Update app.py

app.py

@@ -1,64 +1,107 @@
 import gradio as gr
+import asyncio
+import tempfile
+import edge_tts
 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")
+# -------------------------
+# === Fast Chat (Gemma) ===
+# -------------------------
+client_fast = InferenceClient("google/gemma-1.1-2b-it")
 
+def fast_chat(query):
+    messages = [{
+        "role": "user",
+        "content": f"[SYSTEM] You are ASSISTANT who answers questions in a short and concise manner. [USER] {query}"
+    }]
+    response = ""
+    for message in client_fast.chat_completion(messages, max_tokens=2048, stream=True):
+        token = message.choices[0].delta.content
+        response += token
+        yield response
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# -----------------------------
+# === Critical Thinker Chat ===
+# -----------------------------
+client_critical = InferenceClient("mistralai/Mistral-Nemo-Instruct-2407")
 
-    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 critical_thinker(query):
+    budget = 10
+    prompt = f"""[INST] [SYSTEM] You are a French robot full of hope and enthusiasm for future projects...
+<QUERY> {query} [/INST] [ASSISTANT]"""
+    stream = client_critical.text_generation(prompt, max_new_tokens=4096, stream=True, details=True, return_full_text=False)
+    output = ""
+    for response in stream:
+        output += response.token.text
+    return output
 
-    messages.append({"role": "user", "content": message})
+# -----------------
+# === Edge TTS ====
+# -----------------
+async def get_voices():
+    voices = await edge_tts.list_voices()
+    return {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}
 
-    response = ""
+async def text_to_speech(text, voice, rate, pitch):
+    if not text.strip():
+        return None, gr.Warning("Please enter text to convert.")
+    if not voice:
+        return None, gr.Warning("Please select a voice.")
+    
+    voice_short_name = voice.split(" - ")[0]
+    rate_str = f"{rate:+d}%"
+    pitch_str = f"{pitch:+d}Hz"
+    communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, pitch=pitch_str)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    return tmp_path, None
 
-    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 tts_interface(text, voice, rate, pitch):
+    audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch))
+    return audio, warning
 
-        response += token
-        yield response
+# -------------------------------
+# === Interface Gradio globale ==
+# -------------------------------
+async def main():
+    voices = await get_voices()
+
+    # Onglet 1 : Chat Rapide
+    with gr.Blocks() as fast_tab:
+        gr.Markdown("# 💬 Fast Chat")
+        gr.Interface(fn=fast_chat, inputs=gr.Textbox(label="Your message"), outputs="text")
+
+    # Onglet 2 : Chat Critique
+    with gr.Blocks() as critical_tab:
+        gr.Markdown("# 🤖 Critical Thinker")
+        gr.Interface(fn=critical_thinker, inputs=gr.Textbox(label="Your question"), outputs="text")
 
+    # Onglet 3 : TTS
+    with gr.Blocks() as tts_tab:
+        gr.Markdown("# 🔊 Text-to-Speech")
+        gr.Interface(
+            fn=tts_interface,
+            inputs=[
+                gr.Textbox(label="Text to Speak", lines=5),
+                gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice"),
+                gr.Slider(minimum=-50, maximum=50, value=0, label="Rate (%)"),
+                gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch (Hz)")
+            ],
+            outputs=[
+                gr.Audio(label="Generated Audio", type="filepath"),
+                gr.Markdown(label="Warning", visible=False)
+            ]
+        )
 
-"""
-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)",
-        ),
-    ],
-)
+    # Tabs Fusionnées
+    app = gr.TabbedInterface(
+        interface_list=[fast_tab, critical_tab, tts_tab],
+        tab_names=["Fast Chat", "Critical Thinker", "TTS"]
+    )
 
+    app.queue()
+    app.launch()
 
 if __name__ == "__main__":
-    demo.launch()
+    asyncio.run(main())