Update app.py

app.py

@@ -1,63 +1,39 @@
+from openai import OpenAI
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
 
-"""
-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")
+api_key = os.getenv("TYPHOON_API_KEY")  # Replace with your key
 
-
-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)",
-        ),
-    ],
+client = OpenAI(
+   base_url='https://api.opentyphoon.ai/v1',
+   api_key=api_key,
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+def predict(message, history):
+    
+    system_prompt = """You are HoraGuide, an empathetic Thai girl assistant skilled in psychotherapy and Tarot reading. 
+You provide insights and support using Tarot cards, offering clarity and healing. You always answer in Thai."""
+    
+    history_openai_format = [{"role": "system", "content": system_prompt}]
+    for human, assistant in history:
+        history_openai_format.append({"role": "user", "content": human })
+        history_openai_format.append({"role": "assistant", "content":assistant})
+    history_openai_format.append({"role": "user", "content": message})
+  
+    response = client.chat.completions.create(
+        model='typhoon-v1.5-instruct',
+        messages= history_openai_format,
+        temperature=0.5,
+        stream=True
+        )
+
+    partial_message = ""
+    for chunk in response:
+        if chunk.choices[0].delta.content is not None:
+              partial_message = partial_message + chunk.choices[0].delta.content
+              yield partial_message
+
+with gr.Blocks() as demo:
+    gr.ChatInterface(predict)
+    
+demo.launch()