Update app.py

app.py

@@ -1,3 +1,4 @@
+
 import gradio as gr
 import openai
 from openai import OpenAI
@@ -7,21 +8,17 @@ from gtts import gTTS
 from faster_whisper import WhisperModel
 import subprocess
 import shutil
-import datetime
-import json
-import csv
-
-# === Clean /tmp at startup ===
-TMP_DIR = "/tmp"
-for sub in os.listdir(TMP_DIR):
-    sub_path = os.path.join(TMP_DIR, sub)
-    try:
-        if os.path.isfile(sub_path) or os.path.islink(sub_path):
-            os.unlink(sub_path)
-        elif os.path.isdir(sub_path):
-            shutil.rmtree(sub_path)
-    except Exception as e:
-        print(f"Failed to delete {sub_path}. Reason: {e}")
+from datetime import datetime
+from sqlmodel import SQLModel, Field, create_engine, Session, select
+
+# === Clean safe app-generated temp files ===
+import glob
+for pattern in ["/tmp/*.wav", "/tmp/*.mp3"]:
+    for filepath in glob.glob(pattern):
+        try:
+            os.remove(filepath)
+        except Exception as e:
+            print(f"Could not delete {filepath}: {e}")
 
 # === Environment Setup ===
 os.environ["HF_HOME"] = "/tmp/hf"
@@ -29,40 +26,48 @@ os.environ["TRANSFORMERS_CACHE"] = "/tmp/hf"
 os.environ["XDG_CACHE_HOME"] = "/tmp/hf"
 os.environ["MPLCONFIGDIR"] = "/tmp/matplotlib"
 openai.api_key = os.getenv("OPENAI_API_KEY")
+client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 
-# === Language Codes for GPT + TTS ===
+# === Language Codes ===
 LANG_CODES = {
-    "English": "en",
-    "Spanish": "es",
-    "Hindi": "hi",
-    "French": "fr",
-    "German": "de",
-    "Arabic": "ar",
-    "Chinese": "zh",
-    "Portuguese": "pt",
-    "Japanese": "ja",
-    "Korean": "ko"
+    "English": "en", "Spanish": "es", "Hindi": "hi", "French": "fr", "German": "de",
+    "Arabic": "ar", "Chinese": "zh", "Portuguese": "pt", "Japanese": "ja", "Korean": "ko"
 }
 
-# === Load Whisper Model ===
+# === SQLModel Setup ===
+class SessionEntry(SQLModel, table=True):
+    id: int = Field(default=None, primary_key=True)
+    timestamp: str
+    transcript: str
+    feedback: str
+    language: str
+
+db_path = "chatter_sessions.db"
+engine = create_engine(f"sqlite:///{db_path}")
+SQLModel.metadata.create_all(engine)
+
+def save_to_db(transcript, feedback, language):
+    session = Session(engine)
+    entry = SessionEntry(
+        timestamp=datetime.now().strftime("%Y-%m-%d %H:%M"),
+        transcript=transcript,
+        feedback=feedback,
+        language=language
+    )
+    session.add(entry)
+    session.commit()
+    session.close()
+
+def fetch_all_sessions():
+    session = Session(engine)
+    statement = select(SessionEntry)
+    results = session.exec(statement).all()
+    session.close()
+    return results
+
+# === Load Whisper ===
 model = WhisperModel("base", compute_type="int8")
-client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
-
-# === Persistent session history ===
-HISTORY_FILE = "history.json"
-def load_history():
-    if os.path.exists(HISTORY_FILE):
-        with open(HISTORY_FILE, "r", encoding="utf-8") as f:
-            return json.load(f)
-    return []
 
-def save_history(history):
-    with open(HISTORY_FILE, "w", encoding="utf-8") as f:
-        json.dump(history, f, ensure_ascii=False, indent=2)
-
-session_history = load_history()
-
-# === Audio Processing ===
 def convert_to_wav(input_file):
     output_wav = f"/tmp/{uuid.uuid4()}.wav"
     command = ["ffmpeg", "-y", "-i", input_file, "-ar", "16000", "-ac", "1", output_wav]
@@ -70,13 +75,12 @@ def convert_to_wav(input_file):
     return output_wav
 
 def transcribe_audio(audio_path):
-    segments, info = model.transcribe(audio_path)
+    segments, _ = model.transcribe(audio_path)
     return " ".join([segment.text for segment in segments])
 
-# === GPT-4 Feedback Generation ===
+# === GPT Feedback ===
 def generate_feedback(transcript, language):
-    prompt = f"""
-You are a communication coach. Please respond in [language={language}].
+    prompt = f"""You are a communication coach. Please respond in [language={language}].
 Evaluate the user's speech on:
 1. Clarity
 2. Structure
@@ -102,11 +106,8 @@ Transcript:
     )
     return response.choices[0].message.content
 
-# === GPT-4 Suggested Example ===
 def generate_example_response(transcript, language):
-    prompt = f"""
-You are a communication coach.
-Rewrite this speech to make it more polished, fluent, and confident.
+    prompt = f"""You are a communication coach. Rewrite this speech to make it more polished, fluent, and confident.
 Keep the meaning and tone the same, but improve clarity and structure.
 Transcript:
 {transcript}
@@ -120,10 +121,9 @@ Transcript:
     )
     return response.choices[0].message.content
 
-# === Main Feedback Function ===
 def tutor_feedback(audio_file, language):
     if not audio_file or not os.path.exists(audio_file):
-        return "", "No audio received.", None, ""
+        return "", "No audio received.", None, "", []
 
     wav_path = convert_to_wav(audio_file)
     transcript = transcribe_audio(wav_path)
@@ -134,47 +134,22 @@ def tutor_feedback(audio_file, language):
     mp3_path = f"/tmp/{uuid.uuid4()}.mp3"
     tts.save(mp3_path)
 
-    timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M")
-    session_entry = {
-        "timestamp": timestamp,
-        "transcript": transcript,
-        "feedback": feedback_text
-    }
-    session_history.append(session_entry)
-    save_history(session_history)
-
-    return transcript, feedback_text, mp3_path, transcript
-
-# === Export history ===
-def export_history_json():
-    return json.dumps(session_history, indent=2, ensure_ascii=False)
-
-def export_history_csv():
-    csv_path = "/tmp/session_history.csv"
-    with open(csv_path, "w", newline='', encoding="utf-8") as f:
-        writer = csv.writer(f)
-        writer.writerow(["Timestamp", "Transcript", "Feedback"])
-        for s in session_history:
-            writer.writerow([s['timestamp'], s['transcript'], s['feedback']])
-    return csv_path
+    save_to_db(transcript, feedback_text, language)
+    sessions = fetch_all_sessions()
+
+    return transcript, feedback_text, mp3_path, transcript, [[s.timestamp, s.language, s.transcript[:40], s.feedback[:40]] for s in sessions]
 
 # === Gradio Interface ===
 with gr.Blocks(css="light_mode_chatter_owl.css") as app:
-    gr.Markdown(
-        """
-        <div id="header" style="text-align: center;">
-            <img src="file/images/chatter_owl.png" width="120">
-            <h2>🦉 Meet <strong>Chatter the Owl</strong></h2>
-            <p>Choose your language, speak into the mic, and I’ll give you structured feedback to help you grow as a communicator!</p>
-        </div>
-        """
-    )
+    gr.Markdown("""
+    <div id="header" style="text-align: center;">
+        <img src="file/images/chatter_owl.png" width="120">
+        <h2>🦉 Meet <strong>Chatter the Owl</strong></h2>
+        <p>Choose your language, speak into the mic, and I’ll give you structured feedback to help you grow as a communicator!</p>
+    </div>
+    """)
 
-    language_dropdown = gr.Dropdown(
-        label="🌍 Select Your Language",
-        choices=list(LANG_CODES.keys()),
-        value="English"
-    )
+    language_dropdown = gr.Dropdown(label="🌍 Select Your Language", choices=list(LANG_CODES.keys()), value="English")
 
     with gr.Row():
         audio_input = gr.Audio(type="filepath", label="🎙 Speak or Upload Audio")
@@ -189,55 +164,22 @@ with gr.Blocks(css="light_mode_chatter_owl.css") as app:
         show_example = gr.Button("🎯 Show Me an Example")
 
     example_box = gr.Textbox(label="🗣 Suggested Improvement", visible=True, placeholder="Click to generate improved speech...")
+    history_table = gr.Dataframe(headers=["🕒 Timestamp", "🌐 Language", "📝 Transcript (Preview)", "📋 Feedback (Preview)"])
 
-    def get_session_table():
-        rows = [[s['timestamp'], s['transcript'][:60] + '...', s['feedback'][:60] + '...'] for s in session_history]
-        return rows
-
-    history_display = gr.Dataframe(headers=["🕒 Timestamp", "📝 Transcript", "📋 Feedback Preview"], interactive=False)
-    history_btn = gr.Button("🕓 View My Past Sessions")
-    export_json_btn = gr.Button("📤 Export History (JSON)")
-    export_csv_btn = gr.Button("📄 Export History (CSV)")
-    export_json_output = gr.Textbox(visible=False)
-    export_csv_output = gr.File(label="Download CSV")
-
-    audio_input.change(
-        fn=tutor_feedback,
-        inputs=[audio_input, language_dropdown],
-        outputs=[transcript_box, feedback_box, audio_output, hidden_transcript]
-    )
+    # Interactions
+    audio_input.change(fn=tutor_feedback,
+                       inputs=[audio_input, language_dropdown],
+                       outputs=[transcript_box, feedback_box, audio_output, hidden_transcript, history_table])
 
-    try_again.click(
-        fn=lambda: ("", "", None, "", ""),
-        inputs=None,
-        outputs=[transcript_box, feedback_box, audio_output, hidden_transcript, example_box]
-    )
+    try_again.click(fn=lambda: ("", "", None, "", "", []),
+                    inputs=None,
+                    outputs=[transcript_box, feedback_box, audio_output, hidden_transcript, example_box, history_table])
 
-    show_example.click(
-        fn=generate_example_response,
-        inputs=[hidden_transcript, language_dropdown],
-        outputs=example_box
-    )
-
-    history_btn.click(
-        fn=get_session_table,
-        inputs=None,
-        outputs=history_display
-    )
-
-    export_json_btn.click(
-        fn=export_history_json,
-        inputs=None,
-        outputs=export_json_output
-    )
-
-    export_csv_btn.click(
-        fn=export_history_csv,
-        inputs=None,
-        outputs=export_csv_output
-    )
+    show_example.click(fn=generate_example_response,
+                       inputs=[hidden_transcript, language_dropdown],
+                       outputs=example_box)
 
 # === Launch App ===
 if __name__ == "__main__":
     print("✅ App is launching...")
-    app.launch(server_name="0.0.0.0", server_port=7860, debug=True)
+    app.launch(server_name="0.0.0.0", server_port=7860, debug=True)