Update app.py

app.py

@@ -4,8 +4,6 @@ import requests
 import os
 from together import Together
 import base64
-from threading import Thread
-import time
 import io
 
 # Initialize Together client
@@ -20,15 +18,10 @@ def initialize_client(api_key=None):
     else:
         raise ValueError("Please provide a Together API Key")
 
-def encode_image(image_path, max_size=(800, 800), quality=85):
+def encode_image(image_path):
     with Image.open(image_path) as img:
-        img.thumbnail(max_size)
-        if img.mode in ('RGBA', 'LA'):
-            background = Image.new(img.mode[:-1], img.size, (255, 255, 255))
-            background.paste(img, mask=img.split()[-1])
-            img = background
         buffered = io.BytesIO()
-        img.save(buffered, format="JPEG", quality=quality)
+        img.save(buffered, format="PNG")
         return base64.b64encode(buffered.getvalue()).decode('utf-8')
 
 def bot_streaming(message, history, together_api_key, max_new_tokens=250, temperature=0.7):
@@ -45,18 +38,27 @@ def bot_streaming(message, history, together_api_key, max_new_tokens=250, temper
     
     # Add history to messages
     for user_msg, assistant_msg in history:
-        messages.append({"role": "user", "content": user_msg})
-        messages.append({"role": "assistant", "content": assistant_msg})
+        if isinstance(user_msg, tuple):  # Handle image messages
+            text = user_msg[1] if len(user_msg) > 1 else ""
+            messages.append({"role": "user", "content": [
+                {"type": "text", "text": text},
+                {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{encode_image(user_msg[0])}"}}
+            ]})
+        else:
+            messages.append({"role": "user", "content": [{"type": "text", "text": user_msg}]})
+        messages.append({"role": "assistant", "content": [{"type": "text", "text": assistant_msg}]})
     
     # Prepare the current message
     current_message = {"role": "user", "content": []}
     
     # Add text content
-    if message.get("text"):
+    if isinstance(message, dict) and message.get("text"):
         current_message["content"].append({"type": "text", "text": message["text"]})
+    elif isinstance(message, str):
+        current_message["content"].append({"type": "text", "text": message})
     
     # Add image content if present
-    if message.get("files") and len(message["files"]) > 0:
+    if isinstance(message, dict) and message.get("files") and len(message["files"]) > 0:
         image_path = message["files"][0]["path"] if isinstance(message["files"][0], dict) else message["files"][0]
         image_base64 = encode_image(image_path)
         current_message["content"].append({
@@ -90,6 +92,7 @@ def bot_streaming(message, history, together_api_key, max_new_tokens=250, temper
         else:
             yield f"An error occurred: {str(e)}"
 
+# The rest of your Gradio interface code remains the same
 with gr.Blocks() as demo:
     gr.Markdown("# Meta Llama-3.2-11B-Vision-Instruct (FREE)")
     gr.Markdown("Try the new Llama 3.2 11B Vision API by Meta for free through Together AI. Upload an image, and start chatting about it. Just paste in your Together AI API key and get started!")
@@ -97,7 +100,7 @@ with gr.Blocks() as demo:
     with gr.Row():
         together_api_key = gr.Textbox(
             label="Together API Key",
-            placeholder="Enter your Together API key here",
+            placeholder="Enter your TOGETHER_API_KEY here",
             type="password"
         )