updated api key

app.py

@@ -1,63 +1,67 @@
+import os
 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)",
-        ),
-    ],
-)
+import whisper
+from gtts import gTTS
+import io
+import almlapi  # Assuming AL/ML has a Python API library
+
+# Set your AL/ML API key for authentication
+os.environ["ALML_API_KEY"] = "701b35863e6d4a7b81bdcad2e6f3c880"
+
+# Load the Whisper model for audio transcription
+model = whisper.load_model("base")
+
+# Function to process audio and interact with the AL/ML API
+def process_audio(file_path):
+    try:
+        # Load and transcribe audio using Whisper
+        audio = whisper.load_audio(file_path)
+        result = model.transcribe(audio)
+        text = result["text"]
+
+        # Call OpenAI o1 model via AL/ML API for problem-solving
+        response = almlapi.call_o1(
+            api_key=os.environ.get("ALML_API_KEY"),
+            prompt=text,
+            model="o1"  # Model name, adjust according to AL/ML documentation
+        )
+
+        # Extract the response message
+        response_message = response["generated_text"].strip()
 
+        # Convert response message to speech using gTTS
+        tts = gTTS(response_message)
+        response_audio_io = io.BytesIO()
+        tts.write_to_fp(response_audio_io)  # Save the audio to BytesIO object
+        response_audio_io.seek(0)
+
+        # Save the audio file
+        with open("response.mp3", "wb") as audio_file:
+            audio_file.write(response_audio_io.getvalue())
+
+        # Return the response text and audio file path
+        return response_message, "response.mp3"
+
+    except Exception as e:
+        # Handle exceptions
+        return f"An error occurred: {e}", None
+
+# Interface configurations (UI)
+title = "Voice-to-Voice AI Chatbot with AL/ML API"
+description = "Developed by [Adnan Tariq](https://www.linkedin.com/in/adnaantariq/) with ❤️"
+article = "### Instructions\n1. Upload an audio file.\n2. Wait for the transcription.\n3. Listen to the chatbot's response."
+
+# Gradio interface setup
+iface = gr.Interface(
+    fn=process_audio,
+    inputs=gr.Audio(type="filepath"),  # Upload audio via file path
+    outputs=[gr.Textbox(label="Response Text"), gr.Audio(label="Response Audio")],
+    live=True,
+    title=title,
+    description=description,
+    theme="dark",
+    article=article
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio app
+iface.launch()