Update space

app.py

@@ -1,64 +1,36 @@
+from models import ModelChain
 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")
+DEEPSEEK_MODEL = "deepseek/deepseek-r1:free"
+GEMINI_MODEL = "google/gemini-2.0-flash-exp:free"
+QWEN_MODEL="qwen/qwen2.5-vl-72b-instruct:free"
+
+def get_models_response(models,user_input,system_prompt):
+    if len(models) >1:
+        return "Currently Unsupported"
+    else:
+        print(f"Reponse using model {models}")
+        chain = ModelChain()
+        if models[0]=="deepseek-r1":
+            return chain.get_model_response(DEEPSEEK_MODEL,user_input,system_prompt)
+        elif models[0]=="gemini-2.0-flash-exp":
+            return chain.get_model_response(GEMINI_MODEL,user_input,system_prompt)
+        elif models[0]=="qwen2.5-vl-72b-instruct":
+            return chain.get_model_response(QWEN_MODEL,user_input,system_prompt)
+        else:
+            return "Current Unsupported"
+
+def main():
+    view = gr.Interface(
+        fn= get_models_response,
+        inputs = [gr.CheckboxGroup(["gemini-2.0-flash-exp","deepseek-r1","qwen2.5-vl-72b-instruct"], label = "Response model", value = "deepseek-r1"),gr.Textbox(label = "Your input",lines = 10, placeholder = "Nhập nội dung"), gr.Textbox(label = "Nhiệm vụ của Bot", placeholder = "Vd: bạn là một chuyên gia thương mại điện tử 10 năm kinh nghiệm hãy giúp tôi trả lời các câu hỏi sau")], 
+        outputs = gr.Textbox(label ="Output", lines = 26),
+        flagging_mode = "never",
+        stop_btn = gr.Button("Stop",variant = "stop",visible = True),
+    ).launch(share = True)
+
+if __name__ == '__main__':
+    main()
 
 
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()

models.py

@@ -0,0 +1,37 @@
+
+import os
+import openai
+from dotenv import load_dotenv
+# MOELS
+DEEPSEEK_MODEL = "deepseek/deepseek-r1:free"
+GEMINI_MODEL = "google/gemini-2.0-flash-exp:free"
+QWEN_MODEL="qwen/qwen2.5-vl-72b-instruct:free"
+OPENROUTER_API_KEY="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"
+load_dotenv()
+class ModelChain:
+	def __init__(self):
+		self.client = self.generate_client(OPENROUTER_API_KEY,"https://openrouter.ai/api/v1" )
+		self.deepseek_messages = []
+		self.gemini_messages = []
+
+	def generate_client(self,api_key, url):
+		return openai.OpenAI(
+			api_key = api_key,
+			base_url = url,
+			) 
+	def get_model_response(self,model,user_input,system_prompt):
+		messages = [{"role":"system","content": system_prompt},
+					{"role":"user","content":user_input}]
+		try:
+			result = self.client.chat.completions.create(
+				model = model,
+				messages = messages,
+				)
+			return result.choices[0].message.content
+		except Exception as e:
+			return f"Error occurred while getting response{e}"
+def main():
+	chain= Modelschain()
+
+if __name__ == "__main__":
+	main()

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio
+openai