Update app.py

app.py

@@ -1,64 +1,35 @@
+import os
 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)",
-        ),
-    ],
+from camel.agents import ChatAgent
+from camel.models import ModelFactory
+from camel.types import ModelPlatformType
+
+# Load API key from environment variable
+aiml_key = os.getenv("AIML_API_KEY")
+
+# Function to process queries
+def query_model(query):
+    if not aiml_key:
+        return "AIML API key not configured."
+    deepseek_model = ModelFactory.create(
+        model_platform=ModelPlatformType.AIML,
+        model_type="deepseek/deepseek-r1",
+        model_config_dict={"max_tokens": 2000}
+    )
+    agent = ChatAgent(
+        system_message="Answer questions based on context.",
+        model=deepseek_model
+    )
+    response = agent.step(query)
+    return response.msgs[0].content if response.msgs else "No response."
+
+# Launch Gradio Interface
+demo = gr.Interface(
+    fn=query_model,
+    inputs="text",
+    outputs="text",
+    title="RAG App with DeepSeek-R1 (AIML API)",
+    description="Ask questions and receive responses powered by DeepSeek-R1 via AIML API."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()