Update app.py

app.py

@@ -1,64 +1,51 @@
+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")
-
-
-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
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import requests
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.document_loaders import UnstructuredHTMLLoader
+from langchain.text_splitter import CharacterTextSplitter
+
+# API Key 從環境變數讀取
+GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
+GROQ_MODEL = "gemma2-9b-it"
+
+embedding_model = HuggingFaceEmbeddings(model_name="BAAI/bge-base-zh")
+text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=100)
+
+def build_vector_db_from_local_html(folder_path="data"):
+    all_docs = []
+    for filename in os.listdir(folder_path):
+        if filename.endswith(".html"):
+            loader = UnstructuredHTMLLoader(os.path.join(folder_path, filename))
+            docs = loader.load()
+            chunks = text_splitter.split_documents(docs)
+            all_docs.extend(chunks)
+    db = FAISS.from_documents(all_docs, embedding_model)
+    return db
+
+db = build_vector_db_from_local_html()
+
+def rag_chat(user_input):
+    docs = db.similarity_search(user_input, k=3)
+    context = "\n\n".join([doc.page_content for doc in docs])
+    messages = [
+        {"role": "system", "content": "你是一個親切的諮詢師，幫助使用者了解數位性暴力並提供協助。請使用繁體中文回答。"},
+        {"role": "user", "content": f"以下是相關資料：\n{context}\n\n請回答這個問題：{user_input}"}
+    ]
+    headers = {"Authorization": f"Bearer {GROQ_API_KEY}", "Content-Type": "application/json"}
+    payload = {"model": GROQ_MODEL, "messages": messages}
+    try:
+        res = requests.post("https://api.groq.com/openai/v1/chat/completions", headers=headers, json=payload)
+        res.raise_for_status()
+        return res.json()["choices"][0]["message"]["content"]
+    except Exception as e:
+        return f"錯誤：{str(e)}"
+
+iface = gr.Interface(fn=rag_chat,
+                     inputs=gr.Textbox(label="輸入你的問題", placeholder="請輸入問題...", lines=3),
+                     outputs="text",
+                     title="AI諮詢機器人",
+                     description="詢問我關於數位性暴力的事情，或者你遇到甚麼困境？")
+
+iface.launch()