Update app.py

app.py

@@ -1,18 +1,111 @@
+# import gradio as gr
+# import requests
+# import time
+# import json
+# import os
+# import datetime
+# from transformers import AutoModelForCausalLM, AutoTokenizer
+# import torch
+
+# ### SET YOUR ASSEMBLYAI API KEY
+# ASSEMBLYAI_API_KEY = os.getenv("ASSEMBLYAI_API_KEY", "your_assemblyai_api_key")
+# headers = {"authorization": ASSEMBLYAI_API_KEY}
+# notes_file = "notes.json"
+
+# ### LOAD LLM
+# model_id = "IlmaJiyadh/phi3-4k-ft"
+# tokenizer = AutoTokenizer.from_pretrained(model_id)
+# model = AutoModelForCausalLM.from_pretrained(
+#     model_id,
+#     device_map="auto",
+#     torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+#     trust_remote_code=True
+# )
+
+# ### TRANSCRIBE AUDIO WITH ASSEMBLYAI
+# def transcribe(audio_path):
+#     with open(audio_path, 'rb') as f:
+#         upload_res = requests.post("https://api.assemblyai.com/v2/upload", headers=headers, files={"file": f})
+#     audio_url = upload_res.json()["upload_url"]
+
+#     transcript_res = requests.post("https://api.assemblyai.com/v2/transcript", json={"audio_url": audio_url}, headers=headers)
+#     transcript_id = transcript_res.json()["id"]
+
+#     while True:
+#         poll = requests.get(f"https://api.assemblyai.com/v2/transcript/{transcript_id}", headers=headers).json()
+#         if poll['status'] == 'completed':
+#             return poll['text']
+#         elif poll['status'] == 'error':
+#             return f"Transcription failed: {poll['error']}"
+#         time.sleep(2)
+
+# ### SUMMARIZE USING LLM
+# def summarize(text):
+#     prompt = f"Below is a lecture transcript. Take lecture notes in bullet points.\n\nInput:\n{text}\n\nSummary:\n"
+#     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+#     outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7, use_cache=False)
+#     return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# ## SAVE TO JSON
+# def save_note(date, transcript, summary):
+#     data = {"date": date, "transcript": transcript, "summary": summary}
+#     if os.path.exists(notes_file):
+#         with open(notes_file, "r") as f:
+#             all_notes = json.load(f)
+#     else:
+#         all_notes = []
+#     all_notes.append(data)
+#     with open(notes_file, "w") as f:
+#         json.dump(all_notes, f, indent=2)
+
+# ### SEARCH NOTES
+# def search_notes(query):
+#     if not os.path.exists(notes_file):
+#         return "No notes available yet."
+#     with open(notes_file, "r") as f:
+#         notes = json.load(f)
+#     results = [n for n in notes if query.lower() in n['summary'].lower() or query.lower() in n['transcript'].lower()]
+#     if not results:
+#         return "No matching notes found."
+#     return "\n\n".join([f"📅 {n['date']}\n{n['summary']}" for n in results])
+
+# ### FULL PIPELINE
+# def full_pipeline(audio):
+#     if audio is None:
+#         return "No audio provided", "", ""
+    
+#     transcript = transcribe(audio)
+#     summary = summarize(transcript)
+#     date_str = str(datetime.date.today())
+#     save_note(date_str, transcript, summary)
+#     return transcript, summary, f"✅ Lecture saved for {date_str}"
+
+# ### BUILD GRADIO UI
+# with gr.Blocks() as demo:
+#     gr.Markdown("# 🎓 Lecture Assistant (Audio → Summary + Search)")
+#     with gr.Row():
+#         with gr.Column():
+#             #audio_input = gr.Audio(source="microphone", type="filepath", label="🎙️ Record Audio")
+#             audio_input = gr.Audio(type="filepath", label="🎙️ Record Audio")
+#             submit_btn = gr.Button("Transcribe & Summarize")
+#             transcript_output = gr.Textbox(label="📄 Transcript")
+#             summary_output = gr.Textbox(label="📝 Summary")
+#             save_status = gr.Textbox(label="💾 Save Status")
+
+#         with gr.Column():
+#             search_query = gr.Textbox(label="🔍 Search Notes")
+#             search_btn = gr.Button("Search")
+#             search_output = gr.Textbox(label="Results")
+
+#     submit_btn.click(fn=full_pipeline, inputs=audio_input, outputs=[transcript_output, summary_output, save_status])
+#     search_btn.click(fn=search_notes, inputs=search_query, outputs=search_output)
+
+# demo.launch()
+
 import gradio as gr
-import requests
-import time
-import json
-import os
-import datetime
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-### SET YOUR ASSEMBLYAI API KEY
-ASSEMBLYAI_API_KEY = os.getenv("ASSEMBLYAI_API_KEY", "your_assemblyai_api_key")
-headers = {"authorization": ASSEMBLYAI_API_KEY}
-notes_file = "notes.json"
-
-### LOAD LLM
 model_id = "IlmaJiyadh/phi3-4k-ft"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
@@ -22,82 +115,17 @@ model = AutoModelForCausalLM.from_pretrained(
     trust_remote_code=True
 )
 
-### TRANSCRIBE AUDIO WITH ASSEMBLYAI
-def transcribe(audio_path):
-    with open(audio_path, 'rb') as f:
-        upload_res = requests.post("https://api.assemblyai.com/v2/upload", headers=headers, files={"file": f})
-    audio_url = upload_res.json()["upload_url"]
-
-    transcript_res = requests.post("https://api.assemblyai.com/v2/transcript", json={"audio_url": audio_url}, headers=headers)
-    transcript_id = transcript_res.json()["id"]
-
-    while True:
-        poll = requests.get(f"https://api.assemblyai.com/v2/transcript/{transcript_id}", headers=headers).json()
-        if poll['status'] == 'completed':
-            return poll['text']
-        elif poll['status'] == 'error':
-            return f"Transcription failed: {poll['error']}"
-        time.sleep(2)
-
-### SUMMARIZE USING LLM
 def summarize(text):
     prompt = f"Below is a lecture transcript. Take lecture notes in bullet points.\n\nInput:\n{text}\n\nSummary:\n"
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7, use_cache=False)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-### SAVE TO JSON
-def save_note(date, transcript, summary):
-    data = {"date": date, "transcript": transcript, "summary": summary}
-    if os.path.exists(notes_file):
-        with open(notes_file, "r") as f:
-            all_notes = json.load(f)
-    else:
-        all_notes = []
-    all_notes.append(data)
-    with open(notes_file, "w") as f:
-        json.dump(all_notes, f, indent=2)
-
-### SEARCH NOTES
-def search_notes(query):
-    if not os.path.exists(notes_file):
-        return "No notes available yet."
-    with open(notes_file, "r") as f:
-        notes = json.load(f)
-    results = [n for n in notes if query.lower() in n['summary'].lower() or query.lower() in n['transcript'].lower()]
-    if not results:
-        return "No matching notes found."
-    return "\n\n".join([f"📅 {n['date']}\n{n['summary']}" for n in results])
-
-### FULL PIPELINE
-def full_pipeline(audio):
-    if audio is None:
-        return "No audio provided", "", ""
-    
-    transcript = transcribe(audio)
-    summary = summarize(transcript)
-    date_str = str(datetime.date.today())
-    save_note(date_str, transcript, summary)
-    return transcript, summary, f"✅ Lecture saved for {date_str}"
-
-### BUILD GRADIO UI
-with gr.Blocks() as demo:
-    gr.Markdown("# 🎓 Lecture Assistant (Audio → Summary + Search)")
-    with gr.Row():
-        with gr.Column():
-            #audio_input = gr.Audio(source="microphone", type="filepath", label="🎙️ Record Audio")
-            audio_input = gr.Audio(type="filepath", label="🎙️ Record Audio")
-            submit_btn = gr.Button("Transcribe & Summarize")
-            transcript_output = gr.Textbox(label="📄 Transcript")
-            summary_output = gr.Textbox(label="📝 Summary")
-            save_status = gr.Textbox(label="💾 Save Status")
-
-        with gr.Column():
-            search_query = gr.Textbox(label="🔍 Search Notes")
-            search_btn = gr.Button("Search")
-            search_output = gr.Textbox(label="Results")
-
-    submit_btn.click(fn=full_pipeline, inputs=audio_input, outputs=[transcript_output, summary_output, save_status])
-    search_btn.click(fn=search_notes, inputs=search_query, outputs=search_output)
-
-demo.launch()
+gr.Interface(
+    fn=summarize,
+    inputs=gr.Textbox(lines=10, label="📄 Paste Transcript"),
+    outputs=gr.Textbox(label="📝 Summary"),
+    title="🧠 Transcript → Summary (Phi-3 Fine-tuned)",
+    description="Test only the summarization step."
+).launch()
+