Upload 4 files

README.md

@@ -1,5 +1,5 @@
 ---
-title: International Chefs Teach You How To Cook
+title: Rag Chatbot
 emoji: 💬
 colorFrom: yellow
 colorTo: purple
@@ -7,7 +7,6 @@ sdk: gradio
 sdk_version: 5.0.1
 app_file: app.py
 pinned: false
-short_description: 國際大廚教你做菜
 ---
 
 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

@@ -1,64 +1,82 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain.chains import ConversationalRetrievalChain
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.document_loaders import PyPDFLoader
+from langchain.vectorstores import Chroma
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings.openai import OpenAIEmbeddings
 
-"""
-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")
+vectordb = None
 
+# 處理 PDF 文件並初始化向量數據庫
+def load_and_process_pdf(pdf_file, api_key):
+    try:
+        loader = PyPDFLoader(pdf_file.name)
+        documents = loader.load()
+        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+        docs = text_splitter.split_documents(documents)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+        # 傳遞 API Key
+        embeddings = OpenAIEmbeddings(openai_api_key=api_key)
+        vectordb = Chroma.from_documents(docs, embedding=embeddings, persist_directory="./data")
+        return vectordb
+    except Exception as e:
+        return f"無法處理文件，錯誤: {str(e)}"
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# 查詢處理函數
+def handle_query(api_key, user_message, pdf_vectordb, chat_history):
+    if not pdf_vectordb or isinstance(pdf_vectordb, str):
+        return chat_history, "請先上傳有效的 PDF 文件。"
 
-    messages.append({"role": "user", "content": message})
+    try:
+        retriever = pdf_vectordb.as_retriever(search_kwargs={"k": 5})
+        pdf_qa_chain = ConversationalRetrievalChain.from_llm(
+            ChatOpenAI(temperature=0.7, model_name="gpt-4", openai_api_key=api_key),
+            retriever=retriever
+        )
+        result = pdf_qa_chain({"question": user_message, "chat_history": chat_history})
+        answer = result.get("answer", "抱歉，我無法提供答案。")
+        chat_history.append((user_message, answer))
+        return chat_history, answer
+    except Exception as e:
+        return chat_history, f"出現錯誤: {str(e)}"
 
-    response = ""
+# 當用戶上傳 PDF 時處理
+def process_pdf_upload(api_key, pdf_file):
+    global vectordb
+    vectordb = load_and_process_pdf(pdf_file, api_key)
+    if isinstance(vectordb, str):
+        return vectordb
+    return "PDF 已成功載入！請開始提問。"
 
-    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
+# 主程式 - Gradio 介面
+with gr.Blocks() as demo:
+    gr.Markdown("## 📘 AI 文件助理 - 支援 PDF 問答")
 
-        response += token
-        yield response
+    with gr.Row():
+        api_key = gr.Textbox(label="🔑 請輸入您的 OpenAI API Key", type="password")
+        pdf_file = gr.File(label="📂 上傳 PDF 文件", file_types=[".pdf"])
 
+    chatbot = gr.Chatbot(label="💬 聊天區")
+    state = gr.State([])
 
-"""
-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)",
-        ),
-    ],
-)
+    with gr.Row():
+        user_input = gr.Textbox(show_label=False, placeholder="請輸入問題...", lines=2)
+        send_btn = gr.Button("提交問題")
 
+    response = gr.Textbox(label="📢 回應", interactive=False, lines=4)
 
-if __name__ == "__main__":
-    demo.launch()
+    pdf_file.change(process_pdf_upload, inputs=[api_key, pdf_file], outputs=response)
+
+    def handle_user_input(api_key, user_message, chat_history):
+        if not vectordb:
+            return chat_history, "請先上傳 PDF 文件。"
+        if user_message.strip().lower() == "謝謝":
+            return chat_history, "加油~~~"
+        return handle_query(api_key, user_message, vectordb, chat_history)
+
+    send_btn.click(handle_user_input, inputs=[api_key, user_input, state], outputs=[chatbot, response])
+    user_input.submit(handle_user_input, inputs=[api_key, user_input, state], outputs=[chatbot, response])
+
+demo.launch()

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -1 +1,12 @@
-huggingface_hub==0.25.2
+#requirements
+gradio
+langchain
+langchain-community
+langchain-openai
+openai
+chromadb
+PyPDF2
+pypdf
+docx2txt
+python-dotenv
+python-docx