access ernie4.5 through qianfan sdk

Signed-off-by: Zhang Jun <jzhang533@gmail.com>

README.md

@@ -1,5 +1,5 @@
 ---
-title: Ernie Demo
+title: ERNIE 4.5
 emoji: 💬
 colorFrom: yellow
 colorTo: purple
@@ -8,7 +8,7 @@ sdk_version: 5.0.1
 app_file: app.py
 pinned: false
 license: apache-2.0
-short_description: Demonstrating ERNIE 4.5, https://yiyan.baidu.com/
+short_description: ERNIE 4.5 (BAIDU's LLM), https://yiyan.baidu.com/
 ---
 
 An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,10 +1,23 @@
+import os
 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")
+
+title = "ERNIE 4.5 : BAIDU's LLM"
+description = '''
+- Official Website: <https://yiyan.baidu.com/> (UI in Chinese)
+- Twitter post: [We've just unveiled ERNIE 4.5 & X1! 🚀](https://x.com/Baidu_Inc/status/1901089355890036897)
+- API services: [Qianfan Large Model Platform](https://cloud.baidu.com/product-s/qianfan_home) (cloud platform providing LLM services, UI in Chinese)
+'''
+
+
+qianfan_api_key = os.getenv("QIANFAN_TOKEN")
+qianfan_model = "ernie-4.5-8k-preview"
+
+client = OpenAI(
+        base_url='https://qianfan.baidubce.com/v2',
+        api_key=qianfan_api_key
+        )
 
 
 def respond(
@@ -25,40 +38,32 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    response = client.chat.completions.create(
+            model=qianfan_model, 
+            messages=messages,
+            max_completion_tokens = max_tokens,
+            temperature = temperature,
+            top_p = top_p
+            )
+    return response.choices[0].message.content
 
-    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=2, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
-            value=0.95,
+            value=0.7,
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
     ],
+    title = title,
+    description = description,
 )
 
-
 if __name__ == "__main__":
     demo.launch()

requirements.txt

@@ -1 +1,2 @@
-huggingface_hub==0.25.2
+openai
+huggingface_hub