Upload app.py

app.py

@@ -0,0 +1,72 @@
+import streamlit as st
+import requests
+import base64
+from PIL import Image
+from io import BytesIO
+
+# Function to encode an image into base64 format
+def encode_image(img):
+    buffered = BytesIO()
+    img.save(buffered, format="PNG")
+    encoded_string = base64.b64encode(buffered.getvalue()).decode("utf-8")
+    return encoded_string
+
+# Function to get explanation from VLM API
+def explain_image_with_vlm(image):
+    api = "https://api.hyperbolic.xyz/v1/chat/completions"
+    api_key = "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiJhZGlsYXppejIwMTNAZ21haWwuY29tIiwiaWF0IjoxNzMyODU1NDI1fQ.lRjbz9LMW9jj7Lf7I8m_dTRh4KQ1wDCdWiTRGErMuEk"
+
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {api_key}",
+    }
+
+    base64_img = encode_image(image)
+
+    payload = {
+        "messages": [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "Explain the Image in 10 words only"},
+                    {
+                        "type": "image_url",
+                        "image_url": {"url": f"data:image/jpeg;base64,{base64_img}"},
+                    },
+                ],
+            }
+        ],
+        "model": "Qwen/Qwen2-VL-72B-Instruct",
+        "max_tokens": 2048,
+        "temperature": 0.7,
+        "top_p": 0.9,
+    }
+
+    response = requests.post(api, headers=headers, json=payload)
+    if response.status_code == 200:
+        return response.json().get("choices", [{}])[0].get("message", {}).get("content", "No explanation found.")
+    else:
+        return f"Error: {response.status_code} - {response.text}"
+
+# Streamlit UI
+st.title("📸 AI-Powered Image Explainer")
+st.subheader("Capture an image and let the AI explain it!")
+
+# Camera input
+img_file_buffer = st.camera_input("Take a picture")
+
+if img_file_buffer:
+    # Display captured image
+    image = Image.open(img_file_buffer)
+    st.image(image, caption="Captured Image", use_column_width=True)
+
+    st.subheader("🔍 Image Explanation")
+    with st.spinner("Analyzing image..."):
+        explanation = explain_image_with_vlm(image)
+        st.success("Analysis Complete!")
+        st.write(f"**Explanation:** {explanation}")
+
+st.info(
+    "This app captures an image using your device's camera and provides an AI-generated explanation "
+    "using a cutting-edge Vision Language Model (VLM)."
+)