LlamaIndex_Gemma-IT-7B-RAG.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Gemma IT 7B\n",
    "#### RAG with LlamaIndex - Nvidia CUDA + WSL (Windows Subsystem for Linux) + Word documents + Local LLM\n",
    "\n",
    "This notebook demonstrates the use of LlamaIndex for Retrieval Augmented Generation using Windows' WSL and an Nvidia's CUDA.\n",
    "\n",
    "See the [README.md](README.md) file for help on how to run this."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 1. Prepare Llama Index for use"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/markwsl/miniconda3/envs/LlamaIndexRAGLinux/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import logging\n",
    "import sys\n",
    "\n",
    "logging.basicConfig(stream=sys.stdout, level=logging.INFO)\n",
    "logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))\n",
    "\n",
    "from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, ServiceContext"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 2. Load the Word document(s)\n",
    "\n",
    "Note: A fictitious story about Thundertooth a dinosaur who has travelled to the future. Thanks ChatGPT!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "documents = SimpleDirectoryReader(\"./Data/\").load_data()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 3. Instantiate the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no\n",
      "ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes\n",
      "ggml_init_cublas: found 1 CUDA devices:\n",
      "  Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes\n",
      "llama_model_loader: loaded meta data with 21 key-value pairs and 254 tensors from ./Models/gemma-7b-it-q8_0.gguf (version GGUF V3 (latest))\n",
      "llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.\n",
      "llama_model_loader: - kv   0:                       general.architecture str              = gemma\n",
      "llama_model_loader: - kv   1:                               general.name str              = gemma-7b-it\n",
      "llama_model_loader: - kv   2:                       gemma.context_length u32              = 8192\n",
      "llama_model_loader: - kv   3:                          gemma.block_count u32              = 28\n",
      "llama_model_loader: - kv   4:                     gemma.embedding_length u32              = 3072\n",
      "llama_model_loader: - kv   5:                  gemma.feed_forward_length u32              = 24576\n",
      "llama_model_loader: - kv   6:                 gemma.attention.head_count u32              = 16\n",
      "llama_model_loader: - kv   7:              gemma.attention.head_count_kv u32              = 16\n",
      "llama_model_loader: - kv   8:                 gemma.attention.key_length u32              = 256\n",
      "llama_model_loader: - kv   9:               gemma.attention.value_length u32              = 256\n",
      "llama_model_loader: - kv  10:     gemma.attention.layer_norm_rms_epsilon f32              = 0.000001\n",
      "llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = llama\n",
      "llama_model_loader: - kv  12:                tokenizer.ggml.bos_token_id u32              = 2\n",
      "llama_model_loader: - kv  13:                tokenizer.ggml.eos_token_id u32              = 1\n",
      "llama_model_loader: - kv  14:            tokenizer.ggml.padding_token_id u32              = 0\n",
      "llama_model_loader: - kv  15:            tokenizer.ggml.unknown_token_id u32              = 3\n",
      "llama_model_loader: - kv  16:                      tokenizer.ggml.tokens arr[str,256128]  = [\"<pad>\", \"<eos>\", \"<bos>\", \"<unk>\", ...\n",
      "llama_model_loader: - kv  17:                      tokenizer.ggml.scores arr[f32,256128]  = [0.000000, 0.000000, 0.000000, 0.0000...\n",
      "llama_model_loader: - kv  18:                  tokenizer.ggml.token_type arr[i32,256128]  = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...\n",
      "llama_model_loader: - kv  19:               general.quantization_version u32              = 2\n",
      "llama_model_loader: - kv  20:                          general.file_type u32              = 7\n",
      "llama_model_loader: - type  f32:   57 tensors\n",
      "llama_model_loader: - type q8_0:  197 tensors\n",
      "llm_load_vocab: mismatch in special tokens definition ( 544/256128 vs 388/256128 ).\n",
      "llm_load_print_meta: format           = GGUF V3 (latest)\n",
      "llm_load_print_meta: arch             = gemma\n",
      "llm_load_print_meta: vocab type       = SPM\n",
      "llm_load_print_meta: n_vocab          = 256128\n",
      "llm_load_print_meta: n_merges         = 0\n",
      "llm_load_print_meta: n_ctx_train      = 8192\n",
      "llm_load_print_meta: n_embd           = 3072\n",
      "llm_load_print_meta: n_head           = 16\n",
      "llm_load_print_meta: n_head_kv        = 16\n",
      "llm_load_print_meta: n_layer          = 28\n",
      "llm_load_print_meta: n_rot            = 192\n",
      "llm_load_print_meta: n_embd_head_k    = 256\n",
      "llm_load_print_meta: n_embd_head_v    = 256\n",
      "llm_load_print_meta: n_gqa            = 1\n",
      "llm_load_print_meta: n_embd_k_gqa     = 4096\n",
      "llm_load_print_meta: n_embd_v_gqa     = 4096\n",
      "llm_load_print_meta: f_norm_eps       = 0.0e+00\n",
      "llm_load_print_meta: f_norm_rms_eps   = 1.0e-06\n",
      "llm_load_print_meta: f_clamp_kqv      = 0.0e+00\n",
      "llm_load_print_meta: f_max_alibi_bias = 0.0e+00\n",
      "llm_load_print_meta: n_ff             = 24576\n",
      "llm_load_print_meta: n_expert         = 0\n",
      "llm_load_print_meta: n_expert_used    = 0\n",
      "llm_load_print_meta: rope scaling     = linear\n",
      "llm_load_print_meta: freq_base_train  = 10000.0\n",
      "llm_load_print_meta: freq_scale_train = 1\n",
      "llm_load_print_meta: n_yarn_orig_ctx  = 8192\n",
      "llm_load_print_meta: rope_finetuned   = unknown\n",
      "llm_load_print_meta: model type       = 7B\n",
      "llm_load_print_meta: model ftype      = Q8_0\n",
      "llm_load_print_meta: model params     = 8.54 B\n",
      "llm_load_print_meta: model size       = 8.45 GiB (8.50 BPW) \n",
      "llm_load_print_meta: general.name     = gemma-7b-it\n",
      "llm_load_print_meta: BOS token        = 2 '<bos>'\n",
      "llm_load_print_meta: EOS token        = 1 '<eos>'\n",
      "llm_load_print_meta: UNK token        = 3 '<unk>'\n",
      "llm_load_print_meta: PAD token        = 0 '<pad>'\n",
      "llm_load_print_meta: LF token         = 227 '<0x0A>'\n",
      "llm_load_tensors: ggml ctx size =    0.19 MiB\n",
      "llm_load_tensors: offloading 28 repeating layers to GPU\n",
      "llm_load_tensors: offloading non-repeating layers to GPU\n",
      "llm_load_tensors: offloaded 29/29 layers to GPU\n",
      "llm_load_tensors:        CPU buffer size =   797.27 MiB\n",
      "llm_load_tensors:      CUDA0 buffer size =  8651.94 MiB\n",
      "......................................................................................\n",
      "llama_new_context_with_model: n_ctx      = 8192\n",
      "llama_new_context_with_model: freq_base  = 10000.0\n",
      "llama_new_context_with_model: freq_scale = 1\n",
      "llama_kv_cache_init:      CUDA0 KV buffer size =  3584.00 MiB\n",
      "llama_new_context_with_model: KV self size  = 3584.00 MiB, K (f16): 1792.00 MiB, V (f16): 1792.00 MiB\n",
      "llama_new_context_with_model:  CUDA_Host input buffer size   =    23.07 MiB\n",
      "llama_new_context_with_model:      CUDA0 compute buffer size =   506.25 MiB\n",
      "llama_new_context_with_model:  CUDA_Host compute buffer size =     6.00 MiB\n",
      "llama_new_context_with_model: graph splits (measure): 3\n",
      "AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | \n",
      "Model metadata: {'general.file_type': '7', 'tokenizer.ggml.unknown_token_id': '3', 'tokenizer.ggml.padding_token_id': '0', 'tokenizer.ggml.eos_token_id': '1', 'general.architecture': 'gemma', 'gemma.feed_forward_length': '24576', 'gemma.attention.head_count': '16', 'general.name': 'gemma-7b-it', 'gemma.context_length': '8192', 'gemma.block_count': '28', 'gemma.embedding_length': '3072', 'gemma.attention.head_count_kv': '16', 'gemma.attention.key_length': '256', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'llama', 'gemma.attention.value_length': '256', 'gemma.attention.layer_norm_rms_epsilon': '0.000001', 'tokenizer.ggml.bos_token_id': '2'}\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "\n",
    "from llama_index.llms.llama_cpp import LlamaCPP\n",
    "from llama_index.llms.llama_cpp.llama_utils import messages_to_prompt, completion_to_prompt\n",
    "llm = LlamaCPP(\n",
    "    model_url=None, # We'll load locally.\n",
    "    model_path='./Models/gemma-7b-it-q8_0.gguf', # 8-bit model\n",
    "    temperature=0.1,\n",
    "    max_new_tokens=1024, # Increasing to support longer responses\n",
    "    context_window=8192, # 8K context window\n",
    "    generate_kwargs={},\n",
    "    # set to at least 1 to use GPU\n",
    "    model_kwargs={\"n_gpu_layers\": 40}, # 40 was a good amount of layers for the RTX 3090, you may need to decrease yours if you have less VRAM than 24GB\n",
    "    messages_to_prompt=messages_to_prompt,\n",
    "    completion_to_prompt=completion_to_prompt,\n",
    "    verbose=True\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 4. Checkpoint\n",
    "\n",
    "Are you running on GPU? The above output should include near the top something like:\n",
    "> ggml_init_cublas: found 1 CUDA devices:\n",
    "\n",
    "And in the full text near the bottom should be:\n",
    "> llm_load_tensors: using CUDA for GPU acceleration"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 5. Embeddings\n",
    "\n",
    "Convert your source document text into embeddings.\n",
    "\n",
    "The embedding model is from huggingface, this one performs well.\n",
    "\n",
    "> https://huggingface.co/thenlper/gte-large\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.embeddings.huggingface import HuggingFaceEmbedding\n",
    "\n",
    "embed_model = HuggingFaceEmbedding(model_name=\"thenlper/gte-large\", cache_folder=None)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 6. Prompt Template\n",
    "\n",
    "Prompt template:\n",
    "\n",
    "```\n",
    "<start_of_turn>user\n",
    "Question here<end_of_turn>\n",
    "<start_of_turn>model\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 7. Service Context\n",
    "\n",
    "For chunking the document into tokens using the embedding model and our LLM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.core import Settings\n",
    "\n",
    "Settings.llm = llm\n",
    "Settings.embed_model = embed_model\n",
    "Settings.chunk_size=256 # Number of tokens in each chunk"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 8. Index documents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "index = VectorStoreIndex.from_documents(documents)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 9. Query Engine\n",
    "\n",
    "Create a query engine, specifying how many citations we want to get back from the searched text (in this case 3).\n",
    "\n",
    "The DB_DOC_ID_KEY is used to get back the filename of the original document"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.core.query_engine import CitationQueryEngine\n",
    "query_engine = CitationQueryEngine.from_args(\n",
    "    index,\n",
    "    similarity_top_k=3,\n",
    "    # here we can control how granular citation sources are, the default is 512\n",
    "    citation_chunk_size=256,\n",
    ")\n",
    "\n",
    "# For citations we get the document info\n",
    "DB_DOC_ID_KEY = \"db_document_id\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 10. Prompt and Response function\n",
    "\n",
    "Pass in a question, get a response back.\n",
    "\n",
    "IMPORTANT: The prompt is in the question, adjust it to match what you want the LLM to act like and do."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def RunQuestion(questionText):\n",
    "\n",
    "    queryQuestion = \"You are a technology specialist. Answer questions in a positive, helpful and empathetic way. Answer the following question: \" + questionText + \"\"\n",
    "\n",
    "    response = query_engine.query(queryQuestion)\n",
    "\n",
    "    return response"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 11. Questions to test with"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "TestQuestions = [\n",
    "    \"Summarise the story for me\",\n",
    "    \"Who was the main protagonist?\",\n",
    "    \"Did they have any children? If so, what were their names?\",\n",
    "    \"Did anything eventful happen?\",\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 12. Run Questions through model (this can take a while) and see citations\n",
    "\n",
    "Runs each test question, saves it to a dictionary for output in the last step.\n",
    "\n",
    "Note: Citations are the source documents used and the text the response is based on. This is important for RAG so you can reference these documents for the user, and to ensure it's utilising the right documents."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "1/4: Summarise the story for me\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =    5359.76 ms\n",
      "llama_print_timings:      sample time =     607.49 ms /   196 runs   (    3.10 ms per token,   322.64 tokens per second)\n",
      "llama_print_timings: prompt eval time =    5579.59 ms /  1005 tokens (    5.55 ms per token,   180.12 tokens per second)\n",
      "llama_print_timings:        eval time =    4425.53 ms /   195 runs   (   22.70 ms per token,    44.06 tokens per second)\n",
      "llama_print_timings:       total time =   14953.76 ms /  1200 tokens\n",
      "Llama.generate: prefix-match hit\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/4: |Thundertooth Part 1.docx| Source 1:\n",
      "\"Hello there, majestic creature. What brings you to our time?\" Mayor Grace inquired, her voice calm and reassuring.\n",
      "\n",
      "\n",
      "\n",
      "Thundertooth, though initially startled, found comfort in the mayor's soothing tone. In broken sentences, he explained his journey through time, the strange portal, and his hunger dilemma. Mayor Grace listened intently, her eyes widening with amazement at the tale of the prehistoric dinosaur navigating the future.\n",
      "\n",
      "\n",
      "\n",
      "Realizing the dinosaur's predicament, Mayor Grace extended an invitation. \"You are welcome in our city, Thundertooth. We can find a way to provide for you without causing harm to anyone. Let us work together to find a solution.\"\n",
      "\n",
      "\n",
      "\n",
      "Grateful for the mayor's hospitality, Thundertooth followed her through the city. Together, they explored the futuristic marketplaces and innovative food labs, eventually discovering a sustainable solution that satisfied the dinosaur's hunger without compromising the well-being of the city's inhabitants.\n",
      "\n",
      "2/4: |Thundertooth Part 1.docx| Source 2:\n",
      "As the dazzling vortex subsided, Thundertooth opened his eyes to a world unlike anything he had ever seen. The air was filled with the hum of engines, and towering structures reached towards the sky. Thundertooth's surroundings were a blend of metal and glass, and he quickly realized that he had been transported to a future era.\n",
      "\n",
      "\n",
      "\n",
      "The once mighty dinosaur now stood bewildered in the midst of a bustling city. Above him, sleek flying cars zipped through the air, leaving trails of neon lights in their wake. Thundertooth felt like an ancient relic in this technological jungle, lost and out of place. With each step, he marveled at the skyscrapers that loomed overhead, their surfaces reflecting the myriad lights of the city.\n",
      "\n",
      "\n",
      "\n",
      "However, as night fell, Thundertooth's stomach growled loudly. He realized that he was hungry, and the once vibrant city now seemed like a daunting maze of unfamiliar smells and sights. He wandered through the streets, his massive form drawing astonished stares from the futuristic inhabitants.\n",
      "\n",
      "3/4: |Thundertooth Part 1.docx| Source 3:\n",
      "\"Hello there, majestic creature. What brings you to our time?\" Mayor Grace inquired, her voice calm and reassuring.\n",
      "\n",
      "\n",
      "\n",
      "Thundertooth, though initially startled, found comfort in the mayor's soothing tone. In broken sentences, he explained his journey through time, the strange portal, and his hunger dilemma. Mayor Grace listened intently, her eyes widening with amazement at the tale of the prehistoric dinosaur navigating the future.\n",
      "\n",
      "\n",
      "\n",
      "Realizing the dinosaur's predicament, Mayor Grace extended an invitation. \"You are welcome in our city, Thundertooth. We can find a way to provide for you without causing harm to anyone. Let us work together to find a solution.\"\n",
      "\n",
      "\n",
      "\n",
      "Grateful for the mayor's hospitality, Thundertooth followed her through the city. Together, they explored the futuristic marketplaces and innovative food labs, eventually discovering a sustainable solution that satisfied the dinosaur's hunger without compromising the well-being of the city's inhabitants.\n",
      "\n",
      "4/4: |Thundertooth Part 1.docx| Source 4:\n",
      "As the news of Thundertooth's arrival spread, the city embraced the talking dinosaur as a symbol of unity between the past and the future. Thundertooth found a new home in the city's park, where holographic flowers bloomed, and the citizens marveled at the beauty of coexistence across time. And so, in this extraordinary city of flying cars and advanced technology, Thundertooth became a beloved figure, a living bridge between eras, teaching the people that understanding and cooperation could overcome even the greatest challenges.\n",
      "\n",
      "\n",
      "2/4: Who was the main protagonist?\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =    5359.76 ms\n",
      "llama_print_timings:      sample time =     186.71 ms /    54 runs   (    3.46 ms per token,   289.22 tokens per second)\n",
      "llama_print_timings: prompt eval time =     350.97 ms /   794 tokens (    0.44 ms per token,  2262.30 tokens per second)\n",
      "llama_print_timings:        eval time =    1296.01 ms /    53 runs   (   24.45 ms per token,    40.89 tokens per second)\n",
      "llama_print_timings:       total time =    3123.94 ms /   847 tokens\n",
      "Llama.generate: prefix-match hit\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/3: |Thundertooth Part 3.docx| Source 1:\n",
      "2. **Echo**: With his extraordinary mimicry abilities, Echo would amplify the emergency signals, ensuring that every citizen received timely warnings and instructions for evacuation.\n",
      "\n",
      "\n",
      "\n",
      "3. **Sapphire**: Harnessing her calming and healing powers, Sapphire would assist in calming the panicked masses, ensuring an orderly and efficient evacuation.\n",
      "\n",
      "\n",
      "\n",
      "4. **Ignis**: Drawing upon his fiery talents, Ignis would create controlled bursts of heat, attempting to alter the meteor's trajectory and reduce its destructive force.\n",
      "\n",
      "\n",
      "\n",
      "As the citizens evacuated to designated shelters, the Thundertooth family sprang into action. Lumina worked tirelessly to strengthen the city's energy systems, Echo echoed evacuation orders through the city's speakers, Sapphire offered comfort to those in distress, and Ignis unleashed controlled bursts of flames towards the approaching meteor.\n",
      "\n",
      "\n",
      "\n",
      "Thundertooth stood at the forefront, using his mighty roar to coordinate and inspire the efforts of the city's inhabitants. The ground trembled as the meteor drew closer, but the Thundertooth family's coordinated efforts began to take effect. Lumina's force field shimmered to life, deflecting the meteor's deadly path. Echo's amplified warnings reached every corner of the city, ensuring that no one was left behind.\n",
      "\n",
      "2/3: |Thundertooth Part 3.docx| Source 2:\n",
      "Thundertooth nodded, understanding the gravity of the situation. He gathered Lumina, Echo, Sapphire, and Ignis, explaining the urgency and the role each of them would play in the impending crisis.\n",
      "\n",
      "\n",
      "\n",
      "1. **Lumina**: Utilizing her deep understanding of technology, Lumina would enhance the city's energy systems to generate a powerful force field, providing a protective barrier against the meteor's impact.\n",
      "\n",
      "\n",
      "\n",
      "2. **Echo**: With his extraordinary mimicry abilities, Echo would amplify the emergency signals, ensuring that every citizen received timely warnings and instructions for evacuation.\n",
      "\n",
      "\n",
      "\n",
      "3. **Sapphire**: Harnessing her calming and healing powers, Sapphire would assist in calming the panicked masses, ensuring an orderly and efficient evacuation.\n",
      "\n",
      "\n",
      "\n",
      "4. **Ignis**: Drawing upon his fiery talents, Ignis would create controlled bursts of heat, attempting to alter the meteor's trajectory and reduce its destructive force.\n",
      "\n",
      "\n",
      "\n",
      "As the citizens evacuated to designated shelters, the Thundertooth family sprang into action. Lumina worked tirelessly to strengthen the city's energy systems, Echo echoed evacuation orders through the city's speakers, Sapphire offered comfort to those in distress, and Ignis unleashed controlled bursts of flames towards the approaching meteor.\n",
      "\n",
      "3/3: |Thundertooth Part 2.docx| Source 3:\n",
      "Thundertooth\n",
      "\n",
      "\n",
      "\n",
      "Embraced by the futuristic city and its inhabitants, Thundertooth found a sense of purpose beyond merely satisfying his hunger. Inspired by the advanced technology surrounding him, he decided to channel his creativity into something extraordinary. With the help of the city's brilliant engineers, Thundertooth founded a one-of-a-kind toy factory that produced amazing widgets – magical, interactive toys that captivated the hearts of both children and adults alike.\n",
      "\n",
      "\n",
      "\n",
      "Thundertooth's toy factory became a sensation, and its creations were highly sought after. The widgets incorporated cutting-edge holographic displays, levitation technology, and even the ability to change shapes and colors with a mere thought. Children across the city rejoiced as they played with these incredible toys that seemed to bring their wildest fantasies to life.\n",
      "\n",
      "\n",
      "\n",
      "As the years passed, Thundertooth's life took a heartwarming turn. He met a kind and intelligent dinosaur named Seraphina, and together they started a family. Thundertooth and Seraphina were blessed with four children, each with unique characteristics that mirrored the diversity of their modern world.\n",
      "\n",
      "\n",
      "3/4: Did they have any children? If so, what were their names?\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =    5359.76 ms\n",
      "llama_print_timings:      sample time =     517.96 ms /   147 runs   (    3.52 ms per token,   283.80 tokens per second)\n",
      "llama_print_timings: prompt eval time =     336.51 ms /   765 tokens (    0.44 ms per token,  2273.35 tokens per second)\n",
      "llama_print_timings:        eval time =    3748.88 ms /   146 runs   (   25.68 ms per token,    38.94 tokens per second)\n",
      "llama_print_timings:       total time =    8070.21 ms /   911 tokens\n",
      "Llama.generate: prefix-match hit\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/4: |Thundertooth Part 2.docx| Source 1:\n",
      "Thundertooth's toy factory became a sensation, and its creations were highly sought after. The widgets incorporated cutting-edge holographic displays, levitation technology, and even the ability to change shapes and colors with a mere thought. Children across the city rejoiced as they played with these incredible toys that seemed to bring their wildest fantasies to life.\n",
      "\n",
      "\n",
      "\n",
      "As the years passed, Thundertooth's life took a heartwarming turn. He met a kind and intelligent dinosaur named Seraphina, and together they started a family. Thundertooth and Seraphina were blessed with four children, each with unique characteristics that mirrored the diversity of their modern world.\n",
      "\n",
      "\n",
      "\n",
      "Lumina: The eldest of Thundertooth's children, Lumina inherited her mother's intelligence and her father's sense of wonder. With sparkling scales that emitted a soft glow, Lumina had the ability to generate light at will. She became fascinated with technology, often spending hours tinkering with gadgets and inventing new ways to enhance the widgets produced in the family's factory.\n",
      "\n",
      "2/4: |Thundertooth Part 2.docx| Source 2:\n",
      "As the years passed, Thundertooth's life took a heartwarming turn. He met a kind and intelligent dinosaur named Seraphina, and together they started a family. Thundertooth and Seraphina were blessed with four children, each with unique characteristics that mirrored the diversity of their modern world.\n",
      "\n",
      "\n",
      "\n",
      "Lumina: The eldest of Thundertooth's children, Lumina inherited her mother's intelligence and her father's sense of wonder. With sparkling scales that emitted a soft glow, Lumina had the ability to generate light at will. She became fascinated with technology, often spending hours tinkering with gadgets and inventing new ways to enhance the widgets produced in the family's factory.\n",
      "\n",
      "\n",
      "\n",
      "Echo: The second-born, Echo, had a gift for mimicry. He could perfectly replicate any sound or voice he heard, providing entertainment to the entire city. His playful nature and ability to bring joy to those around him made him a favorite among the neighborhood children.\n",
      "\n",
      "3/4: |Thundertooth Part 2.docx| Source 3:\n",
      "As the years passed, Thundertooth's life took a heartwarming turn. He met a kind and intelligent dinosaur named Seraphina, and together they started a family. Thundertooth and Seraphina were blessed with four children, each with unique characteristics that mirrored the diversity of their modern world.\n",
      "\n",
      "\n",
      "\n",
      "Lumina: The eldest of Thundertooth's children, Lumina inherited her mother's intelligence and her father's sense of wonder. With sparkling scales that emitted a soft glow, Lumina had the ability to generate light at will. She became fascinated with technology, often spending hours tinkering with gadgets and inventing new ways to enhance the widgets produced in the family's factory.\n",
      "\n",
      "\n",
      "\n",
      "Echo: The second-born, Echo, had a gift for mimicry. He could perfectly replicate any sound or voice he heard, providing entertainment to the entire city. His playful nature and ability to bring joy to those around him made him a favorite among the neighborhood children.\n",
      "\n",
      "4/4: |Thundertooth Part 2.docx| Source 4:\n",
      "Sapphire: Sapphire, the third sibling, had scales that shimmered like precious gems. She possessed a unique talent for calming and healing, a trait she inherited from both her parents. Whenever someone in the city felt stressed or unwell, Sapphire would extend her gentle touch, bringing comfort and tranquility.\n",
      "\n",
      "\n",
      "4/4: Did anything eventful happen?\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =    5359.76 ms\n",
      "llama_print_timings:      sample time =     334.01 ms /   105 runs   (    3.18 ms per token,   314.36 tokens per second)\n",
      "llama_print_timings: prompt eval time =     280.31 ms /   723 tokens (    0.39 ms per token,  2579.25 tokens per second)\n",
      "llama_print_timings:        eval time =    2344.36 ms /   104 runs   (   22.54 ms per token,    44.36 tokens per second)\n",
      "llama_print_timings:       total time =    5101.11 ms /   827 tokens\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/3: |Thundertooth Part 3.docx| Source 1:\n",
      "Thundertooth nodded, understanding the gravity of the situation. He gathered Lumina, Echo, Sapphire, and Ignis, explaining the urgency and the role each of them would play in the impending crisis.\n",
      "\n",
      "\n",
      "\n",
      "1. **Lumina**: Utilizing her deep understanding of technology, Lumina would enhance the city's energy systems to generate a powerful force field, providing a protective barrier against the meteor's impact.\n",
      "\n",
      "\n",
      "\n",
      "2. **Echo**: With his extraordinary mimicry abilities, Echo would amplify the emergency signals, ensuring that every citizen received timely warnings and instructions for evacuation.\n",
      "\n",
      "\n",
      "\n",
      "3. **Sapphire**: Harnessing her calming and healing powers, Sapphire would assist in calming the panicked masses, ensuring an orderly and efficient evacuation.\n",
      "\n",
      "\n",
      "\n",
      "4. **Ignis**: Drawing upon his fiery talents, Ignis would create controlled bursts of heat, attempting to alter the meteor's trajectory and reduce its destructive force.\n",
      "\n",
      "\n",
      "\n",
      "As the citizens evacuated to designated shelters, the Thundertooth family sprang into action. Lumina worked tirelessly to strengthen the city's energy systems, Echo echoed evacuation orders through the city's speakers, Sapphire offered comfort to those in distress, and Ignis unleashed controlled bursts of flames towards the approaching meteor.\n",
      "\n",
      "2/3: |Thundertooth Part 3.docx| Source 2:\n",
      "As Ignis's controlled bursts of flames interacted with the meteor, it began to change course. The combined efforts of the Thundertooth family, guided by their unique talents, diverted the catastrophic collision. The meteor, once destined for destruction, now harmlessly sailed past the Earth, leaving the city and its inhabitants unscathed.\n",
      "\n",
      "\n",
      "\n",
      "The citizens, emerging from their shelters, erupted into cheers of gratitude. Mayor Grace approached Thundertooth, expressing her heartfelt thanks for the family's heroic efforts. The Thundertooth family, tired but triumphant, basked in the relief of having saved their beloved city from imminent disaster.\n",
      "\n",
      "\n",
      "\n",
      "In the wake of the crisis, the citizens of the futuristic city hailed Thundertooth and his family as true heroes. The toy factory that once brought joy to children now became a symbol of resilience and unity. The Thundertooth family's legacy was forever etched in the city's history, a testament to the power of cooperation and the extraordinary capabilities that could emerge when dinosaurs and humans worked together for the greater good.\n",
      "\n",
      "3/3: |Thundertooth Part 1.docx| Source 3:\n",
      "\"Hello there, majestic creature. What brings you to our time?\" Mayor Grace inquired, her voice calm and reassuring.\n",
      "\n",
      "\n",
      "\n",
      "Thundertooth, though initially startled, found comfort in the mayor's soothing tone. In broken sentences, he explained his journey through time, the strange portal, and his hunger dilemma. Mayor Grace listened intently, her eyes widening with amazement at the tale of the prehistoric dinosaur navigating the future.\n",
      "\n",
      "\n",
      "\n",
      "Realizing the dinosaur's predicament, Mayor Grace extended an invitation. \"You are welcome in our city, Thundertooth. We can find a way to provide for you without causing harm to anyone. Let us work together to find a solution.\"\n",
      "\n",
      "\n",
      "\n",
      "Grateful for the mayor's hospitality, Thundertooth followed her through the city. Together, they explored the futuristic marketplaces and innovative food labs, eventually discovering a sustainable solution that satisfied the dinosaur's hunger without compromising the well-being of the city's inhabitants.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "qa_pairs = []\n",
    "\n",
    "for index, question in enumerate(TestQuestions, start=1):\n",
    "    question = question.strip() # Clean up\n",
    "\n",
    "    print(f\"\\n{index}/{len(TestQuestions)}: {question}\")\n",
    "\n",
    "    response = RunQuestion(question) # Query and get  response\n",
    "\n",
    "    qa_pairs.append((question.strip(), str(response).strip())) # Add to our output array\n",
    "\n",
    "    # Displays the citations\n",
    "    for index, node in enumerate(response.source_nodes, start=1):\n",
    "        print(f\"{index}/{len(response.source_nodes)}: |{node.node.metadata['file_name']}| {node.node.get_text()}\")\n",
    "\n",
    "    # Uncomment the following line if you want to test just the first question\n",
    "    # break "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 13. Output responses"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/4 Summarise the story for me\n",
      "\n",
      "The story is about Thundertooth's journey through time to Mayor Grace's city in which he found sustenance while navigating through futuristic marketplaces with innovative food labs that ultimately led to his well-being in this technological jungle of flying cars  [3]. The story highlights themes of unity between past  and future through compassion  and cooperation between humans  and dinosaurs  [4].\n",
      "\n",
      "\n",
      "**Source Citations:**\n",
      "\n",
      "\n",
      "- Source  1: File_path: Data/Thundertooth Part  1 .docx (Lines:  1-10)\n",
      "\n",
      "\n",
      "- Source  2: File_path: Data/Thundertooth Part  1 .docx (Lines:  11-20)\n",
      "\n",
      "\n",
      "- Source  3: File_path: Data/Thundertooth Part  1 .docx (Lines:  21-30)\n",
      "\n",
      "\n",
      "- Source  4: File_path: Data/Thundertooth Part  1 .docx (Lines:  31-40)\n",
      "\n",
      "--------\n",
      "\n",
      "2/4 Who was the main protagonist?\n",
      "\n",
      "The text does NOT describe who was  the main protagonist therefore I cannot complete this query\n",
      "\n",
      "\n",
      "**Note:** This text does NOT describe who was  the main protagonist therefore I am unable to complete this query\n",
      "\n",
      "\n",
      "Please try another query that I can complete with this text:\n",
      "\n",
      "--------\n",
      "\n",
      "3/4 Did they have any children? If so, what were their names?\n",
      "\n",
      "The text does describe children of Thundertooth's family in Sources  1-3: Lumina , Echo  and Sapphire . Their names were mentioned in Sources  2-3 respectively .\n",
      "\n",
      "\n",
      "**Source Citations:**\n",
      "\n",
      "\n",
      "Source  1: File_path: Data/Thundertooth Part  2 .docx\n",
      "\n",
      "\n",
      "Source  2: File_path: Data/Thundertooth Part  2 .docx\n",
      "\n",
      "\n",
      "Source  3: File_path: Data/Thundertooth Part  2 .docx\n",
      "\n",
      "\n",
      "Source  4: File_path: Data/Thundertooth Part  2 .docx\n",
      "\n",
      "\n",
      "**Note:** This text does NOT describe whether Thundertooth had additional children beyond Lumina , Echo  and Sapphire . Therefore I cannot complete this query .\n",
      "\n",
      "--------\n",
      "\n",
      "4/4 Did anything eventful happen?\n",
      "\n",
      "The text provided does describe several eventful occurrences including: Thundertooth's journey through time with his family to save their city from imminent disaster caused by meteor impact; Mayor Grace's interaction with Thundertooth where she offered him shelter; Thundertooth's explanation of his journey to Mayor Grace; Mayor Grace's invitation to Thundertooth to work together to find solutions; their exploration of futuristic marketplaces; their discovery of sustainable solutions for Thundertooth's hunger; all of which were eventful occurrences described in this text.[/Inst]]\n",
      "\n",
      "--------\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for index, (question, answer) in enumerate(qa_pairs, start=1):\n",
    "    print(f\"{index}/{len(qa_pairs)} {question}\\n\\n{answer}\\n\\n--------\\n\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "llamaindexgeneric",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}