Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,5 +1,3 @@
|
|
| 1 |
-
# app.py
|
| 2 |
-
|
| 3 |
import os
|
| 4 |
import openai
|
| 5 |
import gradio as gr
|
|
@@ -12,55 +10,26 @@ from langchain_community.chat_models import ChatOpenAI
|
|
| 12 |
import shutil # 用於文件複製
|
| 13 |
import logging
|
| 14 |
|
| 15 |
-
# 設置日誌配置
|
| 16 |
-
logging.basicConfig(level=logging.INFO)
|
| 17 |
-
logger = logging.getLogger(__name__)
|
| 18 |
-
|
| 19 |
# 獲取 OpenAI API 密鑰(初始不使用固定密鑰)
|
| 20 |
api_key_env = os.getenv("OPENAI_API_KEY")
|
| 21 |
if api_key_env:
|
| 22 |
openai.api_key = api_key_env
|
| 23 |
-
logger.info("OpenAI API 密鑰已設置。")
|
| 24 |
else:
|
| 25 |
-
|
| 26 |
|
| 27 |
# 確保向量資料庫目錄存在且有寫入權限
|
| 28 |
VECTORDB_DIR = os.path.abspath("./data")
|
| 29 |
os.makedirs(VECTORDB_DIR, exist_ok=True)
|
| 30 |
-
os.chmod(VECTORDB_DIR, 0o755)
|
| 31 |
-
logger.info(f"VECTORDB_DIR set to: {VECTORDB_DIR}")
|
| 32 |
-
|
| 33 |
-
# 定義測試 PDF 加載器的函數
|
| 34 |
-
def test_pdf_loader(file_path, loader_type='PyMuPDFLoader'):
|
| 35 |
-
logger.info(f"Testing PDF loader ({loader_type}) with file: {file_path}")
|
| 36 |
-
try:
|
| 37 |
-
if loader_type == 'PyMuPDFLoader':
|
| 38 |
-
loader = PyMuPDFLoader(file_path)
|
| 39 |
-
elif loader_type == 'PyPDFLoader':
|
| 40 |
-
loader = PyPDFLoader(file_path)
|
| 41 |
-
else:
|
| 42 |
-
logger.error(f"Unknown loader type: {loader_type}")
|
| 43 |
-
return
|
| 44 |
-
loaded_docs = loader.load()
|
| 45 |
-
if loaded_docs:
|
| 46 |
-
logger.info(f"Successfully loaded {file_path} with {len(loaded_docs)} documents.")
|
| 47 |
-
logger.info(f"Document content (first 500 chars): {loaded_docs[0].page_content[:500]}")
|
| 48 |
-
else:
|
| 49 |
-
logger.error(f"No documents loaded from {file_path}.")
|
| 50 |
-
except Exception as e:
|
| 51 |
-
logger.error(f"Error loading {file_path} with {loader_type}: {e}")
|
| 52 |
|
| 53 |
# 定義載入和處理 PDF 文件的函數
|
| 54 |
def load_and_process_documents(file_paths, loader_type='PyMuPDFLoader', api_key=None):
|
| 55 |
if not api_key:
|
| 56 |
raise ValueError("未提供 OpenAI API 密鑰。")
|
| 57 |
documents = []
|
| 58 |
-
logger.info("開始載入上傳的 PDF 文件。")
|
| 59 |
|
| 60 |
for file_path in file_paths:
|
| 61 |
-
logger.info(f"載入 PDF 文件: {file_path}")
|
| 62 |
if not os.path.exists(file_path):
|
| 63 |
-
logger.error(f"文件不存在: {file_path}")
|
| 64 |
continue
|
| 65 |
try:
|
| 66 |
if loader_type == 'PyMuPDFLoader':
|
|
@@ -68,28 +37,19 @@ def load_and_process_documents(file_paths, loader_type='PyMuPDFLoader', api_key=
|
|
| 68 |
elif loader_type == 'PyPDFLoader':
|
| 69 |
loader = PyPDFLoader(file_path)
|
| 70 |
else:
|
| 71 |
-
logger.error(f"Unknown loader type: {loader_type}")
|
| 72 |
continue
|
| 73 |
loaded_docs = loader.load()
|
| 74 |
if loaded_docs:
|
| 75 |
-
logger.info(f"載入 {file_path} 成功,包含 {len(loaded_docs)} 個文檔。")
|
| 76 |
-
# 打印第一個文檔的部分內容以確認
|
| 77 |
-
logger.info(f"第一個文檔內容: {loaded_docs[0].page_content[:500]}")
|
| 78 |
documents.extend(loaded_docs)
|
| 79 |
-
else:
|
| 80 |
-
logger.error(f"載入 {file_path} 但未找到任何文檔。")
|
| 81 |
except Exception as e:
|
| 82 |
-
|
| 83 |
|
| 84 |
if not documents:
|
| 85 |
raise ValueError("沒有找到任何 PDF 文件或 PDF 文件無法載入。")
|
| 86 |
-
else:
|
| 87 |
-
logger.info(f"總共載入了 {len(documents)} 個文檔。")
|
| 88 |
|
| 89 |
# 分割長文本
|
| 90 |
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=50)
|
| 91 |
documents = text_splitter.split_documents(documents)
|
| 92 |
-
logger.info(f"分割後的文檔數量: {len(documents)}")
|
| 93 |
|
| 94 |
if not documents:
|
| 95 |
raise ValueError("分割後的文檔列表為空。請檢查 PDF 文件內容。")
|
|
@@ -97,7 +57,6 @@ def load_and_process_documents(file_paths, loader_type='PyMuPDFLoader', api_key=
|
|
| 97 |
# 初始化向量資料庫
|
| 98 |
try:
|
| 99 |
embeddings = OpenAIEmbeddings(openai_api_key=api_key) # 使用使用者的 API 密鑰
|
| 100 |
-
logger.info("初始化 OpenAIEmbeddings 成功。")
|
| 101 |
except Exception as e:
|
| 102 |
raise ValueError(f"初始化 OpenAIEmbeddings 時出現錯誤: {e}")
|
| 103 |
|
|
@@ -107,7 +66,6 @@ def load_and_process_documents(file_paths, loader_type='PyMuPDFLoader', api_key=
|
|
| 107 |
embedding=embeddings,
|
| 108 |
persist_directory=VECTORDB_DIR
|
| 109 |
)
|
| 110 |
-
logger.info("初始化 Chroma 向量資料庫成功。")
|
| 111 |
except Exception as e:
|
| 112 |
raise ValueError(f"初始化 Chroma 向量資料庫時出現錯誤: {e}")
|
| 113 |
|
|
@@ -121,8 +79,8 @@ def handle_query(user_message, chat_history, vectordb, api_key):
|
|
| 121 |
|
| 122 |
# 添加角色指令前綴
|
| 123 |
preface = """
|
| 124 |
-
指令: 以繁體中文回答問題,200
|
| 125 |
-
|
| 126 |
"""
|
| 127 |
query = f"{preface} 查詢內容:{user_message}"
|
| 128 |
|
|
@@ -136,15 +94,13 @@ def handle_query(user_message, chat_history, vectordb, api_key):
|
|
| 136 |
# 呼叫模型並處理查詢
|
| 137 |
result = pdf_qa.invoke({"question": query, "chat_history": chat_history})
|
| 138 |
|
| 139 |
-
# 檢查結果並更新聊天歷史
|
| 140 |
if "answer" in result:
|
| 141 |
chat_history = chat_history + [(user_message, result["answer"])]
|
| 142 |
else:
|
| 143 |
-
chat_history = chat_history + [(user_message, "抱歉,未能獲得有效回應。")]
|
| 144 |
return chat_history
|
| 145 |
|
| 146 |
except Exception as e:
|
| 147 |
-
logger.error(f"Error in handle_query: {e}")
|
| 148 |
return chat_history + [("系統", f"出現錯誤: {str(e)}")]
|
| 149 |
|
| 150 |
# 定義保存 API 密鑰的函數
|
|
@@ -152,58 +108,27 @@ def save_api_key(api_key, state):
|
|
| 152 |
if not api_key.startswith("sk-"):
|
| 153 |
return "請輸入有效的 OpenAI API 密鑰。", state
|
| 154 |
state['api_key'] = api_key
|
| 155 |
-
logger.info("使用者已保存自己的 OpenAI API 密鑰。")
|
| 156 |
return "API 密鑰已成功保存。您現在可以上傳 PDF 文件並開始提問。", state
|
| 157 |
|
| 158 |
# 定義 Gradio 的處理函數
|
| 159 |
def process_files(files, state):
|
| 160 |
-
logger.info("process_files called")
|
| 161 |
if files:
|
| 162 |
try:
|
| 163 |
-
# 檢查是否已保存 API 密鑰
|
| 164 |
api_key = state.get('api_key', None)
|
| 165 |
if not api_key:
|
| 166 |
-
logger.error("使用者未提供 OpenAI API 密鑰。")
|
| 167 |
return "請先在「設定 API 密鑰」標籤中輸入並保存您的 OpenAI API 密鑰。", state
|
| 168 |
|
| 169 |
-
logger.info(f"Received {len(files)} files")
|
| 170 |
saved_file_paths = []
|
| 171 |
for idx, file_data in enumerate(files):
|
| 172 |
-
# 為每個文件分配唯一的文件名
|
| 173 |
filename = f"uploaded_{idx}.pdf"
|
| 174 |
save_path = os.path.join(VECTORDB_DIR, filename)
|
| 175 |
with open(save_path, "wb") as f:
|
| 176 |
f.write(file_data)
|
| 177 |
-
# 確認文件是否存在並檢查文件大小
|
| 178 |
-
if os.path.exists(save_path):
|
| 179 |
-
file_size = os.path.getsize(save_path)
|
| 180 |
-
if file_size > 0:
|
| 181 |
-
logger.info(f"File successfully saved to: {save_path} (Size: {file_size} bytes)")
|
| 182 |
-
else:
|
| 183 |
-
logger.error(f"File saved to {save_path} is empty.")
|
| 184 |
-
raise ValueError(f"上傳的文件 {filename} 為空。")
|
| 185 |
-
else:
|
| 186 |
-
logger.error(f"Failed to save file to: {save_path}")
|
| 187 |
-
raise FileNotFoundError(f"無法保存文件到 {save_path}")
|
| 188 |
saved_file_paths.append(save_path)
|
| 189 |
-
# 測試 PDF 加載器,先用 PyMuPDFLoader,再用 PyPDFLoader
|
| 190 |
-
try:
|
| 191 |
-
test_pdf_loader(save_path, loader_type='PyMuPDFLoader')
|
| 192 |
-
except Exception as e:
|
| 193 |
-
logger.error(f"PyMuPDFLoader failed: {e}")
|
| 194 |
-
logger.info("Attempting to load with PyPDFLoader...")
|
| 195 |
-
test_pdf_loader(save_path, loader_type='PyPDFLoader')
|
| 196 |
-
# 列出 VECTORDB_DIR 中的所有文件
|
| 197 |
-
saved_files = os.listdir(VECTORDB_DIR)
|
| 198 |
-
logger.info(f"Files in VECTORDB_DIR ({VECTORDB_DIR}): {saved_files}")
|
| 199 |
-
# 列出文件大小
|
| 200 |
-
file_sizes = {file: os.path.getsize(os.path.join(VECTORDB_DIR, file)) for file in saved_files}
|
| 201 |
-
logger.info(f"File sizes in VECTORDB_DIR: {file_sizes}")
|
| 202 |
vectordb = load_and_process_documents(saved_file_paths, loader_type='PyMuPDFLoader', api_key=api_key)
|
| 203 |
state['vectordb'] = vectordb
|
| 204 |
return "PDF 文件已成功上傳並處理。您現在可以開始提問。", state
|
| 205 |
except Exception as e:
|
| 206 |
-
logger.error(f"Error in process_files: {e}")
|
| 207 |
return f"處理文件時出現錯誤: {e}", state
|
| 208 |
else:
|
| 209 |
return "請上傳至少一個 PDF 文件。", state
|
|
@@ -216,15 +141,13 @@ def chat_interface(user_message, chat_history, state):
|
|
| 216 |
if not api_key:
|
| 217 |
return chat_history, state, "請先在「設定 API 密鑰」標籤中輸入並保存您的 OpenAI API 密鑰。"
|
| 218 |
|
| 219 |
-
# 處理查詢
|
| 220 |
updated_history = handle_query(user_message, chat_history, vectordb, api_key)
|
| 221 |
return updated_history, state, ""
|
| 222 |
|
| 223 |
# 設計 Gradio 介面
|
| 224 |
with gr.Blocks() as demo:
|
| 225 |
-
gr.Markdown("<h1 style='text-align: center;'
|
| 226 |
|
| 227 |
-
# 定義共享的 state
|
| 228 |
state = gr.State({"vectordb": None, "api_key": None})
|
| 229 |
|
| 230 |
with gr.Tab("設定 API 密鑰"):
|
|
@@ -239,50 +162,46 @@ with gr.Blocks() as demo:
|
|
| 239 |
save_api_key_btn = gr.Button("保存 API 密鑰")
|
| 240 |
api_key_status = gr.Textbox(label="狀態", interactive=False)
|
| 241 |
|
| 242 |
-
with gr.Tab("
|
| 243 |
with gr.Row():
|
| 244 |
with gr.Column(scale=1):
|
| 245 |
upload = gr.File(
|
| 246 |
file_count="multiple",
|
| 247 |
file_types=[".pdf"],
|
| 248 |
-
label="
|
| 249 |
interactive=True,
|
| 250 |
-
type="binary"
|
| 251 |
)
|
| 252 |
upload_btn = gr.Button("上傳並處理")
|
| 253 |
upload_status = gr.Textbox(label="上傳狀態", interactive=False)
|
| 254 |
|
| 255 |
-
with gr.Tab("
|
| 256 |
chatbot = gr.Chatbot()
|
| 257 |
|
| 258 |
with gr.Row():
|
| 259 |
with gr.Column(scale=0.85):
|
| 260 |
-
txt = gr.Textbox(show_label=False, placeholder="
|
| 261 |
with gr.Column(scale=0.15, min_width=0):
|
| 262 |
submit_btn = gr.Button("提問")
|
| 263 |
|
| 264 |
-
# 綁定提問按鈕
|
| 265 |
submit_btn.click(
|
| 266 |
chat_interface,
|
| 267 |
inputs=[txt, chatbot, state],
|
| 268 |
outputs=[chatbot, state, txt]
|
| 269 |
)
|
| 270 |
|
| 271 |
-
# 綁定輸入框的提交事件
|
| 272 |
txt.submit(
|
| 273 |
chat_interface,
|
| 274 |
inputs=[txt, chatbot, state],
|
| 275 |
outputs=[chatbot, state, txt]
|
| 276 |
)
|
| 277 |
|
| 278 |
-
# 綁定保存 API 密鑰按鈕
|
| 279 |
save_api_key_btn.click(
|
| 280 |
save_api_key,
|
| 281 |
inputs=[api_key_input, state],
|
| 282 |
outputs=[api_key_status, state]
|
| 283 |
)
|
| 284 |
|
| 285 |
-
# 綁定上傳按鈕
|
| 286 |
upload_btn.click(
|
| 287 |
process_files,
|
| 288 |
inputs=[upload, state],
|
|
@@ -290,4 +209,5 @@ with gr.Blocks() as demo:
|
|
| 290 |
)
|
| 291 |
|
| 292 |
# 啟動 Gradio 應用
|
| 293 |
-
demo.launch()
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import os
|
| 2 |
import openai
|
| 3 |
import gradio as gr
|
|
|
|
| 10 |
import shutil # 用於文件複製
|
| 11 |
import logging
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
# 獲取 OpenAI API 密鑰(初始不使用固定密鑰)
|
| 14 |
api_key_env = os.getenv("OPENAI_API_KEY")
|
| 15 |
if api_key_env:
|
| 16 |
openai.api_key = api_key_env
|
|
|
|
| 17 |
else:
|
| 18 |
+
print("未設置固定的 OpenAI API 密鑰。將使用使用者提供的密鑰。")
|
| 19 |
|
| 20 |
# 確保向量資料庫目錄存在且有寫入權限
|
| 21 |
VECTORDB_DIR = os.path.abspath("./data")
|
| 22 |
os.makedirs(VECTORDB_DIR, exist_ok=True)
|
| 23 |
+
os.chmod(VECTORDB_DIR, 0o755)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
# 定義載入和處理 PDF 文件的函數
|
| 26 |
def load_and_process_documents(file_paths, loader_type='PyMuPDFLoader', api_key=None):
|
| 27 |
if not api_key:
|
| 28 |
raise ValueError("未提供 OpenAI API 密鑰。")
|
| 29 |
documents = []
|
|
|
|
| 30 |
|
| 31 |
for file_path in file_paths:
|
|
|
|
| 32 |
if not os.path.exists(file_path):
|
|
|
|
| 33 |
continue
|
| 34 |
try:
|
| 35 |
if loader_type == 'PyMuPDFLoader':
|
|
|
|
| 37 |
elif loader_type == 'PyPDFLoader':
|
| 38 |
loader = PyPDFLoader(file_path)
|
| 39 |
else:
|
|
|
|
| 40 |
continue
|
| 41 |
loaded_docs = loader.load()
|
| 42 |
if loaded_docs:
|
|
|
|
|
|
|
|
|
|
| 43 |
documents.extend(loaded_docs)
|
|
|
|
|
|
|
| 44 |
except Exception as e:
|
| 45 |
+
continue
|
| 46 |
|
| 47 |
if not documents:
|
| 48 |
raise ValueError("沒有找到任何 PDF 文件或 PDF 文件無法載入。")
|
|
|
|
|
|
|
| 49 |
|
| 50 |
# 分割長文本
|
| 51 |
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=50)
|
| 52 |
documents = text_splitter.split_documents(documents)
|
|
|
|
| 53 |
|
| 54 |
if not documents:
|
| 55 |
raise ValueError("分割後的文檔列表為空。請檢查 PDF 文件內容。")
|
|
|
|
| 57 |
# 初始化向量資料庫
|
| 58 |
try:
|
| 59 |
embeddings = OpenAIEmbeddings(openai_api_key=api_key) # 使用使用者的 API 密鑰
|
|
|
|
| 60 |
except Exception as e:
|
| 61 |
raise ValueError(f"初始化 OpenAIEmbeddings 時出現錯誤: {e}")
|
| 62 |
|
|
|
|
| 66 |
embedding=embeddings,
|
| 67 |
persist_directory=VECTORDB_DIR
|
| 68 |
)
|
|
|
|
| 69 |
except Exception as e:
|
| 70 |
raise ValueError(f"初始化 Chroma 向量資料庫時出現錯誤: {e}")
|
| 71 |
|
|
|
|
| 79 |
|
| 80 |
# 添加角色指令前綴
|
| 81 |
preface = """
|
| 82 |
+
指令: 以繁體中文回答問題,200字以內。你是一位勞動法專家,針對員工權益與合同條款等法律問題進行回應。
|
| 83 |
+
非相關問題,請回應:「目前僅支援勞動法相關問題。」。
|
| 84 |
"""
|
| 85 |
query = f"{preface} 查詢內容:{user_message}"
|
| 86 |
|
|
|
|
| 94 |
# 呼叫模型並處理查詢
|
| 95 |
result = pdf_qa.invoke({"question": query, "chat_history": chat_history})
|
| 96 |
|
|
|
|
| 97 |
if "answer" in result:
|
| 98 |
chat_history = chat_history + [(user_message, result["answer"])]
|
| 99 |
else:
|
| 100 |
+
chat_history = chat_history + [(user_message, "抱歉,未能獲得有效回應。")]
|
| 101 |
return chat_history
|
| 102 |
|
| 103 |
except Exception as e:
|
|
|
|
| 104 |
return chat_history + [("系統", f"出現錯誤: {str(e)}")]
|
| 105 |
|
| 106 |
# 定義保存 API 密鑰的函數
|
|
|
|
| 108 |
if not api_key.startswith("sk-"):
|
| 109 |
return "請輸入有效的 OpenAI API 密鑰。", state
|
| 110 |
state['api_key'] = api_key
|
|
|
|
| 111 |
return "API 密鑰已成功保存。您現在可以上傳 PDF 文件並開始提問。", state
|
| 112 |
|
| 113 |
# 定義 Gradio 的處理函數
|
| 114 |
def process_files(files, state):
|
|
|
|
| 115 |
if files:
|
| 116 |
try:
|
|
|
|
| 117 |
api_key = state.get('api_key', None)
|
| 118 |
if not api_key:
|
|
|
|
| 119 |
return "請先在「設定 API 密鑰」標籤中輸入並保存您的 OpenAI API 密鑰。", state
|
| 120 |
|
|
|
|
| 121 |
saved_file_paths = []
|
| 122 |
for idx, file_data in enumerate(files):
|
|
|
|
| 123 |
filename = f"uploaded_{idx}.pdf"
|
| 124 |
save_path = os.path.join(VECTORDB_DIR, filename)
|
| 125 |
with open(save_path, "wb") as f:
|
| 126 |
f.write(file_data)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
saved_file_paths.append(save_path)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
vectordb = load_and_process_documents(saved_file_paths, loader_type='PyMuPDFLoader', api_key=api_key)
|
| 129 |
state['vectordb'] = vectordb
|
| 130 |
return "PDF 文件已成功上傳並處理。您現在可以開始提問。", state
|
| 131 |
except Exception as e:
|
|
|
|
| 132 |
return f"處理文件時出現錯誤: {e}", state
|
| 133 |
else:
|
| 134 |
return "請上傳至少一個 PDF 文件。", state
|
|
|
|
| 141 |
if not api_key:
|
| 142 |
return chat_history, state, "請先在「設定 API 密鑰」標籤中輸入並保存您的 OpenAI API 密鑰。"
|
| 143 |
|
|
|
|
| 144 |
updated_history = handle_query(user_message, chat_history, vectordb, api_key)
|
| 145 |
return updated_history, state, ""
|
| 146 |
|
| 147 |
# 設計 Gradio 介面
|
| 148 |
with gr.Blocks() as demo:
|
| 149 |
+
gr.Markdown("<h1 style='text-align: center;'>勞動法智能諮詢系統</h1>")
|
| 150 |
|
|
|
|
| 151 |
state = gr.State({"vectordb": None, "api_key": None})
|
| 152 |
|
| 153 |
with gr.Tab("設定 API 密鑰"):
|
|
|
|
| 162 |
save_api_key_btn = gr.Button("保存 API 密鑰")
|
| 163 |
api_key_status = gr.Textbox(label="狀態", interactive=False)
|
| 164 |
|
| 165 |
+
with gr.Tab("上傳勞動法 PDF 文件"):
|
| 166 |
with gr.Row():
|
| 167 |
with gr.Column(scale=1):
|
| 168 |
upload = gr.File(
|
| 169 |
file_count="multiple",
|
| 170 |
file_types=[".pdf"],
|
| 171 |
+
label="上傳勞動法 PDF 文件",
|
| 172 |
interactive=True,
|
| 173 |
+
type="binary"
|
| 174 |
)
|
| 175 |
upload_btn = gr.Button("上傳並處理")
|
| 176 |
upload_status = gr.Textbox(label="上傳狀態", interactive=False)
|
| 177 |
|
| 178 |
+
with gr.Tab("智能諮詢"):
|
| 179 |
chatbot = gr.Chatbot()
|
| 180 |
|
| 181 |
with gr.Row():
|
| 182 |
with gr.Column(scale=0.85):
|
| 183 |
+
txt = gr.Textbox(show_label=False, placeholder="請輸入您的法律問題...")
|
| 184 |
with gr.Column(scale=0.15, min_width=0):
|
| 185 |
submit_btn = gr.Button("提問")
|
| 186 |
|
|
|
|
| 187 |
submit_btn.click(
|
| 188 |
chat_interface,
|
| 189 |
inputs=[txt, chatbot, state],
|
| 190 |
outputs=[chatbot, state, txt]
|
| 191 |
)
|
| 192 |
|
|
|
|
| 193 |
txt.submit(
|
| 194 |
chat_interface,
|
| 195 |
inputs=[txt, chatbot, state],
|
| 196 |
outputs=[chatbot, state, txt]
|
| 197 |
)
|
| 198 |
|
|
|
|
| 199 |
save_api_key_btn.click(
|
| 200 |
save_api_key,
|
| 201 |
inputs=[api_key_input, state],
|
| 202 |
outputs=[api_key_status, state]
|
| 203 |
)
|
| 204 |
|
|
|
|
| 205 |
upload_btn.click(
|
| 206 |
process_files,
|
| 207 |
inputs=[upload, state],
|
|
|
|
| 209 |
)
|
| 210 |
|
| 211 |
# 啟動 Gradio 應用
|
| 212 |
+
demo.launch()
|
| 213 |
+
|