try deploy goog

.gitignore

@@ -1 +1,2 @@
-.env
+.env
+__pycache__

app.py

@@ -1,68 +1,47 @@
 import os
-import faster_whisper
 import gradio as gr
-from dotenv import load_dotenv
-from huggingface_hub import InferenceClient
-from groq import Groq
-
-# Load API key dari .env
-load_dotenv()
-GROQ_API_KEY = os.getenv("GROQ_API_KEY")
-
-if not GROQ_API_KEY:
-    raise ValueError("GROQ API NOT FOUND!")
-gclient = Groq(api_key=GROQ_API_KEY)
-
-
-def chat_with_groq(message):
-    """Handles conversation with Groq LLM."""
-    response = gclient.chat.completions.create(
-        model="gemma2-9b-it",
-        messages=[
-            {
-                "role": "system",
-                "content": """Anda adalah asisten medis yang membantu dokter dalam menyusun catatan medis dalam bentuk paragraf menggunakan bahasa Indonesia.""",
-            },
-            {"role": "user", "content": message},
-        ],
-        temperature=0.0,
-        max_tokens=248,
-    )
-    return response.choices[0].message.content  # Extract response text
+from google import genai
+from google.genai import types
+import asyncio
 
 
-def save_to_file(content, filename):
-    with open(filename, "w", encoding="utf-8") as file:
-        file.write(content)
-    return filename
+def audio_from_bytes(audio_file_path: str):
+    """Converts an audio file into Gemini-compatible format."""
+    try:
+        with open(audio_file_path, "rb") as f:
+            audio_data = f.read()
 
+        mime_type = "audio/mp3"  # Adjust based on your audio type
+        return types.Part.from_bytes(data=audio_data, mime_type=mime_type)
+
+    except FileNotFoundError:
+        return "Error: Audio file not found!"
+    except Exception as e:
+        return f"An error occurred: {e}"
 
-def transcribe_audio(audio_file):
-    """Transkripsi audio menggunakan Whisper tanpa koreksi model Hugging Face."""
-    # segments, _ = model.transcribe(audio_file)
-    # raw_transcription = " ".join(segment.text for segment in segments)
-    with open(audio_file, "rb") as file:
-        res = gclient.audio.transcriptions.create(
-            file=(audio_file, file.read()),
-            model="whisper-large-v3-turbo",
-            language="id",
-        )
-        print(res)
-        raw_transcription = res.text
-        soap_output, download_soap = generate_soap_summary(raw_transcription)
-        tags_output, download_tags = detect_medical_tags(raw_transcription)
-    return (
-        save_to_file(raw_transcription, "raw_transcription.txt"),
-        audio_file,
-        soap_output,
-        download_soap,
-        tags_output,
-        download_tags,
-    )
 
+def transcribe_and_summarize(audio_file):
+    """Processes audio with Gemini API and returns a SOAP summary."""
+    if audio_file is None:
+        return "No audio file uploaded."
 
-def generate_soap_summary(transcription_text):
-    template = """Buat ringkasan SOAP berdasarkan percakapan dokter dan pasien dalam format berikut:
+    # Ensure API Key is set
+    GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
+    if not GEMINI_API_KEY:
+        return "Error: GEMINI_API_KEY environment variable is missing."
+    asyncio.set_event_loop(asyncio.new_event_loop())
+
+    client = genai.Client(api_key=GEMINI_API_KEY)
+    model = "gemini-2.0-flash"
+
+    # Prepare the request
+    contents = [
+        types.Content(
+            role="user",
+            parts=[
+                types.Part.from_text(
+                    text="""Anda adalah asisten medis yang membantu dokter dalam menyusun catatan medis dalam bentuk paragraf menggunakan bahasa Indonesia.
+Buat ringkasan SOAP berdasarkan percakapan dokter dan pasien dalam format berikut:
 
     Subjective:
     ICD10:
@@ -70,66 +49,45 @@ def generate_soap_summary(transcription_text):
     Assessment:
     Plan:
 
-    ### Percakapan:
-    {dialogue}
-    """
-
-    soap = chat_with_groq(template.format(dialogue=transcription_text))
-    return soap, save_to_file(soap, "soap_summary.txt")
-
-
-def detect_medical_tags(transcription_text):
-    """Mendeteksi tags Diagnosis, Obat, Hasil Lab, dan Radiologi menggunakan model yang dipilih."""
-    template = """
-    Identifikasi dan berikan saran dalam bahasa Indonesia tindakan logis selanjutnya dalam format:
+Identifikasi dan berikan saran dalam bahasa Indonesia tindakan logis selanjutnya dalam format:
     ICD10:
     Obat:
     Laboratorium:
     Radiologi:
-
-    ### Percakapan:
-    {dialogue}
-    """
-    tags = chat_with_groq(template.format(dialogue=transcription_text))
-    return tags, save_to_file(tags, "medical_tags.txt")
-
-
-# Antarmuka Gradio
-with gr.Blocks(
-    title="AI-based Medical SOAP Summarization and Tag Detection with Whisper Large"
-) as app:
-    gr.Markdown("## Medical SOAP Summarization and Tag Detection with Whisper Large")
-
-    with gr.Row():
-        with gr.Column():
-            audio_input = gr.Audio("microphone", type="filepath", label="🎙️ Rekam Suara")
-            transcribe_button = gr.Button("🎧 Tulis Rekam Medis")
-
-        with gr.Column():
-            soap_output = gr.Textbox(label="📃 Hasil SOAP", lines=10, interactive=False)
-            tags_output = gr.Textbox(
-                label="🏷️ Hasil  Saran Tags ICD 10, Obat, Laboratorium, Radiologi",
-                lines=10,
-                interactive=False,
-            )
-            download_audio = gr.File(label="⬇️ Download Rekaman")
-            download_transcription = gr.File(label="⬇️ Download Transkripsi")
-            download_soap = gr.File(label="⬇️ Download SOAP")
-            download_tags = gr.File(label="⬇️ Download Tags")
-
-    # Tombol Transkripsi
-    transcribe_button.click(
-        transcribe_audio,
-        inputs=[audio_input],
-        outputs=[
-            download_transcription,
-            download_audio,
-            soap_output,
-            download_soap,
-            tags_output,
-            download_tags,
-        ],
+"""
+                ),
+                audio_from_bytes(audio_file),
+            ],
+        )
+    ]
+
+    generate_content_config = types.GenerateContentConfig(
+        temperature=0,
+        top_p=0.95,
+        top_k=40,
+        max_output_tokens=8192,
+        response_mime_type="text/plain",
     )
 
-# Jalankan aplikasi
-app.launch(share=True)
+    # Process the audio
+    response_text = ""
+    for chunk in client.models.generate_content_stream(
+        model=model,
+        contents=contents,
+        config=generate_content_config,
+    ):
+        response_text += chunk.text
+
+    return response_text
+
+
+# Gradio UI
+demo = gr.Interface(
+    fn=transcribe_and_summarize,
+    inputs=gr.Audio(type="filepath"),
+    outputs="text",
+    title="eH Medical Transcription",
+    description="Upload an Indonesian audio file of a doctor-patient conversation and get a SOAP summary.",
+)
+
+demo.launch()

requirements.txt

@@ -1,5 +1,3 @@
-faster_whisper==1.1.1
 gradio==5.17.0
-huggingface_hub==0.28.1
 python-dotenv==1.0.1
-groq
+google-genai