Merge pull request #703 from Krabulek/week-5-contributions

Week 5 Excercise - DocSearch with Gemini for Notion exported workspace

week5/community-contributions/DocSearch_Notion/DocSearch_notion_gemini.ipynb

@@ -0,0 +1,333 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Personal Knowledge Worker\n",
+    "\n",
+    "Search through your exported Notion Workspace with Gemini models using RAG.\n",
+    "\n",
+    "How to export the content from Notion: https://www.notion.com/help/export-your-content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports and Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -U -q langchain-google-genai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import re\n",
+    "import glob\n",
+    "from dotenv import load_dotenv\n",
+    "import gradio as gr\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import DirectoryLoader, TextLoader\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.schema import Document\n",
+    "from langchain_chroma import Chroma\n",
+    "from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain.chains import ConversationalRetrievalChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "LLM_MODEL = \"gemini-2.5-flash-lite\"\n",
+    "EMBEDDINGS_MODEL = \"models/gemini-embedding-001\"\n",
+    "db_name = \"vector_db\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv()\n",
+    "os.environ['GOOGLE_API_KEY'] = os.getenv('GOOGLE_API_KEY', 'your-key-if-not-using-env')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Vector DB Setup"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Clean up and Load Documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Clean up the Notion directory, remove MD5 hashes from filenames and directory names\n",
+    "\n",
+    "# Root directory of your export\n",
+    "root_dir = \"notion_export\"\n",
+    "\n",
+    "# Regex to match the hash: space + 24-32 hex chars (sometimes longer)\n",
+    "hash_pattern = re.compile(r\"\\s[0-9a-f]{16,32}(_all)?\")\n",
+    "\n",
+    "for dirpath, dirnames, filenames in os.walk(root_dir, topdown=False):\n",
+    "    # Rename files\n",
+    "    for filename in filenames:\n",
+    "        new_name = re.sub(hash_pattern, \"\", filename)\n",
+    "        if new_name != filename:\n",
+    "            old_path = os.path.join(dirpath, filename)\n",
+    "            new_path = os.path.join(dirpath, new_name)\n",
+    "            print(f\"Renaming file: {old_path} -> {new_path}\")\n",
+    "            os.rename(old_path, new_path)\n",
+    "\n",
+    "    # Rename directories\n",
+    "    for dirname in dirnames:\n",
+    "        new_name = re.sub(hash_pattern, \"\", dirname)\n",
+    "        if new_name != dirname:\n",
+    "            old_path = os.path.join(dirpath, dirname)\n",
+    "            new_path = os.path.join(dirpath, new_name)\n",
+    "            print(f\"Renaming dir: {old_path} -> {new_path}\")\n",
+    "            os.rename(old_path, new_path)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Read in documents using LangChain's loaders\n",
+    "\n",
+    "documents = []\n",
+    "for dirpath, dirnames, filenames in os.walk(root_dir):\n",
+    "    # Define doc_type relative to root_dir\n",
+    "    doc_type = os.path.relpath(dirpath, root_dir)\n",
+    "\n",
+    "    # for main pages in Notion\n",
+    "    if doc_type == \".\":\n",
+    "        doc_type = \"Main\"\n",
+    "    \n",
+    "    loader = DirectoryLoader(\n",
+    "        dirpath,\n",
+    "        glob=\"**/*.md\",  # recursive match inside dirpath\n",
+    "        loader_cls=TextLoader\n",
+    "    )\n",
+    "    \n",
+    "    folder_docs = loader.load()\n",
+    "    for doc in folder_docs:\n",
+    "        doc.metadata[\"doc_type\"] = doc_type\n",
+    "        documents.append(doc)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create chunks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text_splitter = CharacterTextSplitter(chunk_size=800, chunk_overlap=200)\n",
+    "chunks = text_splitter.split_documents(documents)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(chunks)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_types = set(chunk.metadata['doc_type'] for chunk in chunks)\n",
+    "print(f\"Document types found: {', '.join(doc_types)}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create Embeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = GoogleGenerativeAIEmbeddings(model=EMBEDDINGS_MODEL)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# If you don't want to recreate the collection\n",
+    "\n",
+    "vectorstore = Chroma(embedding_function=embeddings, persist_directory=db_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check if a Chroma Datastore already exists - if so, delete the collection to start from scratch\n",
+    "\n",
+    "if os.path.exists(db_name):\n",
+    "    Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()\n",
+    "\n",
+    "# Create our Chroma vectorstore!\n",
+    "\n",
+    "vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)\n",
+    "print(f\"Vectorstore created with {vectorstore._collection.count()} documents\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get one vector and find how many dimensions it has\n",
+    "\n",
+    "collection = vectorstore._collection\n",
+    "sample_embedding = collection.get(limit=1, include=[\"embeddings\"])[\"embeddings\"][0]\n",
+    "dimensions = len(sample_embedding)\n",
+    "print(f\"The vectors have {dimensions:,} dimensions\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## RAG pipeline using LangChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create a new Chat with ChatGoogleGenerativeAI\n",
+    "llm = ChatGoogleGenerativeAI(model=LLM_MODEL, temperature=0.7)\n",
+    "\n",
+    "# set up the conversation memory for the chat\n",
+    "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
+    "\n",
+    "# the retriever is an abstraction over the VectorStore that will be used during RAG\n",
+    "retriever = vectorstore.as_retriever()\n",
+    "\n",
+    "# putting it together: set up the conversation chain with the GPT 4o-mini LLM, the vector store and memory\n",
+    "conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Gradio User Interface"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def chat(message, history):\n",
+    "    result = conversation_chain.invoke({\"question\": message})\n",
+    "    return result[\"answer\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "view = gr.ChatInterface(chat, type=\"messages\").launch(inbrowser=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}