Update app.py

app.py

@@ -1,70 +1,153 @@
+import os
+import json
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+# =========================================
+# Configuration
+# =========================================
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+DEFAULT_MODEL = "openai/gpt-oss-20b"
 
-    messages = [{"role": "system", "content": system_message}]
+MODEL_OPTIONS = {
+    "Fast (Mistral 7B)": "mistralai/Mistral-7B-Instruct-v0.2",
+    "Balanced (GPT-OSS 20B)": "openai/gpt-oss-20b",
+}
 
-    messages.extend(history)
+PERSONA_PRESETS = {
+    "Balanced Assistant": "You are a helpful, intelligent, and clear AI assistant.",
+    "Creative": "You are a highly creative and imaginative assistant.",
+    "Precise": "You are a concise, factual, and analytical assistant.",
+    "Code Expert": "You are a senior software engineer who writes clean, well-explained code.",
+}
+
+# =========================================
+# Core Chat Logic
+# =========================================
+
+def stream_response(message, history, model_label, persona_label):
+    if not message:
+        yield history
+        return
+
+    model_name = MODEL_OPTIONS[model_label]
+    system_prompt = PERSONA_PRESETS[persona_label]
+
+    hf_token = os.environ.get("HF_TOKEN")
+    client = InferenceClient(model=model_name, token=hf_token)
+
+    messages = [{"role": "system", "content": system_prompt}]
+
+    for user_msg, assistant_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": assistant_msg})
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    history.append((message, ""))
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    partial_response = ""
+
+    for chunk in client.chat_completion(
+        messages=messages,
+        max_tokens=800,
+        temperature=0.7,
+        top_p=0.95,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
     ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+        if chunk.choices and chunk.choices[0].delta.content:
+            token = chunk.choices[0].delta.content
+            partial_response += token
+            history[-1] = (message, partial_response)
+            yield history
+
+# =========================================
+# Utility Functions
+# =========================================
+
+def clear_chat():
+    return []
+
+def export_chat(history):
+    return json.dumps(
+        [{"user": u, "assistant": a} for u, a in history],
+        indent=2
+    )
+
+# =========================================
+# UI Layout
+# =========================================
+
+with gr.Blocks(theme=gr.themes.Soft(), title="Omniscient IRIS") as demo:
+
+    gr.Markdown("## Omniscient IRIS — Public General AI")
+
+    with gr.Row():
+        with gr.Column(scale=3):
+            chatbot = gr.Chatbot(height=500)
+            msg = gr.Textbox(
+                placeholder="Type your message and press Enter...",
+                show_label=False
+            )
+
+            with gr.Row():
+                submit_btn = gr.Button("Send", variant="primary")
+                stop_btn = gr.Button("Stop")
+                clear_btn = gr.Button("Clear")
+
+        with gr.Column(scale=1):
+            model_selector = gr.Dropdown(
+                choices=list(MODEL_OPTIONS.keys()),
+                value="Balanced (GPT-OSS 20B)",
+                label="Model"
+            )
+
+            persona_selector = gr.Dropdown(
+                choices=list(PERSONA_PRESETS.keys()),
+                value="Balanced Assistant",
+                label="Persona"
+            )
+
+            export_btn = gr.Button("Export Conversation")
+
+    state = gr.State([])
+
+    # Submit events
+    submit_event = submit_btn.click(
+        stream_response,
+        inputs=[msg, state, model_selector, persona_selector],
+        outputs=chatbot,
+    )
+
+    msg.submit(
+        stream_response,
+        inputs=[msg, state, model_selector, persona_selector],
+        outputs=chatbot,
+    )
+
+    # Stop streaming
+    stop_btn.click(fn=None, cancels=[submit_event])
+
+    # Clear
+    clear_btn.click(
+        fn=clear_chat,
+        outputs=chatbot,
+    ).then(
+        lambda: [],
+        outputs=state
+    )
+
+    # Export
+    export_btn.click(
+        export_chat,
+        inputs=chatbot,
+        outputs=gr.File(label="Download JSON")
+    )
 
+# =========================================
+# Launch
+# =========================================
 
 if __name__ == "__main__":
+    demo.queue()
     demo.launch()