{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "fdfc1b2a",
   "metadata": {},
   "source": [
    "## 1. Install Required Packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "e0f621d9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "📦 Installing required packages...\n",
      "✅ All packages installed!\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "import subprocess\n",
    "\n",
    "# Install packages (works in VS Code Jupyter)\n",
    "packages = [\n",
    "    'langchain-community',\n",
    "    'sentence-transformers',\n",
    "    'transformers',\n",
    "    'faiss-cpu',\n",
    "    'pypdf',\n",
    "    'google-generativeai',\n",
    "    'langchain-huggingface',\n",
    "    'langchain-text-splitters',\n",
    "    'fastapi',\n",
    "    'uvicorn',\n",
    "    'nest-asyncio'\n",
    "]\n",
    "\n",
    "print(\"📦 Installing required packages...\")\n",
    "subprocess.check_call([sys.executable, '-m', 'pip', 'install', '-q'] + packages)\n",
    "print(\"✅ All packages installed!\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6c5a12c2",
   "metadata": {},
   "source": [
    "## 2. Setup Local Directories (Windows)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "fbe27891",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ Local directories created!\n",
      "📁 RAG data will be stored at: /content/rag_data\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "# Use local directories instead of Google Drive\n",
    "RAG_DIR = os.path.join(os.getcwd(), 'rag_data')\n",
    "FAISS_PATH = os.path.join(RAG_DIR, 'faiss_index')\n",
    "PDFS_PATH = os.path.join(RAG_DIR, 'pdfs')\n",
    "\n",
    "os.makedirs(FAISS_PATH, exist_ok=True)\n",
    "os.makedirs(PDFS_PATH, exist_ok=True)\n",
    "\n",
    "print(f\"✅ Local directories created!\")\n",
    "print(f\"📁 RAG data will be stored at: {RAG_DIR}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b75dabae",
   "metadata": {},
   "source": [
    "## 3. Configure Gemini API Key"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "330b1f65",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ Gemini API configured!\n"
     ]
    }
   ],
   "source": [
    "import google.generativeai as genai\n",
    "\n",
    "# Replace with your API key\n",
    "GOOGLE_API_KEY = \"AIzaSyC7tkb3uFgmh8YSuOVHYgIDywyL2lzICBA\"  # Get from https://makersuite.google.com/app/apikey\n",
    "\n",
    "genai.configure(api_key=GOOGLE_API_KEY)\n",
    "print(\"✅ Gemini API configured!\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49f2b49c",
   "metadata": {},
   "source": [
    "## 4. RAG Functions - Load, Process, Query"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "c296fc8b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ RAG functions defined!\n"
     ]
    }
   ],
   "source": [
    "import unicodedata\n",
    "import re\n",
    "from typing import List, Dict\n",
    "from langchain_community.document_loaders.pdf import PyPDFLoader\n",
    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
    "from langchain_huggingface import HuggingFaceEmbeddings\n",
    "from langchain_community.vectorstores import FAISS\n",
    "\n",
    "# Global variables\n",
    "vectordb = None\n",
    "retriever = None\n",
    "embeddings = None\n",
    "rag_initialized = False\n",
    "uploaded_documents = []\n",
    "\n",
    "\n",
    "def initialize_embeddings():\n",
    "    \"\"\"Initialize multilingual embedding model\"\"\"\n",
    "    global embeddings\n",
    "    \n",
    "    if embeddings is not None:\n",
    "        return embeddings\n",
    "    \n",
    "    print(\"Loading multilingual embedding model...\")\n",
    "    embeddings = HuggingFaceEmbeddings(\n",
    "        model_name=\"sentence-transformers/paraphrase-multilingual-mpnet-base-v2\"\n",
    "    )\n",
    "    print(\"✅ Embedding model loaded!\")\n",
    "    return embeddings\n",
    "\n",
    "\n",
    "def clean_text(text: str) -> str:\n",
    "    \"\"\"Clean and normalize text\"\"\"\n",
    "    if not isinstance(text, str) or not text.strip():\n",
    "        return \"\"\n",
    "    \n",
    "    normalized_text = unicodedata.normalize('NFKC', text)\n",
    "    cleaned_chars = [\n",
    "        char for char in normalized_text\n",
    "        if unicodedata.category(char) not in ['So', 'Cn', 'Cc', 'Cf', 'Cs']\n",
    "    ]\n",
    "    cleaned_text = \"\".join(cleaned_chars)\n",
    "    cleaned_text = re.sub(r'\\s+', ' ', cleaned_text).strip()\n",
    "    return cleaned_text\n",
    "\n",
    "\n",
    "def load_and_process_pdf(pdf_path: str) -> List:\n",
    "    \"\"\"Load PDF and split into chunks\"\"\"\n",
    "    print(f\"Loading PDF: {pdf_path}\")\n",
    "    \n",
    "    loader = PyPDFLoader(pdf_path)\n",
    "    docs = loader.load()\n",
    "    \n",
    "    splitter = RecursiveCharacterTextSplitter(\n",
    "        chunk_size=300,\n",
    "        chunk_overlap=80\n",
    "    )\n",
    "    chunks = splitter.split_documents(docs)\n",
    "    \n",
    "    print(f\"✅ Loaded {len(docs)} pages, created {len(chunks)} chunks\")\n",
    "    return chunks\n",
    "\n",
    "\n",
    "def create_vector_store(chunks: List) -> bool:\n",
    "    \"\"\"Create or update FAISS vector store\"\"\"\n",
    "    global vectordb, retriever, rag_initialized\n",
    "    \n",
    "    initialize_embeddings()\n",
    "    \n",
    "    texts = [doc.page_content for doc in chunks]\n",
    "    metadatas = [doc.metadata for doc in chunks]\n",
    "    \n",
    "    processed_texts = []\n",
    "    processed_metadatas = []\n",
    "    \n",
    "    for i, text in enumerate(texts):\n",
    "        cleaned_text = clean_text(text)\n",
    "        if cleaned_text:\n",
    "            processed_texts.append(cleaned_text)\n",
    "            processed_metadatas.append(metadatas[i])\n",
    "    \n",
    "    if not processed_texts:\n",
    "        print(\"⚠ No valid texts after cleaning\")\n",
    "        return False\n",
    "    \n",
    "    print(f\"Creating embeddings for {len(processed_texts)} chunks...\")\n",
    "    \n",
    "    if vectordb is None:\n",
    "        vectordb = FAISS.from_texts(processed_texts, embeddings, metadatas=processed_metadatas)\n",
    "    else:\n",
    "        new_vectordb = FAISS.from_texts(processed_texts, embeddings, metadatas=processed_metadatas)\n",
    "        vectordb.merge_from(new_vectordb)\n",
    "    \n",
    "    retriever = vectordb.as_retriever(search_kwargs={\"k\": 4})\n",
    "    rag_initialized = True\n",
    "    \n",
    "    # Save to Google Drive\n",
    "    save_vector_store()\n",
    "    \n",
    "    print(\"✅ Vector store created/updated!\")\n",
    "    return True\n",
    "\n",
    "\n",
    "def save_vector_store():\n",
    "    \"\"\"Save FAISS index to Google Drive\"\"\"\n",
    "    if vectordb is None:\n",
    "        return\n",
    "    \n",
    "    vectordb.save_local(FAISS_PATH)\n",
    "    print(f\"✅ Vector store saved to Google Drive: {FAISS_PATH}\")\n",
    "\n",
    "\n",
    "def load_vector_store() -> bool:\n",
    "    \"\"\"Load FAISS index from Google Drive\"\"\"\n",
    "    global vectordb, retriever, rag_initialized\n",
    "    \n",
    "    if not os.path.exists(FAISS_PATH):\n",
    "        print(\"ℹ No existing vector store found\")\n",
    "        return False\n",
    "    \n",
    "    try:\n",
    "        initialize_embeddings()\n",
    "        vectordb = FAISS.load_local(\n",
    "            FAISS_PATH, \n",
    "            embeddings,\n",
    "            allow_dangerous_deserialization=True\n",
    "        )\n",
    "        retriever = vectordb.as_retriever(search_kwargs={\"k\": 4})\n",
    "        rag_initialized = True\n",
    "        print(\"✅ Loaded existing vector store from Google Drive\")\n",
    "        return True\n",
    "    except Exception as e:\n",
    "        print(f\"⚠ Failed to load vector store: {e}\")\n",
    "        return False\n",
    "\n",
    "\n",
    "def rag_answer(question: str, relevance_threshold: float = 1.5) -> Dict:\n",
    "    \"\"\"Answer question using RAG - check database first, fallback to Gemini\"\"\"\n",
    "    global retriever, vectordb\n",
    "    \n",
    "    result = {\n",
    "        \"answer\": \"\",\n",
    "        \"source\": \"none\",\n",
    "        \"context_found\": False,\n",
    "        \"relevance_score\": 0.0\n",
    "    }\n",
    "    \n",
    "    if not rag_initialized or retriever is None:\n",
    "        result[\"source\"] = \"gemini\"\n",
    "        result[\"answer\"] = ask_gemini_directly(question)\n",
    "        return result\n",
    "    \n",
    "    # Search vector database\n",
    "    docs_with_scores = vectordb.similarity_search_with_score(question, k=4)\n",
    "    \n",
    "    if not docs_with_scores:\n",
    "        result[\"source\"] = \"gemini\"\n",
    "        result[\"answer\"] = ask_gemini_directly(question)\n",
    "        return result\n",
    "    \n",
    "    best_score = docs_with_scores[0][1]\n",
    "    result[\"relevance_score\"] = float(best_score)\n",
    "    \n",
    "    # Check relevance threshold\n",
    "    if best_score > relevance_threshold:\n",
    "        print(f\"⚠ Low relevance (score: {best_score:.3f}), using Gemini\")\n",
    "        result[\"source\"] = \"gemini\"\n",
    "        result[\"answer\"] = ask_gemini_directly(question)\n",
    "        return result\n",
    "    \n",
    "    # Good relevance - use RAG\n",
    "    print(f\"✅ Good relevance (score: {best_score:.3f}), answering from documents\")\n",
    "    docs = [doc for doc, score in docs_with_scores]\n",
    "    context = \"\\n\\n\".join([d.page_content for d in docs])\n",
    "    result[\"context_found\"] = True\n",
    "    \n",
    "    prompt = f\"\"\"Answer the question based ONLY on the following context from the PDF documents. If the context doesn't contain enough information, say \"I don't have enough information in the documents to answer this.\"\n",
    "\n",
    "Context from PDFs:\n",
    "{context}\n",
    "\n",
    "Question: {question}\n",
    "\n",
    "Answer:\"\"\"\n",
    "    \n",
    "    try:\n",
    "        model = genai.GenerativeModel(\"models/gemini-1.5-flash\")\n",
    "        response = model.generate_content(prompt)\n",
    "        result[\"answer\"] = response.text\n",
    "        result[\"source\"] = \"rag\"\n",
    "    except Exception as e:\n",
    "        print(f\"❌ RAG generation error: {e}\")\n",
    "        result[\"answer\"] = f\"Error: {str(e)}\"\n",
    "        result[\"source\"] = \"error\"\n",
    "    \n",
    "    return result\n",
    "\n",
    "\n",
    "def ask_gemini_directly(question: str) -> str:\n",
    "    \"\"\"Fallback: Ask Gemini directly\"\"\"\n",
    "    try:\n",
    "        model = genai.GenerativeModel(\"models/gemini-1.5-flash\")\n",
    "        response = model.generate_content(f\"Answer this question: {question}\")\n",
    "        return response.text\n",
    "    except Exception as e:\n",
    "        return f\"Error: {str(e)}\"\n",
    "\n",
    "\n",
    "print(\"✅ RAG functions defined!\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b98c801",
   "metadata": {},
   "source": [
    "## 5. Load PDFs from Local Directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "6aecdbe9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading multilingual embedding model...\n",
      "✅ Embedding model loaded!\n",
      "⚠ Failed to load vector store: Error in faiss::FileIOReader::FileIOReader(const char*) at /project/third-party/faiss/faiss/impl/io.cpp:69: Error: 'f' failed: could not open /content/rag_data/faiss_index/index.faiss for reading: No such file or directory\n",
      "📁 Place your PDF files in: /content/rag_data/pdfs\n",
      "   Current directory: /content\n",
      "\n",
      "⚠️ No PDF files found!\n",
      "   Please add PDF files to: /content/rag_data/pdfs\n"
     ]
    }
   ],
   "source": [
    "import glob\n",
    "\n",
    "# Try to load existing vector store first\n",
    "load_vector_store()\n",
    "\n",
    "# Option 1: Manually place PDFs in the rag_data/pdfs folder, then run this\n",
    "print(f\"📁 Place your PDF files in: {PDFS_PATH}\")\n",
    "print(f\"   Current directory: {os.getcwd()}\")\n",
    "\n",
    "# Find all PDFs in the pdfs folder\n",
    "pdf_files = glob.glob(os.path.join(PDFS_PATH, \"*.pdf\"))\n",
    "\n",
    "if not pdf_files:\n",
    "    print(\"\\n⚠️ No PDF files found!\")\n",
    "    print(f\"   Please add PDF files to: {PDFS_PATH}\")\n",
    "else:\n",
    "    print(f\"\\n📚 Found {len(pdf_files)} PDF file(s):\")\n",
    "    \n",
    "    # Process each PDF\n",
    "    for pdf_path in pdf_files:\n",
    "        filename = os.path.basename(pdf_path)\n",
    "        print(f\"\\n   Processing: {filename}\")\n",
    "        \n",
    "        # Skip if already processed\n",
    "        if filename in uploaded_documents:\n",
    "            print(f\"   ⏭️ Already processed, skipping...\")\n",
    "            continue\n",
    "        \n",
    "        # Process PDF\n",
    "        chunks = load_and_process_pdf(pdf_path)\n",
    "        create_vector_store(chunks)\n",
    "        uploaded_documents.append(filename)\n",
    "    \n",
    "    print(f\"\\n✅ Processed {len(uploaded_documents)} PDF(s) total\")\n",
    "    print(f\"📚 Documents in database: {uploaded_documents}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ff67dfb7",
   "metadata": {},
   "source": [
    "## 6. Test RAG Query (Simple)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "86dc46cd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "❓ Question: What is a wired network?\n",
      "\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m/tmp/ipython-input-1251978023.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"❓ Question: {test_question}\\n\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrag_answer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtest_question\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrelevance_threshold\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m2.0\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# Increased threshold\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      6\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"📊 Source: {result['source'].upper()}\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/tmp/ipython-input-2893062687.py\u001b[0m in \u001b[0;36mrag_answer\u001b[0;34m(question, relevance_threshold)\u001b[0m\n\u001b[1;32m    148\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mrag_initialized\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mretriever\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    149\u001b[0m         \u001b[0mresult\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"source\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"gemini\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 150\u001b[0;31m         \u001b[0mresult\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"answer\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mask_gemini_directly\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mquestion\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    151\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    152\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/tmp/ipython-input-2893062687.py\u001b[0m in \u001b[0;36mask_gemini_directly\u001b[0;34m(question)\u001b[0m\n\u001b[1;32m    201\u001b[0m     \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    202\u001b[0m         \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgenai\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mGenerativeModel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"models/gemini-1.5-flash\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 203\u001b[0;31m         \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgenerate_content\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"Answer this question: {question}\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    204\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mresponse\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    205\u001b[0m     \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/generativeai/generative_models.py\u001b[0m in \u001b[0;36mgenerate_content\u001b[0;34m(self, contents, generation_config, safety_settings, stream, tools, tool_config, request_options)\u001b[0m\n\u001b[1;32m    329\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mgeneration_types\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mGenerateContentResponse\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_iterator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    330\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 331\u001b[0;31m                 response = self._client.generate_content(\n\u001b[0m\u001b[1;32m    332\u001b[0m                     \u001b[0mrequest\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    333\u001b[0m                     \u001b[0;34m**\u001b[0m\u001b[0mrequest_options\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/ai/generativelanguage_v1beta/services/generative_service/client.py\u001b[0m in \u001b[0;36mgenerate_content\u001b[0;34m(self, request, model, contents, retry, timeout, metadata)\u001b[0m\n\u001b[1;32m    833\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    834\u001b[0m         \u001b[0;31m# Send the request.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 835\u001b[0;31m         response = rpc(\n\u001b[0m\u001b[1;32m    836\u001b[0m             \u001b[0mrequest\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    837\u001b[0m             \u001b[0mretry\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mretry\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/gapic_v1/method.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, timeout, retry, compression, *args, **kwargs)\u001b[0m\n\u001b[1;32m    129\u001b[0m             \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"compression\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcompression\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    130\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 131\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mwrapped_func\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    132\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    133\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_wrapped_func\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    292\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_initial\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maximum\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmultiplier\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_multiplier\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    293\u001b[0m             )\n\u001b[0;32m--> 294\u001b[0;31m             return retry_target(\n\u001b[0m\u001b[1;32m    295\u001b[0m                 \u001b[0mtarget\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    296\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_predicate\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m    145\u001b[0m     \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    146\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 147\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    148\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0minspect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misawaitable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    149\u001b[0m                 \u001b[0mwarnings\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwarn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_ASYNC_RETRY_WARNING\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/timeout.py\u001b[0m in \u001b[0;36mfunc_with_timeout\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    128\u001b[0m                 \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"timeout\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mremaining_timeout\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    129\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 130\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    131\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    132\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mfunc_with_timeout\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/grpc_helpers.py\u001b[0m in \u001b[0;36merror_remapped_callable\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     73\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0merror_remapped_callable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     74\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 75\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mcallable_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     76\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mgrpc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mRpcError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     77\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mexceptions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_grpc_error\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexc\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/ai/generativelanguage_v1beta/services/generative_service/transports/rest.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, request, retry, timeout, metadata)\u001b[0m\n\u001b[1;32m   1146\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1147\u001b[0m             \u001b[0;31m# Send the request\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1148\u001b[0;31m             response = GenerativeServiceRestTransport._GenerateContent._get_response(\n\u001b[0m\u001b[1;32m   1149\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_host\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1150\u001b[0m                 \u001b[0mmetadata\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/ai/generativelanguage_v1beta/services/generative_service/transports/rest.py\u001b[0m in \u001b[0;36m_get_response\u001b[0;34m(host, metadata, query_params, session, timeout, transcoded_request, body)\u001b[0m\n\u001b[1;32m   1046\u001b[0m             \u001b[0mheaders\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmetadata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1047\u001b[0m             \u001b[0mheaders\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"Content-Type\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"application/json\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1048\u001b[0;31m             response = getattr(session, method)(\n\u001b[0m\u001b[1;32m   1049\u001b[0m                 \u001b[0;34m\"{host}{uri}\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhost\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mhost\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0muri\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0muri\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1050\u001b[0m                 \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/requests/sessions.py\u001b[0m in \u001b[0;36mpost\u001b[0;34m(self, url, data, json, **kwargs)\u001b[0m\n\u001b[1;32m    635\u001b[0m         \"\"\"\n\u001b[1;32m    636\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 637\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"POST\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mjson\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    638\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    639\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mput\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/auth/transport/requests.py\u001b[0m in \u001b[0;36mrequest\u001b[0;34m(self, method, url, data, headers, max_allowed_time, timeout, **kwargs)\u001b[0m\n\u001b[1;32m    533\u001b[0m         \u001b[0;32mwith\u001b[0m \u001b[0mTimeoutGuard\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mremaining_time\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mguard\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    534\u001b[0m             \u001b[0m_helpers\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrequest_log\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_LOGGER\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 535\u001b[0;31m             response = super(AuthorizedSession, self).request(\n\u001b[0m\u001b[1;32m    536\u001b[0m                 \u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    537\u001b[0m                 \u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/requests/sessions.py\u001b[0m in \u001b[0;36mrequest\u001b[0;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[1;32m    587\u001b[0m         }\n\u001b[1;32m    588\u001b[0m         \u001b[0msend_kwargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msettings\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 589\u001b[0;31m         \u001b[0mresp\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprep\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0msend_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    590\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    591\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mresp\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/requests/sessions.py\u001b[0m in \u001b[0;36msend\u001b[0;34m(self, request, **kwargs)\u001b[0m\n\u001b[1;32m    701\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    702\u001b[0m         \u001b[0;31m# Send the request\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 703\u001b[0;31m         \u001b[0mr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0madapter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    704\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    705\u001b[0m         \u001b[0;31m# Total elapsed time of the request (approximately)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/requests/adapters.py\u001b[0m in \u001b[0;36msend\u001b[0;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[1;32m    642\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    643\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 644\u001b[0;31m             resp = conn.urlopen(\n\u001b[0m\u001b[1;32m    645\u001b[0m                 \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    646\u001b[0m                 \u001b[0murl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36murlopen\u001b[0;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, preload_content, decode_content, **response_kw)\u001b[0m\n\u001b[1;32m    785\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    786\u001b[0m             \u001b[0;31m# Make the request on the HTTPConnection object\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 787\u001b[0;31m             response = self._make_request(\n\u001b[0m\u001b[1;32m    788\u001b[0m                 \u001b[0mconn\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    789\u001b[0m                 \u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[0;34m(self, conn, method, url, body, headers, retries, timeout, chunked, response_conn, preload_content, decode_content, enforce_content_length)\u001b[0m\n\u001b[1;32m    532\u001b[0m         \u001b[0;31m# Receive the response from the server\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    533\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 534\u001b[0;31m             \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetresponse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    535\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mBaseSSLError\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mOSError\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    536\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_raise_timeout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0merr\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout_value\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mread_timeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/urllib3/connection.py\u001b[0m in \u001b[0;36mgetresponse\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    563\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    564\u001b[0m         \u001b[0;31m# Get the response from http.client.HTTPConnection\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 565\u001b[0;31m         \u001b[0mhttplib_response\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetresponse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    566\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    567\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/lib/python3.12/http/client.py\u001b[0m in \u001b[0;36mgetresponse\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1428\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1429\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1430\u001b[0;31m                 \u001b[0mresponse\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbegin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1431\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mConnectionError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1432\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/lib/python3.12/http/client.py\u001b[0m in \u001b[0;36mbegin\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    329\u001b[0m         \u001b[0;31m# read until we get a non-100 response\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    330\u001b[0m         \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 331\u001b[0;31m             \u001b[0mversion\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatus\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreason\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_read_status\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    332\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0mCONTINUE\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    333\u001b[0m                 \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/lib/python3.12/http/client.py\u001b[0m in \u001b[0;36m_read_status\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    290\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    291\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_read_status\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 292\u001b[0;31m         \u001b[0mline\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreadline\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_MAXLINE\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"iso-8859-1\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    293\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mline\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0m_MAXLINE\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    294\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mLineTooLong\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"status line\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/lib/python3.12/socket.py\u001b[0m in \u001b[0;36mreadinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m    718\u001b[0m         \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    719\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 720\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sock\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    721\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    722\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_timeout_occurred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "# Test with a question\n",
    "test_question = \"What is a wired network?\"  # Change this to your question\n",
    "\n",
    "print(f\"❓ Question: {test_question}\\n\")\n",
    "result = rag_answer(test_question, relevance_threshold=2.0)  # Increased threshold\n",
    "\n",
    "print(f\"📊 Source: {result['source'].upper()}\")\n",
    "print(f\"📊 Relevance Score: {result['relevance_score']:.3f}\")\n",
    "print(f\"\\n💬 Answer:\\n{result['answer']}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "04937fbd",
   "metadata": {},
   "source": [
    "## 7. Create FastAPI Server + ngrok (Public API)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "708b25ca",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ FastAPI app created!\n"
     ]
    }
   ],
   "source": [
    "from fastapi import FastAPI, HTTPException\n",
    "from pydantic import BaseModel\n",
    "import nest_asyncio\n",
    "\n",
    "# Allow nested event loops (for Jupyter)\n",
    "nest_asyncio.apply()\n",
    "\n",
    "# Create FastAPI app\n",
    "app = FastAPI(title=\"RAG API\", version=\"1.0\")\n",
    "\n",
    "class QuestionRequest(BaseModel):\n",
    "    question: str\n",
    "    threshold: float = 2.0  # Default threshold\n",
    "\n",
    "class AnswerResponse(BaseModel):\n",
    "    question: str\n",
    "    answer: str\n",
    "    source: str\n",
    "    relevance_score: float\n",
    "    context_found: bool\n",
    "\n",
    "@app.get(\"/\")\n",
    "async def root():\n",
    "    return {\n",
    "        \"message\": \"RAG API is running!\",\n",
    "        \"endpoints\": {\n",
    "            \"/ask\": \"POST - Ask a question\",\n",
    "            \"/status\": \"GET - Check system status\"\n",
    "        }\n",
    "    }\n",
    "\n",
    "@app.post(\"/ask\", response_model=AnswerResponse)\n",
    "async def ask_question(request: QuestionRequest):\n",
    "    \"\"\"Ask a question to RAG system\"\"\"\n",
    "    if not request.question:\n",
    "        raise HTTPException(status_code=400, detail=\"Question is required\")\n",
    "    \n",
    "    result = rag_answer(request.question, relevance_threshold=request.threshold)\n",
    "    \n",
    "    return AnswerResponse(\n",
    "        question=request.question,\n",
    "        answer=result[\"answer\"],\n",
    "        source=result[\"source\"],\n",
    "        relevance_score=result[\"relevance_score\"],\n",
    "        context_found=result[\"context_found\"]\n",
    "    )\n",
    "\n",
    "@app.get(\"/status\")\n",
    "async def get_status():\n",
    "    \"\"\"Get RAG system status\"\"\"\n",
    "    return {\n",
    "        \"initialized\": rag_initialized,\n",
    "        \"documents_count\": len(uploaded_documents),\n",
    "        \"documents\": uploaded_documents,\n",
    "        \"has_vector_store\": vectordb is not None\n",
    "    }\n",
    "\n",
    "print(\"✅ FastAPI app created!\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bd49f8a1",
   "metadata": {},
   "source": [
    "## 8. Start Server Locally (Access at http://localhost:8000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0e4c8558",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "============================================================\n",
      "🌐 LOCAL API SERVER STARTED!\n",
      "============================================================\n",
      "\n",
      "📌 API Endpoints:\n",
      "   POST http://localhost:8000/ask   - Ask a question\n",
      "   GET  http://localhost:8000/status - Check status\n",
      "   GET  http://localhost:8000/docs   - API documentation\n",
      "\n",
      "💡 Test in browser: http://localhost:8000/docs\n",
      "\n",
      "💡 Example curl command:\n",
      "   curl -X POST \"http://localhost:8000/ask\" ^\n",
      "        -H \"Content-Type: application/json\" ^\n",
      "        -d \"{\\\"question\\\": \\\"What is a wired network?\\\", \\\"threshold\\\": 2.0}\"\n",
      "\n",
      "🔄 Server is running in background...\n",
      "   (Server will stop when notebook kernel is restarted)\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.12/dist-packages/uvicorn/server.py:67: RuntimeWarning: coroutine 'Server.serve' was never awaited\n",
      "  return asyncio_run(self.serve(sockets=sockets), loop_factory=self.config.get_loop_factory())\n",
      "RuntimeWarning: Enable tracemalloc to get the object allocation traceback\n",
      "Exception in thread Thread-6 (run_server):\n",
      "Traceback (most recent call last):\n",
      "  File \"/usr/lib/python3.12/threading.py\", line 1075, in _bootstrap_inner\n",
      "    self.run()\n",
      "  File \"/usr/lib/python3.12/threading.py\", line 1012, in run\n",
      "    self._target(*self._args, **self._kwargs)\n",
      "  File \"/tmp/ipython-input-2073060122.py\", line 6, in run_server\n",
      "  File \"/usr/local/lib/python3.12/dist-packages/uvicorn/main.py\", line 593, in run\n",
      "    server.run()\n",
      "  File \"/usr/local/lib/python3.12/dist-packages/uvicorn/server.py\", line 67, in run\n",
      "    return asyncio_run(self.serve(sockets=sockets), loop_factory=self.config.get_loop_factory())\n",
      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
      "TypeError: _patch_asyncio.<locals>.run() got an unexpected keyword argument 'loop_factory'\n"
     ]
    }
   ],
   "source": [
    "import uvicorn\n",
    "import threading\n",
    "\n",
    "def run_server():\n",
    "    \"\"\"Run the FastAPI server in a thread\"\"\"\n",
    "    uvicorn.run(app, host=\"127.0.0.1\", port=8000, log_level=\"info\")\n",
    "\n",
    "# Start server in background thread\n",
    "server_thread = threading.Thread(target=run_server, daemon=True)\n",
    "server_thread.start()\n",
    "\n",
    "print(\"\\n\" + \"=\"*60)\n",
    "print(\"🌐 LOCAL API SERVER STARTED!\")\n",
    "print(\"=\"*60)\n",
    "print(\"\\n📌 API Endpoints:\")\n",
    "print(\"   POST http://localhost:8000/ask   - Ask a question\")\n",
    "print(\"   GET  http://localhost:8000/status - Check status\")\n",
    "print(\"   GET  http://localhost:8000/docs   - API documentation\")\n",
    "print(\"\\n💡 Test in browser: http://localhost:8000/docs\")\n",
    "print(\"\\n💡 Example curl command:\")\n",
    "print('   curl -X POST \"http://localhost:8000/ask\" ^')\n",
    "print('        -H \"Content-Type: application/json\" ^')\n",
    "print('        -d \"{\\\\\"question\\\\\": \\\\\"What is a wired network?\\\\\", \\\\\"threshold\\\\\": 2.0}\"')\n",
    "print(\"\\n🔄 Server is running in background...\")\n",
    "print(\"   (Server will stop when notebook kernel is restarted)\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a025b750",
   "metadata": {},
   "source": [
    "## 9. Test API from Another Cell (While Server is Running)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b368a3ac",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "📡 Testing API at http://localhost:8000/ask\n",
      "\n",
      "❌ Connection error: HTTPConnectionPool(host='localhost', port=8000): Max retries exceeded with url: /ask (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x79ffcd92bd40>: Failed to establish a new connection: [Errno 111] Connection refused'))\n",
      "   Make sure the server is running (cell 8)\n"
     ]
    }
   ],
   "source": [
    "import requests\n",
    "import json\n",
    "import time\n",
    "\n",
    "# Give server a moment to start\n",
    "time.sleep(2)\n",
    "\n",
    "# Local API URL\n",
    "API_URL = \"http://localhost:8000\"\n",
    "\n",
    "# Test question\n",
    "test_data = {\n",
    "    \"question\": \"What is a wireless network?\",\n",
    "    \"threshold\": 2.0\n",
    "}\n",
    "\n",
    "print(f\"📡 Testing API at {API_URL}/ask\\n\")\n",
    "\n",
    "try:\n",
    "    # Make API request\n",
    "    response = requests.post(\n",
    "        f\"{API_URL}/ask\",\n",
    "        json=test_data,\n",
    "        headers={\"Content-Type\": \"application/json\"}\n",
    "    )\n",
    "    \n",
    "    if response.status_code == 200:\n",
    "        result = response.json()\n",
    "        print(f\"❓ Question: {result['question']}\")\n",
    "        print(f\"📊 Source: {result['source'].upper()}\")\n",
    "        print(f\"📊 Score: {result['relevance_score']:.3f}\")\n",
    "        print(f\"\\n💬 Answer:\\n{result['answer']}\")\n",
    "    else:\n",
    "        print(f\"❌ Error: {response.status_code}\")\n",
    "        print(response.text)\n",
    "except Exception as e:\n",
    "    print(f\"❌ Connection error: {e}\")\n",
    "    print(\"   Make sure the server is running (cell 8)\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "86a8d4bb",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "## ✅ Summary - Local Windows Setup\n",
    "\n",
    "Your RAG API is now configured for **local Windows** use:\n",
    "\n",
    "### How to Use:\n",
    "1. ✅ **Run cells 1-4** to install packages and load functions\n",
    "2. ✅ **Add PDFs** to the `rag_data/pdfs` folder in your project directory\n",
    "3. ✅ **Run cell 5** to process PDFs and build the vector database\n",
    "4. ✅ **Run cell 6** to test RAG queries directly\n",
    "5. ✅ **Run cell 8** to start the local API server\n",
    "6. ✅ **Access API docs** at http://localhost:8000/docs\n",
    "\n",
    "### Key Features:\n",
    "- 📁 Data stored locally in `rag_data/` folder\n",
    "- 🔍 Answers from PDF documents first\n",
    "- 🤖 Falls back to Gemini API when needed\n",
    "- 🌐 Local API server at http://localhost:8000\n",
    "- 💾 FAISS index persists between sessions\n",
    "\n",
    "### Quick Test:\n",
    "```python\n",
    "# Direct RAG query (no API)\n",
    "result = rag_answer(\"Your question here\", relevance_threshold=2.0)\n",
    "print(result['answer'])\n",
    "```\n",
    "\n",
    "### Next Steps:\n",
    "- Add more PDFs to `rag_data/pdfs/` folder\n",
    "- Rerun cell 5 to add them to the database\n",
    "- Adjust `relevance_threshold` (lower = stricter, higher = more lenient)\n",
    "- Access interactive API docs at http://localhost:8000/docs"
   ]
  }
 ],
 "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": "3.12.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}