Upload 4 files

README.md

@@ -1,13 +1,17 @@
----
-title: Multi Dataset Rag Chatbot
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 5.0.1
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-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).
+# RAG Chatbot với Gemini
+
+Chatbot sử dụng Retrieval-Augmented Generation (RAG) với Gemini API.
+
+## Cài đặt
+
+1. Clone repo
+2. Cài đặt dependencies: `pip install -r requirements.txt`
+3. Thêm Gemini API key vào file `.env`
+4. Đặt dataset vào `data/your_dataset.txt`
+5. Chạy: `python app.py`
+
+## Deploy lên Hugging Face Spaces
+
+1. Tạo Space mới trên Hugging Face
+2. Upload tất cả files
+3. Thêm secret GEMINI_API_KEY trong Settings

app.py

@@ -1,64 +1,62 @@
-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 gradio as gr
+import os
+from utils.embeddings import EmbeddingModel
+from utils.vector_store import VectorStore
+from utils.rag_chain import RAGChain
+from config import CHUNK_SIZE, CHUNK_OVERLAP
+
+# Initialize components
+embedding_model = EmbeddingModel()
+vector_store = VectorStore()
+vector_store.create_collection()
+
+def load_and_process_data(file_path):
+    """Load và xử lý dataset"""
+    with open(file_path, 'r', encoding='utf-8') as f:
+        text = f.read()
+    
+    # Chia thành chunks
+    chunks = []
+    for i in range(0, len(text), CHUNK_SIZE - CHUNK_OVERLAP):
+        chunk = text[i:i + CHUNK_SIZE]
+        chunks.append(chunk)
+    
+    # Tạo embeddings
+    embeddings = embedding_model.embed_documents(chunks)
+    
+    # Lưu vào vector store
+    vector_store.add_documents(chunks, embeddings)
+    
+    return len(chunks)
+
+# Load data khi khởi động
+if os.path.exists("data/your_dataset.txt"):
+    num_chunks = load_and_process_data("data/your_dataset.txt")
+    print(f"Đã load {num_chunks} chunks")
+
+# Initialize RAG chain
+rag_chain = RAGChain(vector_store, embedding_model)
+
+def chatbot_response(message, history):
+    """Xử lý tin nhắn và trả về response"""
+    try:
+        response = rag_chain.get_answer(message)
+        return response
+    except Exception as e:
+        return f"Lỗi: {str(e)}"
+
+# Tạo Gradio interface
+demo = gr.ChatInterface(
+    fn=chatbot_response,
+    title="RAG Chatbot với Gemini",
+    description="Chatbot sử dụng RAG (Retrieval-Augmented Generation) với Gemini API",
+    examples=[
+        "Xin chào!",
+        "Hãy giải thích về RAG",
+        "Thông tin trong dataset là gì?"
+    ],
+    theme="soft"
+)
+
+if __name__ == "__main__":
+    demo.launch()

config.py

@@ -0,0 +1,13 @@
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Gemini API Key (lấy free tại https://makersuite.google.com/app/apikey)
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY", "your-api-key-here")
+
+# Model settings
+EMBEDDING_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
+GEMINI_MODEL = "gemini-pro"
+CHUNK_SIZE = 500
+CHUNK_OVERLAP = 50

requirements.txt

@@ -1 +1,7 @@
-huggingface_hub==0.25.2
+gradio==4.16.0
+google-generativeai==0.3.2
+langchain==0.1.0
+langchain-google-genai==0.0.5
+chromadb==0.4.22
+sentence-transformers==2.2.2
+python-dotenv==1.0.0