Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+brain_tumor_model.keras filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,19 @@
+import gradio as gr
+from app1_groq_chat import groq_chat_app
+from app2_speech_chat import app2_speech_chat
+from app3_brain_tumor import app3_brain_tumor
+
+groq_chat = groq_chat_app()
+speech_chat = app2_speech_chat()
+tumor_detection = app3_brain_tumor()
+
+with gr.Blocks() as main_app:
+    gr.Markdown("# 🧠🎤🤖 Combined AI Applications Interface")
+    with gr.Tab("🧠 Brain Tumor Detection"):
+        tumor_detection.render()
+    with gr.Tab("🎤 Speech-to-Speech ChatBot"):
+        speech_chat.render()
+    with gr.Tab("🤖 Groq Chatbot"):
+        groq_chat.render()
+
+main_app.launch(share=True)

app1_groq_chat.py

@@ -0,0 +1,51 @@
+import gradio as gr
+from groq import Groq
+import os
+
+client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+
+def groq_chat_app():
+    def chat_with_groq(user_input, history):
+        if history is None:
+            history = []
+
+        if not user_input.strip():
+            return history, []
+
+        history.append({"role": "user", "content": user_input})
+
+        try:
+            response = client.chat.completions.create(
+                messages=history,
+                model="llama-3.1-8b-instant"
+            )
+            reply = response.choices[0].message.content
+            history.append({"role": "assistant", "content": reply})
+
+            formatted_history = [
+                (m["content"] if m["role"] == "user" else None,
+                 m["content"] if m["role"] == "assistant" else None)
+                for m in history if m["role"] != "system"
+            ]
+
+            return history, formatted_history, ""
+
+        except Exception as e:
+            return history, [("Error", str(e))], ""
+
+    with gr.Blocks() as demo:
+        gr.Markdown("## 🤖 Groq Chatbot with Submit Button")
+
+        chatbot = gr.Chatbot()
+        state = gr.State([])
+        msg = gr.Textbox(label="Your Message", placeholder="Type something...")
+        submit_btn = gr.Button("📤 Submit")
+        clear_btn = gr.ClearButton([msg, chatbot, state])
+
+        submit_btn.click(
+            fn=chat_with_groq,
+            inputs=[msg, state],
+            outputs=[state, chatbot, msg]
+        )
+    
+    return demo

app2_speech_chat.py

@@ -0,0 +1,44 @@
+import os
+import tempfile
+import gradio as gr
+from groq import Groq
+import whisper
+from gtts import gTTS
+
+client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+whisper_model = whisper.load_model("small")
+
+def app2_speech_chat():
+    def speech_to_speech(audio_file):
+        try:
+            result = whisper_model.transcribe(audio_file)
+            user_text = result["text"]
+
+            chat_completion = client.chat.completions.create(
+                messages=[{"role": "user", "content": user_text}],
+                model="llama-3.3-70b-versatile"
+            )
+            bot_reply = chat_completion.choices[0].message.content
+
+            tts = gTTS(bot_reply)
+            temp_audio_path = tempfile.mktemp(suffix=".mp3")
+            tts.save(temp_audio_path)
+
+            return user_text, bot_reply, temp_audio_path
+
+        except Exception as e:
+            return f"Error: {str(e)}", "", None
+
+    interface = gr.Interface(
+        fn=speech_to_speech,
+        inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),
+        outputs=[
+            gr.Textbox(label="Transcribed Text"),
+            gr.Textbox(label="Groq Reply"),
+            gr.Audio(label="Reply Audio")
+        ],
+        title="🎤 Speech-to-Speech ChatBot",
+        description="Speak or upload audio → Whisper transcribes → Groq replies → gTTS speaks the answer."
+    )
+
+    return interface

app3_brain_tumor.py

@@ -0,0 +1,27 @@
+import gradio as gr
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+import numpy as np
+from PIL import Image
+
+model = load_model("/content/brain_tumor_model.keras")
+
+def predict_tumor(img):
+    img = img.convert('RGB').resize((150, 150))
+    img_array = image.img_to_array(img)
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array /= 255.0
+
+    prediction = model.predict(img_array)
+    result = "Yes, Tumor Detected 😔" if prediction[0][0] > 0.5 else "No Tumor Detected 😊"
+    return result
+
+def app3_brain_tumor():
+    interface = gr.Interface(
+        fn=predict_tumor,
+        inputs=gr.Image(type="pil", label="Upload MRI Scan"),
+        outputs=gr.Textbox(label="Prediction"),
+        title="🧠 Brain Tumor Detection",
+        description="Upload an MRI scan to check for tumor presence."
+    )
+    return interface

brain_tumor_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f533c25bb87e76f2a0793a3508585f76b52a0bcd732d0bd49eef118bd50108b4
+size 127677329