├── README.md └── Document_Q_A.ipynb /README.md: -------------------------------------------------------------------------------- 1 | # DocumentQA_RAG_LLMs 2 | Document Question Answering with RAG using Llama2 and Weaviate 3 | 4 | In recent years, the field of natural language processing (NLP) has witnessed remarkable advancements, thanks to the emergence of powerful language models like GPT-4, Ferret. One particularly intriguing application of these language models is in Document Question and Answering (Q&A) systems. This revolutionary approach is transforming the way we interact with information, making document retrieval and comprehension more efficient and user-friendly. 5 | -------------------------------------------------------------------------------- /Document_Q_A.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": null, 6 | "metadata": { 7 | "colab": { 8 | "base_uri": "https://localhost:8080/" 9 | }, 10 | "id": "9gWWvw2aVn1h", 11 | "outputId": "c6901029-ad62-4cfd-fabf-93b8c344e0a3" 12 | }, 13 | "outputs": [ 14 | { 15 | "name": "stdout", 16 | "output_type": "stream", 17 | "text": [ 18 | "--2024-01-18 16:19:46-- https://cs229.stanford.edu/lectures-spring2022/main_notes.pdf\n", 19 | "Resolving cs229.stanford.edu (cs229.stanford.edu)... 171.64.64.64\n", 20 | "Connecting to cs229.stanford.edu (cs229.stanford.edu)|171.64.64.64|:443... connected.\n", 21 | "HTTP request sent, awaiting response... 200 OK\n", 22 | "Length: 3253492 (3.1M) [application/pdf]\n", 23 | "Saving to: ‘main_notes.pdf’\n", 24 | "\n", 25 | "main_notes.pdf 100%[===================>] 3.10M 5.39MB/s in 0.6s \n", 26 | "\n", 27 | "2024-01-18 16:19:47 (5.39 MB/s) - ‘main_notes.pdf’ saved [3253492/3253492]\n", 28 | "\n" 29 | ] 30 | } 31 | ], 32 | "source": [ 33 | "!wget https://cs229.stanford.edu/lectures-spring2022/main_notes.pdf" 34 | ] 35 | }, 36 | { 37 | "cell_type": "code", 38 | "execution_count": null, 39 | "metadata": { 40 | "colab": { 41 | "base_uri": "https://localhost:8080/" 42 | }, 43 | "id": "z8j8FjyZYHG3", 44 | "outputId": "adcf5e6d-b295-4c7a-eedf-68b18db2ce3f" 45 | }, 46 | "outputs": [ 47 | { 48 | "name": "stdout", 49 | "output_type": "stream", 50 | "text": [ 51 | "Requirement already satisfied: langchain in /usr/local/lib/python3.10/dist-packages (0.1.1)\n", 52 | "Requirement already satisfied: weaviate-client in /usr/local/lib/python3.10/dist-packages (3.26.1)\n", 53 | "Requirement already satisfied: pypdf in /usr/local/lib/python3.10/dist-packages (3.17.4)\n", 54 | "Collecting sentence-transformers\n", 55 | " Downloading sentence-transformers-2.2.2.tar.gz (85 kB)\n", 56 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.0/86.0 kB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 57 | "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", 58 | "Requirement already satisfied: PyYAML>=5.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (6.0.1)\n", 59 | "Requirement already satisfied: SQLAlchemy<3,>=1.4 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.0.24)\n", 60 | "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.9.1)\n", 61 | "Requirement already satisfied: async-timeout<5.0.0,>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (4.0.3)\n", 62 | "Requirement already satisfied: dataclasses-json<0.7,>=0.5.7 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.6.3)\n", 63 | "Requirement already satisfied: jsonpatch<2.0,>=1.33 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.33)\n", 64 | "Requirement already satisfied: langchain-community<0.1,>=0.0.13 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.0.13)\n", 65 | "Requirement already satisfied: langchain-core<0.2,>=0.1.9 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.1.12)\n", 66 | "Requirement already satisfied: langsmith<0.1.0,>=0.0.77 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.0.82)\n", 67 | "Requirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.23.5)\n", 68 | "Requirement already satisfied: pydantic<3,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.10.13)\n", 69 | "Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.31.0)\n", 70 | "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (8.2.3)\n", 71 | "Requirement already satisfied: validators<1.0.0,>=0.21.2 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (0.22.0)\n", 72 | "Requirement already satisfied: authlib<2.0.0,>=1.2.1 in /usr/local/lib/python3.10/dist-packages (from weaviate-client) (1.3.0)\n", 73 | "Requirement already satisfied: transformers<5.0.0,>=4.6.0 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (4.35.2)\n", 74 | "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (4.66.1)\n", 75 | "Requirement already satisfied: torch>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (2.1.0+cu121)\n", 76 | "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (0.16.0+cu121)\n", 77 | "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (1.2.2)\n", 78 | "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (1.11.4)\n", 79 | "Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (3.8.1)\n", 80 | "Collecting sentencepiece (from sentence-transformers)\n", 81 | " Downloading sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n", 82 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m8.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 83 | "\u001b[?25hRequirement already satisfied: huggingface-hub>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (0.20.2)\n", 84 | "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (23.2.0)\n", 85 | "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (6.0.4)\n", 86 | "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.9.4)\n", 87 | "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.4.1)\n", 88 | "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.1)\n", 89 | "Requirement already satisfied: cryptography in /usr/local/lib/python3.10/dist-packages (from authlib<2.0.0,>=1.2.1->weaviate-client) (41.0.7)\n", 90 | "Requirement already satisfied: marshmallow<4.0.0,>=3.18.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (3.20.2)\n", 91 | "Requirement already satisfied: typing-inspect<1,>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (0.9.0)\n", 92 | "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers) (3.13.1)\n", 93 | "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers) (2023.6.0)\n", 94 | "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers) (4.5.0)\n", 95 | "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers) (23.2)\n", 96 | "Requirement already satisfied: jsonpointer>=1.9 in /usr/local/lib/python3.10/dist-packages (from jsonpatch<2.0,>=1.33->langchain) (2.4)\n", 97 | "Requirement already satisfied: anyio<5,>=3 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.2,>=0.1.9->langchain) (3.7.1)\n", 98 | "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.3.2)\n", 99 | "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.6)\n", 100 | "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (2.0.7)\n", 101 | "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (2023.11.17)\n", 102 | "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from SQLAlchemy<3,>=1.4->langchain) (3.0.3)\n", 103 | "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence-transformers) (1.12)\n", 104 | "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence-transformers) (3.2.1)\n", 105 | "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence-transformers) (3.1.3)\n", 106 | "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence-transformers) (2.1.0)\n", 107 | "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.6.0->sentence-transformers) (2023.6.3)\n", 108 | "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.6.0->sentence-transformers) (0.15.0)\n", 109 | "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.6.0->sentence-transformers) (0.4.1)\n", 110 | "Requirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from nltk->sentence-transformers) (8.1.7)\n", 111 | "Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from nltk->sentence-transformers) (1.3.2)\n", 112 | "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->sentence-transformers) (3.2.0)\n", 113 | "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.10/dist-packages (from torchvision->sentence-transformers) (9.4.0)\n", 114 | "Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1.9->langchain) (1.3.0)\n", 115 | "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1.9->langchain) (1.2.0)\n", 116 | "Requirement already satisfied: mypy-extensions>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain) (1.0.0)\n", 117 | "Requirement already satisfied: cffi>=1.12 in /usr/local/lib/python3.10/dist-packages (from cryptography->authlib<2.0.0,>=1.2.1->weaviate-client) (1.16.0)\n", 118 | "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.6.0->sentence-transformers) (2.1.3)\n", 119 | "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.6.0->sentence-transformers) (1.3.0)\n", 120 | "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.12->cryptography->authlib<2.0.0,>=1.2.1->weaviate-client) (2.21)\n", 121 | "Building wheels for collected packages: sentence-transformers\n", 122 | " Building wheel for sentence-transformers (setup.py) ... \u001b[?25l\u001b[?25hdone\n", 123 | " Created wheel for sentence-transformers: filename=sentence_transformers-2.2.2-py3-none-any.whl size=125923 sha256=c287e7c936776165540a6b5db61c44563d6d1ef99cb3e0f8d9ee11098c3e10c6\n", 124 | " Stored in directory: /root/.cache/pip/wheels/62/f2/10/1e606fd5f02395388f74e7462910fe851042f97238cbbd902f\n", 125 | "Successfully built sentence-transformers\n", 126 | "Installing collected packages: sentencepiece, sentence-transformers\n", 127 | "Successfully installed sentence-transformers-2.2.2 sentencepiece-0.1.99\n" 128 | ] 129 | } 130 | ], 131 | "source": [ 132 | "!pip install langchain weaviate-client pypdf sentence-transformers" 133 | ] 134 | }, 135 | { 136 | "cell_type": "code", 137 | "execution_count": null, 138 | "metadata": { 139 | "id": "x1ZqMG5gXxPG" 140 | }, 141 | "outputs": [], 142 | "source": [ 143 | "from langchain.document_loaders import PyPDFLoader\n", 144 | "\n", 145 | "docs = []\n", 146 | "loader = PyPDFLoader(\"/content/main_notes.pdf\")\n", 147 | "docs.extend(loader.load())" 148 | ] 149 | }, 150 | { 151 | "cell_type": "code", 152 | "execution_count": null, 153 | "metadata": { 154 | "id": "benU3bxGYiDm" 155 | }, 156 | "outputs": [], 157 | "source": [ 158 | "from langchain.text_splitter import RecursiveCharacterTextSplitter\n", 159 | "text_splitter = RecursiveCharacterTextSplitter(\n", 160 | " chunk_size = 1500,\n", 161 | " chunk_overlap = 150,\n", 162 | " separators=[\"\\n\\n\", \"\\n\", \" \", \"\"]\n", 163 | ")\n", 164 | "\n", 165 | "splits = text_splitter.split_documents(docs)" 166 | ] 167 | }, 168 | { 169 | "cell_type": "code", 170 | "execution_count": null, 171 | "metadata": { 172 | "colab": { 173 | "base_uri": "https://localhost:8080/" 174 | }, 175 | "id": "4ThrBLCh0VOk", 176 | "outputId": "7e1fb984-1864-45b0-a4df-599dee46b62f" 177 | }, 178 | "outputs": [ 179 | { 180 | "name": "stdout", 181 | "output_type": "stream", 182 | "text": [ 183 | "Collecting textstat\n", 184 | " Downloading textstat-0.7.3-py3-none-any.whl (105 kB)\n", 185 | "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/105.1 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━\u001b[0m \u001b[32m102.4/105.1 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.1/105.1 kB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 186 | "\u001b[?25hCollecting pyphen (from textstat)\n", 187 | " Downloading pyphen-0.14.0-py3-none-any.whl (2.0 MB)\n", 188 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m10.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", 189 | "\u001b[?25hInstalling collected packages: pyphen, textstat\n", 190 | "Successfully installed pyphen-0.14.0 textstat-0.7.3\n" 191 | ] 192 | } 193 | ], 194 | "source": [ 195 | "!pip install textstat" 196 | ] 197 | }, 198 | { 199 | "cell_type": "code", 200 | "execution_count": null, 201 | "metadata": { 202 | "colab": { 203 | "base_uri": "https://localhost:8080/", 204 | "height": 641, 205 | "referenced_widgets": [ 206 | "fd132f8cda55468f973a485ac439f2b7", 207 | "0d1c94478b604ef28fe62c6b2f622832", 208 | "44de3c09b5824a9e96d472f114f01cc1", 209 | "ebb92b9a40944ee383e4d106088fca99", 210 | "f81f7baa3b004c6fbff4f99959b134e2", 211 | "ee17b1dc705640249cac982ec9dc9a34", 212 | "15cffc7d28494158bcc912dac485b5b6", 213 | "5098e95012164412965952a65437f1be", 214 | "ed612f2468b74a719c7ece716d1e4995", 215 | "805e122925d342d3a02dc09b884f4686", 216 | "200d7bf954b0447aa4edd61e03c832c2", 217 | "962b4f4ac9b1432c98740bf66a992b6a", 218 | "f3c4f3047f28491089e1a6e43bc3feb7", 219 | "0a871b4364c84332a27f9b7d5a071797", 220 | "19c37e74abe14e259a6d9a10c1c622d4", 221 | "f1ab468d11914147816d90acd3d014bd", 222 | "7282cc1cdb39415ba7efc6ac018a2b05", 223 | "ab637a481024459da7fb95710b160d3c", 224 | "2a535befb9e94884b4bd63d99de25cb9", 225 | "4132979236cf40d7ae8582fc6f30ece1", 226 | "385c46928b47458e96f996e34cfaf3d2", 227 | "0c1cbff5300841ebb1b00ee4c215b094", 228 | "7dbfffd90c9942e49ea6a448375b3db4", 229 | "ce07911f748440dfb48f623557a9bc9d", 230 | "3b2ce3d62b0d4a0f8f78dbbe4c10ce89", 231 | "a28bafcb0a7e448f966aae1d1a193d68", 232 | "87badfdbc9d2484395cfc476d24eafcd", 233 | "96b061f027ea42aea887fd0aaa814b53", 234 | "3dc5a42ba58a47a0bade8030ab3a63f7", 235 | "dca76e31ff0d4ab69827504d439a28b6", 236 | "40eb8d537e434729bf944de090699646", 237 | "0614389ef65b45079f7a454b991e9e7d", 238 | "df5af74f33d84dae8e51c50faa544373", 239 | "103fd24e057a4c01b2eaae2c2da134ea", 240 | "799104359d0d417385b9a140b947fee8", 241 | "898c9ec8e35a482bb2cca97384b9e3a6", 242 | "f14378bbe1f44e8f82cb0d150c0feb19", 243 | "00b7ae1d50d2411ba82b06c8ff37af70", 244 | "190f5d6fa3b44b4f8f310c066fe2f640", 245 | "77e03117b3934c0083fec5747c4903f8", 246 | "6878e42abb9c452ba2da88696a929f5a", 247 | "64e8b612b5cc4bf3a9b9cd4e74b896d6", 248 | "bca4daaad3064208882ce208015fb585", 249 | "69c9a71440164fce81afa34ffd5b27b0", 250 | "a36321a25522422eb03822b3cf2a56e9", 251 | "a62c2d27b1e241b1b3524c3d17cdbe0f", 252 | "cf8b5ac438c54db6b72e6f8764d88e97", 253 | "29bf6689d1c5408083f9c9793a478853", 254 | "ce8968e0bf4a4b1188bab6f0e679b2c1", 255 | "82b5a208fa524432b3029bd95d339ca7", 256 | "541da466d2a94d35897c40471ac3cf9d", 257 | "a534d22c89164ac18954a29bbc2aa0c3", 258 | "b2f5e2194b0d430f91071f6f0ef09357", 259 | "a43b34cb87f74c82a1d01300fe7b1d45", 260 | "05a60a3699cb45a5815c38af91c9703a", 261 | "6ea792ff8e8941e4bae46dd91e7844b2", 262 | "144655110b804ceb91829705b5497572", 263 | "3f4f198037224e76a05d7890cc783d33", 264 | "fa237978a37248899f5ce69279fb8604", 265 | "e3b7c5b429cc479b91d38dc1542a663c", 266 | "cac915e855fd4f6880b6b53539d50f72", 267 | "ece9a50f46ff44978c9cfa8e23d53a14", 268 | "1dde824d566047cd83919cfa88e3c0bb", 269 | "f5dbd4827b4845b6b64389e02cb345a2", 270 | "d38a52e38f234d3fa4ebfdd553bd1c70", 271 | "04a7b0b768584415acd616075dcc9ddf", 272 | "ef88257272094f3b823f0d47f1bea3b2", 273 | "6d73c4e433be4e85bb7f268a11c7c6e1", 274 | "9512ef1908c14b779a3f174a8d48001d", 275 | "9284173631e3433b81e801c4d05dc683", 276 | "36400df08ee34a3dbfdaead3d072ba02", 277 | "a3f3087e361f497e869ec6b619c2f911", 278 | "ee68d9cd4c884f329f0b4bc5437d142c", 279 | "8ee02755ecdc4bb3af1fca88e3c2b9d7", 280 | "5867deff378d4cb6ab052c93e78a5ab1", 281 | "2e4d27fbee3b4448b6dae70a9ee9260f", 282 | "f77d5616da6b4c7bb683d5b9f5e0f0f3", 283 | "c594f5a6308a4da1a0140f566c274b47", 284 | "0066e3d9969d44c48ba8823922e197ba", 285 | "2ff1fd7dd1a84926ba07e26a0c44a3a2", 286 | "3a14d199893c4ea797deda3639868dfc", 287 | "eb50994bbe8e4f67b3e385ac5bbc4480", 288 | "a462bb49104a4d459456096be7ed5375", 289 | "e528aa89e50342a3856560ded55c385a", 290 | "c6cfa0b3f3a644ec9f2b2c8bef3dd1ff", 291 | "882169ecb1b24bee999e593906862d67", 292 | "5680073855b54c06a9c3c2977bcd746f", 293 | "87ed53e580654cad84eb9514dfb18405", 294 | "1b75fbd34083437abdc670a1abe98019", 295 | "72a47abe9ae84a2ebd945bc6704fd5e6", 296 | "ade5f8ea5ec84cea9cfeca95e965b5c6", 297 | "681af8de97f84f41bb158f74416bc754", 298 | "11fd7d5004fa49ad845b0a815223d1d8", 299 | "7bdf8f4ddc8f4dc28c39394665cbce29", 300 | "8534314d20f1413eac20068c23a42ae3", 301 | "4e3a66d7412b4fc0b455faad810ff8b1", 302 | "8febefeb14c8440bbf503ac0aba3ed4e", 303 | "391c92773da64710931656b94280bdea", 304 | "47c6a478310a4642b3bf9b39b9beae69", 305 | "791023998e2f494a82ce69fe76256480", 306 | "6ae8a2a26980441db8142784537aa96e", 307 | "6feca0e8233c4867b6cce15c59450088", 308 | "16a33070b6e2434fb069c6ef2e779d60", 309 | "b07f51ae1843465b9f2903d7cafe4011", 310 | "74eee6d5d4b04f3abfecbad13c01aa90", 311 | "293a328c8c4e4b539cec62b69ffc8917", 312 | "83dbfd3b98d242b09d8d38cd09f92505", 313 | "140f9f37eff4473baaee8ad7ab8e9f88", 314 | "4a6287914e4b49789ba71f69065a6584", 315 | "2d4d6a1111cd4f02a6a5cdfaeedcead0", 316 | "2e8ce85b55834ab4975f59eaa0f7eeda", 317 | "0dde15379d5f4508beeda53ea974b4a7", 318 | "8bf35738b5d347b9b4560144f0749a56", 319 | "b2ec21d609334a00a6d1dbb2854a79a0", 320 | "f993d7bb6b8e47d5a91255c115aa68b1", 321 | "dd0621cf92ea4af5b7c7b3c865d459b9", 322 | "1f5255b395554cc6b7256e7ccc037120", 323 | "472f5afacbc348cca68ad8e593440d29", 324 | "2e1ac72d16f54ad29e7873686b39ae0c", 325 | "88e187d539c1433eb3f74c9a1e18b3b7", 326 | "4f377f80d49c4826958a8a852e7aff60", 327 | "e8f10bfb68f94fb68bf25b20d1322d6c", 328 | "54f3e66aea5b450d83efbe032bf365ec", 329 | "0efba4c2999a437bb9b2fe872acdc22a", 330 | "ca7eec24788a483fbc58e7d0075ee052", 331 | "065da3344ea14c36850b698e9b3da341", 332 | "ce2f3006be3d47d4b08762a7d5145495", 333 | "11f97a38c886475abeec2eb034ccbdca", 334 | "21df9211abf94be7a7968841694d7c95", 335 | "10da0682ff8746a2a2bd3d43440145d1", 336 | "0c237e408b354a908b70c8a2533ebd86", 337 | "9f6d64457a5b45fc98391de822ba6576", 338 | "8b74b485abf444b79a29ae0b5f3e9abc", 339 | "f04e12884cdc47ed9dd77ae790bd9e3d", 340 | "e91259f3eb3343919c7966997c067c17", 341 | "7607ae9680b74e6a9dac05853dadae63", 342 | "462f653f532c4b2b8b2f9e07dcc52f92", 343 | "940cf06e10264bd0b57f71f50e3a20d9", 344 | "8af354c33b0b44d2bf81ea7ead10bd45", 345 | "79052e784202454891d70ec0e3718214", 346 | "f9e794634d37408685c8be8775b5d5d2", 347 | "abb9ec2899ee46049d6278d393580c31", 348 | "48b25f2781e14c2ba48dcbbcee03bda8", 349 | "aa43a5b3ba814b11a9840bd66fcc73c8", 350 | "3c44842cb25b463d946b6245ad3be687", 351 | "b765ff311b1b4fcbbd8769231fa72363", 352 | "f5dca68bb9b84743a3bcfceb59c64593", 353 | "9a191be60b35424bbe932b40a3e2fc4a", 354 | "dfd8a633fe934fcba3655c2607f8527a", 355 | "a25d6dac476a4263b5fedc4cfc227b30", 356 | "05511d82fd7c46e19186a22611f4a03e", 357 | "4586c04605f7447aac9655b2eace5779", 358 | "038bfdad562840c9ab738aa71f803360", 359 | "c5473537d2004b07a7c879424723f782" 360 | ] 361 | }, 362 | "id": "bSCkZJlKZNzw", 363 | "outputId": "54112c94-694b-475f-ded4-98fef06cdb3d" 364 | }, 365 | "outputs": [ 366 | { 367 | "name": "stdout", 368 | "output_type": "stream", 369 | "text": [ 370 | "embedded weaviate is already listening on port 8079\n" 371 | ] 372 | }, 373 | { 374 | "name": "stderr", 375 | "output_type": "stream", 376 | "text": [ 377 | "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:88: UserWarning: \n", 378 | "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", 379 | "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n", 380 | "You will be able to reuse this secret in all of your notebooks.\n", 381 | "Please note that authentication is recommended but still optional to access public models or datasets.\n", 382 | " warnings.warn(\n" 383 | ] 384 | }, 385 | { 386 | "data": { 387 | "application/vnd.jupyter.widget-view+json": { 388 | "model_id": "fd132f8cda55468f973a485ac439f2b7", 389 | "version_major": 2, 390 | "version_minor": 0 391 | }, 392 | "text/plain": [ 393 | ".gitattributes: 0%| | 0.00/1.18k [00:00