Update app.py

app.py

@@ -1,63 +1,105 @@
+import itertools
 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
-"""
+import requests
+import os
+from gradio.themes.utils import sizes
+import json
+import pandas as pd
+
+import base64
+import io
+from PIL import Image
+import numpy as np
+    
+def respond(message, history):
+
+    if len(message.strip()) == 0:
+        return "質問を入力してください"
+
+    local_token = os.getenv('API_TOKEN')
+    local_endpoint = os.getenv('API_ENDPOINT')
+
+    if local_token is None or local_endpoint is None:
+        return "ERROR missing env variables"
+
+    # Add your API token to the headers
+    headers = {
+        'Content-Type': 'application/json',
+        'Authorization': f'Bearer {local_token}'
+    }
+
+    #prompt = list(itertools.chain.from_iterable(history))
+    #prompt.append(message)
+
+    # プロンプトの作成
+    prompt = pd.DataFrame(
+        {"prompt": [message], "num_inference_steps": 25}
+    )
+
+    print(prompt)
+    ds_dict = {"dataframe_split": prompt.to_dict(orient="split")}
+    data_json = json.dumps(ds_dict, allow_nan=True)
+
+    embed_image_markdown = ""
+
+    try:
+        # モデルサービングエンドポイントに問い合わせ
+        response = requests.request(method="POST", headers=headers, url=local_endpoint, data=data_json)    
+        response_data = response.json()
+        #print(response_data["predictions"])
+
+        # numpy arrayに変換
+        im_array = np.array(response_data["predictions"], dtype=np.uint8)
+        #print(im_array)
+        # 画像に変換
+        im = Image.fromarray(im_array, 'RGB')
+
+    
+        # debug
+        #image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/e/ec/Mona_Lisa,_by_Leonardo_da_Vinci,_from_C2RMF_retouched.jpg/687px-Mona_Lisa,_by_Leonardo_da_Vinci,_from_C2RMF_retouched.jpg"
+        #print("image_url:", image_url)
+        #im = Image.open(io.BytesIO(requests.get(image_url).content))
+        #numpydata = np.asarray(im)
+
+        rawBytes = io.BytesIO()
+        im.save(rawBytes, "PNG")
+        rawBytes.seek(0)  # ファイルの先頭に移動
+        # base64にエンコード
+        image_encoded = base64.b64encode(rawBytes.read()).decode('ascii')
+        #print(image_encoded)
+
+        # マークダウンに埋め込み
+        embed_image_markdown = f"![](data:image/png;base64,{image_encoded})"
+        #print(embed_image_markdown)
+    
+    except Exception as error:
+        response_data = f"ERROR status_code: {type(error).__name__}" 
+        #+ str(response.status_code) + " response:" + response.text    
+
+    return embed_image_markdown
+
+
+theme = gr.themes.Soft(
+    text_size=sizes.text_sm,radius_size=sizes.radius_sm, spacing_size=sizes.spacing_sm,
+)
+
+
 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)",
-        ),
-    ],
+    chatbot=gr.Chatbot(show_label=False, container=False, show_copy_button=True, bubble_full_width=True),
+    textbox=gr.Textbox(placeholder="質問を入力してください",
+                       container=False, scale=7),
+    title="Databricks QAチャットボット",
+    description="TBD",
+    examples=[["Databricksクラスターとは？"],
+              ["Unity Catalogの有効化方法"],
+              ["リネージの保持期間"],],
+    cache_examples=False,
+    theme=theme,
+    retry_btn=None,
+    undo_btn=None,
+    clear_btn="Clear",
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()