Update app.py

app.py

@@ -1,64 +1,52 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from openai import OpenAI
 
-"""
-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")
+import os
 
+UPSTAGE_API_KEY = os.getenv("UPSTAGE_API_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(
+    api_key=UPSTAGE_API_KEY,  # 실제 API 키로 교체
+    base_url="https://api.upstage.ai/v1/solar"
 )
 
 
+# 임베딩 함수 정의
+def get_embedding(text):
+    try:
+        response = client.embeddings.create(
+            model="embedding-query",
+            input=text
+        )
+        embedding = response.data[0].embedding
+        
+        return embedding
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Gradio 인터페이스
+# with gr.Blocks() as demo:
+#     gr.Markdown("## 🌟 Solar Embedding API 데모\n\n문장을 입력하고 임베딩 결과를 확인해보세요.")
+    
+#     with gr.Row():
+#         input_text = gr.Textbox(label="입력 문장", placeholder="예: How's the weather today?")
+#         output_embedding = gr.Textbox(label="임베딩 결과(소수점 세자리 반올림)")
+    
+#     run_button = gr.Button("임베딩하기")
+#     run_button.click(fn=get_embedding, inputs=input_text, outputs=output_embedding)
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 🌟 Solar Embedding API Demo\n\nEnter a sentence and check the embedding result (rounded to three decimal places).")
+    
+    with gr.Row():
+        input_text = gr.Textbox(label="Input Sentence", placeholder="e.g., How's the weather today?")
+        output_embedding = gr.Textbox(label="Embedding Result (rounded to 3 decimal places)")
+    
+    run_button = gr.Button("Generate Embedding")
+    run_button.click(fn=get_embedding, inputs=input_text, outputs=output_embedding)
+
+
+    
 if __name__ == "__main__":
     demo.launch()