+    result = generator(prompt, max_new_tokens=128, do_sample=True, temperature=0.7)[0]["generated_text"]
+    reply = result[len(prompt):].strip().split("\n")[0]
+    history.append([user_input, reply])
+    return history, session_id
 
-    response = ""
+def upload_handler(file):
+    try:
+        content = file.read().decode("utf-8")
+        return content
+    except Exception as e:
+        return f"Error: {str(e)}"
 
-    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
+def code_viewer(code):
+    # Simulate code output
+    return "Code received. Execution is disabled on this free demo for safety."
 
-        response += token
-        yield response
+# Create unique session ID
+def create_session():
+    return str(uuid.uuid4())
 
+with gr.Blocks(title="Multi-Tool AI Chatbot") as demo:
+    session_id_state = gr.State(value=create_session())
 
-"""
-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)",
-        ),
-    ],
-)
+    with gr.Tab("Chatbot"):
+        chatbot = gr.Chatbot()
+        msg = gr.Textbox(label="Your message")
+        send = gr.Button("Send")
+        send.click(
+            fn=lambda msg, sid: chat_fn(msg, sid),
+            inputs=[msg, session_id_state],
+            outputs=[chatbot, session_id_state]
+        )
 
+    with gr.Tab("File Reader"):
+        file_input = gr.File(label="Upload .txt file", file_types=[".txt"])
+        file_output = gr.Textbox(label="File content")
+        file_input.change(upload_handler, inputs=file_input, outputs=file_output)
+
+    with gr.Tab("Code Viewer"):
+        code_input = gr.Code(language="python", label="Enter Python code")
+        code_output = gr.Textbox(label="Output")
+        run_btn = gr.Button("View Output")
+        run_btn.click(fn=code_viewer, inputs=code_input, outputs=code_output)
 
 if __name__ == "__main__":
     demo.launch()