Update app.py

app.py

@@ -1,107 +1,94 @@
 import gradio as gr
 import os
-import tempfile
-import whisper
-import docx
 import pdfplumber
+import docx
 import pandas as pd
-from groq import Groq
-from PyPDF2 import PdfReader
+from PIL import Image
+from io import BytesIO
+import base64
+import whisper
+from openai import OpenAI
 
-GROQ_API_KEY = os.getenv("GROQ_API_KEY")
-client = Groq(api_key=GROQ_API_KEY)
+# Setup GROQ
+client = OpenAI(api_key=os.environ["GROQ_API_KEY"], base_url="https://api.groq.com/openai/v1")
+
+# Load Whisper model
 whisper_model = whisper.load_model("base")
 
-def read_file(file):
+def extract_text_from_file(file):
+    if file.name.endswith(".pdf"):
+        with pdfplumber.open(file.name) as pdf:
+            text = "\n".join(page.extract_text() for page in pdf.pages if page.extract_text())
+    elif file.name.endswith(".docx"):
+        doc = docx.Document(file.name)
+        text = "\n".join(p.text for p in doc.paragraphs)
+    elif file.name.endswith(".xlsx"):
+        df = pd.read_excel(file.name)
+        text = df.to_string()
+    elif file.name.endswith((".png", ".jpg", ".jpeg")):
+        img = Image.open(file.name)
+        buffer = BytesIO()
+        img.save(buffer, format="PNG")
+        encoded = base64.b64encode(buffer.getvalue()).decode("utf-8")
+        text = f"[Image uploaded: data:image/png;base64,{encoded[:100]}... (truncated)]"
+    else:
+        with open(file.name, "r", encoding="utf-8", errors="ignore") as f:
+            text = f.read()
+    return text
+
+def transcribe_audio(audio_path):
+    result = whisper_model.transcribe(audio_path)
+    return result["text"]
+
+def generate_reply(history):
+    messages = [{"role": "system", "content": "You are a helpful assistant."}]
+    for user_msg, bot_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": bot_msg})
+
+    response = client.chat.completions.create(
+        model="llama3-8b-8192",
+        messages=messages,
+        temperature=0.7
+    )
+    return response.choices[0].message.content
+
+def respond(message, history):
+    reply = generate_reply(history + [[message, ""]])
+    history.append([message, reply])
+    return history, ""
+
+def handle_file_upload(file, message):
     if file is None:
-        return ""
-    ext = os.path.splitext(file.name)[-1].lower()
-    try:
-        if ext == ".txt":
-            with open(file.name, "r", encoding="utf-8") as f:
-                return f.read()
-        elif ext == ".pdf":
-            text = ""
-            with pdfplumber.open(file.name) as pdf:
-                for page in pdf.pages:
-                    text += page.extract_text() + "\n"
-            return text
-        elif ext in [".doc", ".docx"]:
-            doc = docx.Document(file.name)
-            return "\n".join([para.text for para in doc.paragraphs])
-        elif ext in [".xls", ".xlsx"]:
-            df = pd.read_excel(file.name)
-            return df.to_string(index=False)
-        else:
-            return f"[Unsupported file format: {ext}]"
-    except Exception as e:
-        return f"[Error reading file: {e}]"
-
-def transcribe_audio(audio):
+        return message
+    file_content = extract_text_from_file(file)
+    return f"{message}\n\n--- File Content Start ---\n{file_content}\n--- File Content End ---"
+
+def handle_audio_upload(audio, message):
     if audio is None:
-        return ""
-    try:
-        audio_path = audio.name
-        result = whisper_model.transcribe(audio_path)
-        return result["text"]
-    except Exception as e:
-        return f"[Error transcribing audio: {e}]"
-
-def process_input(message, history):
-    if not message.strip():
-        return history
-
-    history = history or []
-    history.append({"role": "user", "content": message})
-
-    try:
-        response = client.chat.completions.create(
-            model="llama3-8b-8192",
-            messages=history,
-        )
-        reply = response.choices[0].message.content
-        history.append({"role": "assistant", "content": reply})
-    except Exception as e:
-        history.append({"role": "assistant", "content": f"[Error: {e}]"})
-    
-    return history
-
-def interface_func(message, history, file, audio):
-    file_text = read_file(file) if file else ""
-    audio_text = transcribe_audio(audio) if audio else ""
-    combined = ""
-
-    if file_text:
-        combined += f"{file.name} content:\n{file_text}\n\n"
-    if audio_text:
-        combined += f"Transcribed audio:\n{audio_text}\n\n"
-    if message:
-        combined += message
-
-    return combined.strip()
-
-with gr.Blocks(css="textarea { font-size: 16px !important; }") as demo:
-    gr.Markdown("<h1 style='text-align: center;'>NEOBOT</h1>")
-
-    chatbot = gr.Chatbot(height=400, label="Chat")
+        return message
+    transcription = transcribe_audio(audio)
+    return f"{message}\n\n--- Transcription ---\n{transcription}"
+
+with gr.Blocks(css="body { background-color: white; color: black }") as demo:
+    gr.Markdown("<h1 style='text-align: center;'>Neobot</h1>")
+    chatbot = gr.Chatbot(label="Chat", elem_id="chatbox", height=450, type="messages")
 
     with gr.Row():
-        msg_box = gr.Textbox(
-            scale=8, 
-            placeholder="Ask something...", 
-            show_label=False, 
-            container=True
-        )
+        txt = gr.Textbox(placeholder="Type your message or review the file/audio content here…", scale=5, show_label=False)
         send_btn = gr.Button("Send", scale=1)
 
     with gr.Row():
-        file_upload = gr.File(label="Upload File", file_types=[".txt", ".pdf", ".docx", ".xlsx"])
-        audio_upload = gr.Audio(source="upload", type="filepath", label="Upload Audio")
+        upload_btn = gr.File(label="📎 Upload File", file_types=[".pdf", ".docx", ".txt", ".xlsx", ".png", ".jpg", ".jpeg"])
+        audio_in = gr.Audio(label="🎙️ Upload Audio", type="filepath")
+
+    history = gr.State([])
 
-    state = gr.State([])
+    # Message only sent when Send is clicked
+    send_btn.click(respond, [txt, history], [chatbot, txt])
 
-    send_btn.click(fn=process_input, inputs=[msg_box, state], outputs=[chatbot, state])
-    file_upload.change(fn=interface_func, inputs=[msg_box, state, file_upload, audio_upload], outputs=msg_box)
-    audio_upload.change(fn=interface_func, inputs=[msg_box, state, file_upload, audio_upload], outputs=msg_box)
+    # File and audio just modify the message box
+    upload_btn.change(handle_file_upload, [upload_btn, txt], txt)
+    audio_in.change(handle_audio_upload, [audio_in, txt], txt)
 
 demo.launch()