diff --git "a/scripts/05_Create_Test_Data.ipynb" "b/scripts/05_Create_Test_Data.ipynb" new file mode 100644--- /dev/null +++ "b/scripts/05_Create_Test_Data.ipynb" @@ -0,0 +1,9769 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "DI5fr-UTfdzg" + }, + "source": [ + "# Install Packages and Setup Variables" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "VTQEnvU2c4lQ", + "outputId": "6a52c70c-d375-4313-cd53-290299b37ec7" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/67.3 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m3.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", + " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m455.6/455.6 kB\u001b[0m \u001b[31m20.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m35.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m481.1/481.1 kB\u001b[0m \u001b[31m28.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m602.1/602.1 kB\u001b[0m \u001b[31m33.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m78.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m284.2/284.2 kB\u001b[0m \u001b[31m18.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.9/1.9 MB\u001b[0m \u001b[31m51.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.7/7.7 MB\u001b[0m \u001b[31m128.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m266.8/266.8 kB\u001b[0m \u001b[31m18.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.0/41.0 kB\u001b[0m \u001b[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m101.6/101.6 kB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m16.4/16.4 MB\u001b[0m \u001b[31m118.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m65.8/65.8 kB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m55.7/55.7 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.2/196.2 kB\u001b[0m \u001b[31m12.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m118.5/118.5 kB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.5/4.5 MB\u001b[0m \u001b[31m108.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m100.0/100.0 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m108.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m93.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m38.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m45.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m20.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m106.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m459.8/459.8 kB\u001b[0m \u001b[31m29.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m304.2/304.2 kB\u001b[0m \u001b[31m19.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.0/4.0 MB\u001b[0m \u001b[31m108.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m453.1/453.1 kB\u001b[0m \u001b[31m25.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.9/50.9 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.3/129.3 kB\u001b[0m \u001b[31m9.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n" + ] + } + ], + "source": [ + "!pip install -q llama-index==0.12.21 openai==1.59.8 tiktoken==0.8.0 huggingface-hub==0.30 chromadb==0.6.0 llama-index-vector-stores-chroma==0.4.1 llama-index-llms-gemini==0.4.1 llama-index-embeddings-adapter==0.3.0 llama-index-embeddings-huggingface==0.5.4" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "zREQvf1YeNra" + }, + "outputs": [], + "source": [ + "# set variables\n", + "import os\n", + "from google.colab import userdata\n", + "\n", + "os.environ[\"OPENAI_API_KEY\"] = userdata.get('openai_api_key')\n", + "\n", + "os.environ[\"HF_TOKEN\"] = userdata.get('HF_TOKEN2')\n", + "HF_TOKEN = userdata.get('HF_TOKEN2')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "q-E5-s41e785" + }, + "outputs": [], + "source": [ + "# Allows running asyncio in environments with an existing event loop, like Jupyter notebooks.\n", + "\n", + "import nest_asyncio\n", + "\n", + "nest_asyncio.apply()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "FTPF89SkEXVM" + }, + "source": [ + "# Load fine tuned embedding model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 163, + "referenced_widgets": [ + "c56d28b3e6314eb3ade9e007fda7824c", + "60429da42de84433b2cd2f659bc3724b", + "a7581c4f70284d4184dd13e617cd7d44", + "b270e7b1227444d6a62b49936ac722ae", + "bf14f079e1b14eb8a12edadfbf1b62bc", + "00227004a6ad42e5ab2547e456db65d9", + "9094eb7285244717a54814b7364efa88", + "a98c026668d24af7b1b87d8749c799ad", + "d71e680af3ad4310a2e45fe84c257f37", + "bc8869a9960241efbd57203cd5541df5", + "95e1a2701bfd4ba0992d323c8ab3f2df", + "8cc23cd30550448bb1462520d19d82f1", + "8aeaa66d05dc4607acd40be24d2fe338", + "01c7b61f145a483f8cf4a8fb8bbda7cb", + "140d8461566a47ac949b6e9c2ef045ac", + "fdb7eb03d5a74ac489e27a3fec460343", + "d625fda8d11840d68122ca3db454be63", + "862dd6a5509e40708f768a61f3672e44", + "0c61fba8b48041a0a40d1491a0fa5685", + "800f91d9e2c94adaa3febef5191f33cf", + "3ce302c95dba43df924173772b3fbd9d", + "548cfb2a2538424e8b8e7aecc3d12958", + "5b99b5e402bd49c299138db03259e7b2", + "a2059855e1cc404d8db5e2468ce0fe79", + "bb20bcfba4564ea9ba4325b60bd78b2f", + "7c8b8e54df3c45d3a2c3024c784652ff", + "0aaf530322c143ee9bf37f05eb78cb6e", + "7d4bb62aee0c4370b7fa6058110f7f00", + "54e5a21b96cf4f1f84da42eaff6a9512", + "a70d02738ac04ac9be2712671ef91869", + "8856ab89048d4fffabfa5573bee8b899", + "571e8f3bf3f34479b73ea500d75eaf82", + "5f6dfc06c0a64e0dafae1f4711031da6", + "b62c816958c94fffb0a4445965011826", + "0c8eb120b2674f12a82f55c9fcf92d12", + "57569d2bde074e2ca7387b19c91662a9", + "567b94e385414e3e93527d5674d70b54", + "b6500694b7e142efbba648c17c1e3141", + "3da086825b7c42fea9959571dbe7c2e6", + "9d0378b70d5046669769e508f24f0196", + "8f06dce76ba44a7fb133bc78e0a125d2", + "5ad68fb9e19048399ca10310d8a72e55", + "8747e61400a940509764f7edec730f75", + "447a44fbcffa4ccabe4ab46d4791dd9a" + ] + }, + "id": "8VlKC4qyEIsf", + "outputId": "83a0e984-26ff-4f9c-e1de-84612593bab8" + }, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "c56d28b3e6314eb3ade9e007fda7824c", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Fetching 3 files: 0%| | 0/3 [00:00