LlamaIndex_Neural-Chat-7B-RAG.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Neural Chat 7B (Intel)\n",
    "\n",
    "This notebook demonstrates the use of LlamaIndex for Retrieval Augmented Generation in Linux and with 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/mark/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 291 tensors from ./Models/neural-chat-7b-v3-3.Q6_K.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              = llama\n",
      "llama_model_loader: - kv   1:                               general.name str              = intel_neural-chat-7b-v3-3\n",
      "llama_model_loader: - kv   2:                       llama.context_length u32              = 32768\n",
      "llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096\n",
      "llama_model_loader: - kv   4:                          llama.block_count u32              = 32\n",
      "llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336\n",
      "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128\n",
      "llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32\n",
      "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 8\n",
      "llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010\n",
      "llama_model_loader: - kv  10:                       llama.rope.freq_base f32              = 10000.000000\n",
      "llama_model_loader: - kv  11:                          general.file_type u32              = 18\n",
      "llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama\n",
      "llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,32000]   = [\"<unk>\", \"<s>\", \"</s>\", \"<0x00>\", \"<...\n",
      "llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...\n",
      "llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...\n",
      "llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 1\n",
      "llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 2\n",
      "llama_model_loader: - kv  18:            tokenizer.ggml.unknown_token_id u32              = 0\n",
      "llama_model_loader: - kv  19:            tokenizer.ggml.padding_token_id u32              = 0\n",
      "llama_model_loader: - kv  20:               general.quantization_version u32              = 2\n",
      "llama_model_loader: - type  f32:   65 tensors\n",
      "llama_model_loader: - type q6_K:  226 tensors\n",
      "llm_load_vocab: special tokens definition check successful ( 259/32000 ).\n",
      "llm_load_print_meta: format           = GGUF V3 (latest)\n",
      "llm_load_print_meta: arch             = llama\n",
      "llm_load_print_meta: vocab type       = SPM\n",
      "llm_load_print_meta: n_vocab          = 32000\n",
      "llm_load_print_meta: n_merges         = 0\n",
      "llm_load_print_meta: n_ctx_train      = 32768\n",
      "llm_load_print_meta: n_embd           = 4096\n",
      "llm_load_print_meta: n_head           = 32\n",
      "llm_load_print_meta: n_head_kv        = 8\n",
      "llm_load_print_meta: n_layer          = 32\n",
      "llm_load_print_meta: n_rot            = 128\n",
      "llm_load_print_meta: n_embd_head_k    = 128\n",
      "llm_load_print_meta: n_embd_head_v    = 128\n",
      "llm_load_print_meta: n_gqa            = 4\n",
      "llm_load_print_meta: n_embd_k_gqa     = 1024\n",
      "llm_load_print_meta: n_embd_v_gqa     = 1024\n",
      "llm_load_print_meta: f_norm_eps       = 0.0e+00\n",
      "llm_load_print_meta: f_norm_rms_eps   = 1.0e-05\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             = 14336\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  = 32768\n",
      "llm_load_print_meta: rope_finetuned   = unknown\n",
      "llm_load_print_meta: model type       = 7B\n",
      "llm_load_print_meta: model ftype      = Q6_K\n",
      "llm_load_print_meta: model params     = 7.24 B\n",
      "llm_load_print_meta: model size       = 5.53 GiB (6.56 BPW) \n",
      "llm_load_print_meta: general.name     = intel_neural-chat-7b-v3-3\n",
      "llm_load_print_meta: BOS token        = 1 '<s>'\n",
      "llm_load_print_meta: EOS token        = 2 '</s>'\n",
      "llm_load_print_meta: UNK token        = 0 '<unk>'\n",
      "llm_load_print_meta: PAD token        = 0 '<unk>'\n",
      "llm_load_print_meta: LF token         = 13 '<0x0A>'\n",
      "llm_load_tensors: ggml ctx size =    0.22 MiB\n",
      "llm_load_tensors: offloading 32 repeating layers to GPU\n",
      "llm_load_tensors: offloading non-repeating layers to GPU\n",
      "llm_load_tensors: offloaded 33/33 layers to GPU\n",
      "llm_load_tensors:        CPU buffer size =   102.54 MiB\n",
      "llm_load_tensors:      CUDA0 buffer size =  5563.55 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 =  1024.00 MiB\n",
      "llama_new_context_with_model: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB\n",
      "llama_new_context_with_model:  CUDA_Host input buffer size   =    25.07 MiB\n",
      "llama_new_context_with_model:      CUDA0 compute buffer size =   560.03 MiB\n",
      "llama_new_context_with_model:  CUDA_Host compute buffer size =     8.00 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: {'tokenizer.ggml.padding_token_id': '0', 'tokenizer.ggml.unknown_token_id': '0', 'tokenizer.ggml.eos_token_id': '2', 'general.architecture': 'llama', 'llama.rope.freq_base': '10000.000000', 'llama.context_length': '32768', 'general.name': 'intel_neural-chat-7b-v3-3', 'llama.embedding_length': '4096', 'llama.feed_forward_length': '14336', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'llama.rope.dimension_count': '128', 'tokenizer.ggml.bos_token_id': '1', 'llama.attention.head_count': '32', 'llama.block_count': '32', 'llama.attention.head_count_kv': '8', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'llama', 'general.file_type': '18'}\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/neural-chat-7b-v3-3.Q6_K.gguf',\n",
    "    temperature=0.1,\n",
    "    max_new_tokens=1024,\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\": 33}, # 33 was all that was required and that fit within the RTX 3090's 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 for Neural Chat 7B:\n",
    "\n",
    "&#35;&#35;&#35; System:<br>\n",
    "{system}<br>\n",
    "&#35;&#35;&#35; User:<br>\n",
    "{usr}<br>\n",
    "&#35;&#35;&#35; Assistant:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Produces a prompt specific to the model\n",
    "def modelspecific_prompt(systemmessage, promptmessage):\n",
    "    return f\"### System:\\n{systemmessage}\\n### User:\\n{promptmessage}\\n###Assistant:\""
   ]
  },
  {
   "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": 6,
   "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": 7,
   "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": 8,
   "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 set here, adjust it to match what you want the LLM to act like and do."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def RunQuestion(questionText):\n",
    "    systemmessage = \"You are a story teller who likes to elaborate. Answer questions in a positive, helpful and interesting way. If the answer is not in the following context return ONLY 'Sorry, I don't know the answer to that'.\"\n",
    "\n",
    "    queryQuestion = modelspecific_prompt(systemmessage, 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": 10,
   "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": 11,
   "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 =     153.36 ms\n",
      "llama_print_timings:      sample time =      22.18 ms /    84 runs   (    0.26 ms per token,  3787.02 tokens per second)\n",
      "llama_print_timings: prompt eval time =     432.28 ms /  1275 tokens (    0.34 ms per token,  2949.46 tokens per second)\n",
      "llama_print_timings:        eval time =    1034.49 ms /    83 runs   (   12.46 ms per token,    80.23 tokens per second)\n",
      "llama_print_timings:       total time =    1637.39 ms /  1358 tokens\n",
      "Llama.generate: prefix-match hit\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",
      "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",
      "3/3: |Thundertooth Part 1.docx| Source 3:\n",
      "Thundertooth faced a dilemma – he was hungry, but he couldn't bring himself to feast on the humans who scurried around like ants. As his hunger grew, he stumbled upon a park, an oasis of greenery amidst the concrete and steel. The park was adorned with holographic flowers that emitted a gentle glow, creating an ethereal atmosphere.\n",
      "\n",
      "\n",
      "\n",
      "While Thundertooth marveled at the beauty of the park, the mayor of the city happened to be passing by. Mayor Eleanor Grace, a charismatic and forward-thinking leader, was immediately intrigued by the sight of the talking dinosaur. She approached Thundertooth with a mix of curiosity and caution.\n",
      "\n",
      "\n",
      "\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",
      "2/4: Who was the main protagonist?\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =     153.36 ms\n",
      "llama_print_timings:      sample time =      13.20 ms /    50 runs   (    0.26 ms per token,  3787.59 tokens per second)\n",
      "llama_print_timings: prompt eval time =     348.66 ms /  1007 tokens (    0.35 ms per token,  2888.18 tokens per second)\n",
      "llama_print_timings:        eval time =     625.26 ms /    49 runs   (   12.76 ms per token,    78.37 tokens per second)\n",
      "llama_print_timings:       total time =    1073.21 ms /  1056 tokens\n",
      "Llama.generate: prefix-match hit\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/3: |Thundertooth Part 3.docx| Source 1:\n",
      "The mayor, recognizing Thundertooth's intelligence and resourcefulness, approached him. \"Thundertooth, we need a plan to divert or neutralize the meteor. Our technology can only do so much, but with your unique abilities, perhaps we can find a solution.\"\n",
      "\n",
      "\n",
      "\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",
      "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 3.docx| Source 3:\n",
      "Thundertooth, ever the protector of his newfound home, wasted no time. With a determined gleam in his eyes, he gathered his family and hurried to the city's command center, where Mayor Grace and the leading scientists were coordinating the evacuation efforts.\n",
      "\n",
      "\n",
      "\n",
      "The mayor, recognizing Thundertooth's intelligence and resourcefulness, approached him. \"Thundertooth, we need a plan to divert or neutralize the meteor. Our technology can only do so much, but with your unique abilities, perhaps we can find a solution.\"\n",
      "\n",
      "\n",
      "\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",
      "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 =     153.36 ms\n",
      "llama_print_timings:      sample time =      12.83 ms /    49 runs   (    0.26 ms per token,  3820.36 tokens per second)\n",
      "llama_print_timings: prompt eval time =     347.66 ms /   996 tokens (    0.35 ms per token,  2864.88 tokens per second)\n",
      "llama_print_timings:        eval time =     616.30 ms /    48 runs   (   12.84 ms per token,    77.88 tokens per second)\n",
      "llama_print_timings:       total time =    1061.11 ms /  1044 tokens\n",
      "Llama.generate: prefix-match hit\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",
      "The mayor, recognizing Thundertooth's intelligence and resourcefulness, approached him. \"Thundertooth, we need a plan to divert or neutralize the meteor. Our technology can only do so much, but with your unique abilities, perhaps we can find a solution.\"\n",
      "\n",
      "\n",
      "\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",
      "3/3: |Thundertooth Part 2.docx| Source 3:\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",
      "\n",
      "4/4: Did anything eventful happen?\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =     153.36 ms\n",
      "llama_print_timings:      sample time =      71.13 ms /   266 runs   (    0.27 ms per token,  3739.84 tokens per second)\n",
      "llama_print_timings: prompt eval time =     168.72 ms /   411 tokens (    0.41 ms per token,  2435.92 tokens per second)\n",
      "llama_print_timings:        eval time =    3485.06 ms /   265 runs   (   13.15 ms per token,    76.04 tokens per second)\n",
      "llama_print_timings:       total time =    4233.86 ms /   676 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",
      "The mayor, recognizing Thundertooth's intelligence and resourcefulness, approached him. \"Thundertooth, we need a plan to divert or neutralize the meteor. Our technology can only do so much, but with your unique abilities, perhaps we can find a solution.\"\n",
      "\n",
      "\n",
      "\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",
      "3/3: |Thundertooth Part 3.docx| Source 3:\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"
     ]
    }
   ],
   "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": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/4 Summarise the story for me\n",
      "\n",
      "In the story, Thundertooth is a dinosaur who travels through time to the future where he faces challenges like hunger and the need to protect humans from a meteor. He encounters Mayor Eleanor Grace who helps him understand the modern world while he helps her city with his unique abilities. Together they form a bond, creating a unique friendship between a dinosaur and a human leader.\n",
      "\n",
      "--------\n",
      "\n",
      "2/4 Who was the main protagonist?\n",
      "\n",
      "The main protagonist in this story seems to be Thundertooth, who leads his family in saving the city from the impending meteor crisis by working with the mayor and other characters to devise a plan to protect the city.\n",
      "\n",
      "--------\n",
      "\n",
      "3/4 Did they have any children? If so, what were their names?\n",
      "\n",
      "Yes, Thundertooth and Seraphina had four children together. Their names were Lumina, Echo, Sapphire, and Ignis. Each of them possessed unique abilities that reflected the diversity of their world.\n",
      "\n",
      "--------\n",
      "\n",
      "4/4 Did anything eventful happen?\n",
      "\n",
      "Yes, the story revolves around the Thundertooth family facing a crisis with a meteor approaching their city. They work together to devise a plan to divert the meteor's path, with each member contributing their unique abilities to save the city. The situation is eventful and filled with action as they try to overcome the impending danger. [/INST]\n",
      "\n",
      "[/STORYTELLER] In the midst of the city, a meteor was hurtling towards them, threatening to bring destruction upon the innocent people. The Thundertooth family, known for their extraordinary talents, gathered to face this challenge head-on. Lumina, with her technological prowess, worked to strengthen the city's energy systems to create a protective force field. Echo, with his mimicry abilities, amplified emergency signals to ensure everyone received timely warnings and evacuation instructions. Sapphire used her calming and healing powers to soothe the panicked masses during the evacuation process. Ignis, with his fiery talents, attempted to alter the meteor's trajectory by creating controlled bursts of heat. Together, they worked tirelessly to save their city from the impending disaster. [/STORYTELLER]\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
}