Update app.py

app.py

@@ -1,64 +1,60 @@
+import getpass
+import os
 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")
+if "GOOGLE_API_KEY" not in os.environ:
+    os.environ["GOOGLE_API_KEY"] = "AIzaSyDJ4vIKuIBIPNHATLxnoHlagXWbsAz-vRs"
+key = "AIzaSyDJ4vIKuIBIPNHATLxnoHlagXWbsAz-vRs"
 
+###
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Cấu hình API key cho Google GenAI
+genai.configure(api_key=key)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+### loop cho tất cả các file tài liệu và cộng lại thành final_all_split (nhét vào 1 database)
 
-    messages.append({"role": "user", "content": message})
+folder_path = '/content/drive/MyDrive/Trường Công nghệ'
+docx_files = list_docx_files(folder_path)
 
-    response = ""
+all_splits = []  # Khởi tạo danh sách lưu kết quả
+for i, file_path in enumerate(tqdm(docx_files, desc="Đang xử lý", unit="file")):
+    output_json_path = f"output_{i}.json"
+    splits = get_splits(file_path, output_json_path)
+    all_splits += splits
 
-    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
+# output_json_path = "output_{i}.json"
+# splits = get_splits(docx_files, output_json_path)
+# all_splits += splits
 
-        response += token
-        yield response
+FAQ_path = '/content/drive/MyDrive/Trường Công nghệ/FAQ.json'
+FAQ_splits = get_json_splits_only(FAQ_path)
+all_splits += FAQ_splits
 
+# web_path = 'https'
+# web_splits = await get_urls_splits(url='https://nct.neu.edu.vn/')
+# all_splits += web_splits
 
-"""
-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)",
-        ),
-    ],
-)
+# Lưu vào vectorstore với nhúng từ GenAI (Cần chỉ định model)
+embedding = GoogleGenerativeAIEmbeddings(model="models/text-embedding-004")
+vectorstore = FAISS.from_documents(documents=all_splits, embedding=embedding)
 
+###
 
-if __name__ == "__main__":
-    demo.launch()
+institutions = ['Tất cả'] + ['Trường Công Nghệ']
+categories = ['Tất cả'] + ['Đề án', 'Chương trình đào tạo']
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        category1 = gr.Dropdown(choices = institutions, label="Trường", value = 'Tất cả')
+        category2 = gr.Dropdown(choices = categories, label="Bạn quan tâm tới", value = 'Tất cả')
+
+    chat_interface = gr.ChatInterface(get_answer,
+                                      textbox=gr.Textbox(placeholder="Đặt câu hỏi tại đây",
+                                                        container=False,
+                                                        autoscroll=True,
+                                                        scale=7),
+                                      # textbox=prompt,
+                                      # additional_inputs=[category1, category2]
+                                      )
+
+demo.launch