Update app.py

app.py

@@ -1,64 +1,82 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+import requests
+import json
+import os
 
+# Set OpenRouter API key in the Space's secrets as "OPENROUTER_API_KEY"
+OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY")
+HEADERS = {
+    "Authorization": f"Bearer {OPENROUTER_API_KEY}",
+    "HTTP-Referer": "https://huggingface.co/spaces/YOUR_SPACE",  # Optional
+    "X-Title": "CrispChat"  # Optional
+}
+
+# List of free OpenRouter models
+FREE_MODELS = {
+    "Google: Gemini Pro 2.5 Experimental (free)": ("google/gemini-2.5-pro-exp-03-25:free", 1000000),
+    "DeepSeek: DeepSeek V3 (free)": ("deepseek/deepseek-chat:free", 131072),
+    "Meta: Llama 3.2 11B Vision Instruct (free)": ("meta-llama/llama-3.2-11b-vision-instruct:free", 131072),
+    "Qwen: Qwen2.5 VL 72B Instruct (free)": ("qwen/qwen2.5-vl-72b-instruct:free", 131072),
+}
+
+
+def query_openrouter_model(model_id, prompt, image=None):
+    messages = [{"role": "user", "content": prompt}]
+
+    # If image is included, add it to the message content as a dict
+    if image is not None:
+        with open(image, "rb") as f:
+            image_bytes = f.read()
+            base64_image = base64.b64encode(image_bytes).decode("utf-8")
+        messages[0]["content"] = [
+            {"type": "text", "text": prompt},
+            {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{base64_image}"}}
+        ]
+
+    payload = {
+        "model": model_id,
+        "messages": messages
+    }
+
+    response = requests.post(
+        url="https://openrouter.ai/api/v1/chat/completions",
+        headers=HEADERS,
+        data=json.dumps(payload)
+    )
+
+    try:
+        response.raise_for_status()
+        data = response.json()
+        return data["choices"][0]["message"]["content"]
+    except Exception as e:
+        return f"Error: {str(e)}\n{response.text}"
+
+
+def chat_interface(prompt, image, model_label):
+    model_id, _ = FREE_MODELS[model_label]
+    return query_openrouter_model(model_id, prompt, image)
+
+
+with gr.Blocks(title="CrispChat") as demo:
+    gr.Markdown("""
+    # 🌟 CrispChat 
+    Multi-modal chat with free OpenRouter models
+    """)
+
+    with gr.Row():
+        prompt = gr.Textbox(label="Enter your message", lines=4, placeholder="Ask me anything...")
+        image = gr.Image(type="filepath", label="Optional image input")
+
+    model_choice = gr.Dropdown(
+        choices=list(FREE_MODELS.keys()),
+        value="Google: Gemini Pro 2.5 Experimental (free)",
+        label="Select model"
+    )
+
+    output = gr.Textbox(label="Response", lines=6)
+
+    submit = gr.Button("Submit")
+    submit.click(fn=chat_interface, inputs=[prompt, image, model_choice], outputs=output)
 
 if __name__ == "__main__":
     demo.launch()