{
"cells": [
{
"cell_type": "markdown",
"id": "dfe37963-1af6-44fc-a841-8e462443f5e6",
"metadata": {},
"source": [
"## Chat with Ed - the Expert on LLM engineering\n",
"This project will: \n",
"- use subtitle files from Ed Donners excellent LLM engineering course on Udemy.\n",
"- use Document loading using Langchain\n",
"- use Vectorization, embeddings and store vectors in a Chroma DB\n",
"- use RAG (Retrieval Augmented Generation) to ensure our question/answering assistant has high accuracy.\n",
"\n",
"These subtitles can be downloaded using the following process:\n",
"- Using an android phone, download Udemy app and open the LLM engineering course. \n",
"- There is option to download the videos as single files or section wise. \n",
"- Download them and along with those videos subs or cc are also downloaded as .srt’s.\n",
"- Plug in your laptop to the android phone using USB and select file transfer in the notification.\n",
"- Open a file explorer and copy the subtitle files (srt format)\n",
"- Here’s the location of subs in android \"internal storage/android/data/com.udemy.android/files/udemy-subtitle-downloads\"\n",
"\n",
"the raw srt files are stored in the folder \"subtitles/srts\". The code below will use the langchain textloader but will preprocess the srt files to remove the timestamps.\n",
"\n",
"### Note: this is only for educational and testing purposes and you should contact Ed Donnner to seek his permission if you want to use the subtitles.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ba2779af-84ef-4227-9e9e-6eaf0df87e77",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\n",
"import glob\n",
"from dotenv import load_dotenv\n",
"import gradio as gr\n",
"import re"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "802137aa-8a74-45e0-a487-d1974927d7ca",
"metadata": {},
"outputs": [],
"source": [
"# imports for langchain\n",
"\n",
"from langchain.document_loaders import DirectoryLoader, TextLoader\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.schema import Document\n",
"from langchain_openai import OpenAIEmbeddings, ChatOpenAI\n",
"from langchain_chroma import Chroma\n",
"import numpy as np\n",
"from sklearn.manifold import TSNE\n",
"import plotly.graph_objects as go\n",
"from langchain.memory import ConversationBufferMemory\n",
"from langchain.chains import ConversationalRetrievalChain"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "58c85082-e417-4708-9efe-81a5d55d1424",
"metadata": {},
"outputs": [],
"source": [
"# price is a factor for our company, so we're going to use a low cost model\n",
"\n",
"MODEL = \"gpt-4o-mini\"\n",
"db_name = \"vector_db\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "ee78efcb-60fe-449e-a944-40bab26261af",
"metadata": {},
"outputs": [],
"source": [
"# Load environment variables in a file called .env\n",
"\n",
"load_dotenv()\n",
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "730711a9-6ffe-4eee-8f48-d6cfb7314905",
"metadata": {},
"outputs": [],
"source": [
"# Read in documents using LangChain's loaders\n",
"# Take everything in all the sub-folders of our knowledgebase\n",
"\n",
"folders = glob.glob(\"subtitles/srts/*\")\n",
"\n",
"# With thanks to CG and Jon R, students on the course, for this fix needed for some users \n",
"text_loader_kwargs = {'encoding': 'utf-8'}\n",
"# If that doesn't work, some Windows users might need to uncomment the next line instead\n",
"# text_loader_kwargs={'autodetect_encoding': True}\n",
"\n",
"def preprocess_srt_content(content):\n",
" \"\"\"\n",
" Preprocess the content of an SRT file to remove timing information and the WEBVTT header.\n",
" \"\"\"\n",
" # Remove the WEBVTT header\n",
" content = re.sub(r'^WEBVTT\\s*', '', content, flags=re.IGNORECASE)\n",
" # Remove timing lines (e.g., 00:00.680 --> 00:08.540)\n",
" content = re.sub(r'\\d{2}:\\d{2}\\.\\d{3} --> \\d{2}:\\d{2}\\.\\d{3}', '', content)\n",
" # Remove extra newlines and strip leading/trailing whitespace\n",
" return \"\\n\".join(line.strip() for line in content.splitlines() if line.strip())\n",
"\n",
"documents = []\n",
"for folder in folders:\n",
" video_number = os.path.basename(folder)\n",
" loader = DirectoryLoader(folder, glob=\"**/en_US.srt\", loader_cls=TextLoader)\n",
" folder_docs = loader.load()\n",
"\n",
" for doc in folder_docs:\n",
" # Preprocess the document content\n",
" cleaned_content = preprocess_srt_content(doc.page_content)\n",
" # Replace the original content with the cleaned content\n",
" doc.page_content = cleaned_content\n",
" # Add metadata\n",
" doc.metadata[\"video_number\"] = video_number\n",
" documents.append(doc)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7310c9c8-03c1-4efc-a104-5e89aec6db1a",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
"chunks = text_splitter.split_documents(documents)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "cd06e02f-6d9b-44cc-a43d-e1faa8acc7bb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"217"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(chunks)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "2c54b4b6-06da-463d-bee7-4dd456c2b887",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Video numbers found: 59507785, 59472503, 59170107, 60616493, 59504887, 59297735, 59472429, 59170291, 60595637, 59473019, 59472441, 59295423, 59170043, 59472067, 59295363, 59472425, 59297723, 59473137, 59473159, 59669375, 59472011, 59295431, 59673721, 59473101, 59167015, 59670087, 60619429, 59667365, 59673639, 59169985, 59507489, 60620143, 59505329, 59670369, 59295549, 60395261, 59668181, 59671231, 60619281, 59506713, 59472491, 59295579, 59167007, 59167009, 59666211, 59673431, 59671567, 59170055, 59472017, 59473021, 59297599, 59472027, 59166947, 59473201, 60619123, 59472873, 59295601, 60614591, 60614541, 59472007, 59507313, 60619721, 59297595, 59472693, 59295527, 60619501, 59166981, 59166421, 59507423, 59170165, 59166951, 59170227, 59673663, 59670121, 59166453, 60616845, 59471979, 59670171, 59503705, 59668923, 60617163, 60616629, 59297693, 59166915, 60617259, 59166847, 59295459, 60619439, 59297593, 59295619, 59472883, 59295439, 59670933, 60619651, 59670073, 59166465, 59295429, 59669631, 59170233, 59472333, 59507635, 60619227, 59667829, 59166353, 60614589, 59295599, 59507687, 59671441, 59170057, 59670259, 59170235, 59472307, 59472421, 59667841, 59667357, 59166949, 59170297, 59504785, 59170093, 59166443, 59673595, 59669211, 60620025, 59297773, 60619883, 60616423, 59295493, 59166461, 60616855, 59297601, 59295435, 59673449, 59503703, 59472505, 59295377, 59166281, 59507435, 59297575, 59504769, 59170037, 60622463, 59508289, 60616663, 60616895, 60620375, 60619247, 59665129, 59170135, 59297743, 59169991, 59506929, 60616407, 59508297, 59297603, 60616927, 60617255, 59295441, 59668027, 59297609, 60620169, 59472383, 59297585, 60616623, 60617251, 59666831, 59295553, 59473191, 59473089, 59669217, 59508175, 60616833, 59297749, 59295609, 59295545, 59669389, 59170025, 60619619, 60620397, 59166481, 59295541, 59297561, 59166919, 59507329, 59506611, 59170223, 60619447, 59166317, 59473071, 60619299, 59507017, 59509185, 59170255, 60619577, 59671221, 60619289, 59508121, 59295583, 60619149, 59665127, 59473147, 59295451, 59271655, 59472137, 59295607, 59669049, 59295587, 59472463, 59506507, 59472413, 59297721, 59508057, 59508055, 59671315, 59297733, 60619275, 60620395, 59505337\n"
]
}
],
"source": [
"video_numbers = set(chunk.metadata['video_number'] for chunk in chunks)\n",
"print(f\"Video numbers found: {', '.join(video_numbers)}\")"
]
},
{
"cell_type": "markdown",
"id": "77f7d2a6-ccfa-425b-a1c3-5e55b23bd013",
"metadata": {},
"source": [
"## A sidenote on Embeddings, and \"Auto-Encoding LLMs\"\n",
"\n",
"We will be mapping each chunk of text into a Vector that represents the meaning of the text, known as an embedding.\n",
"\n",
"OpenAI offers a model to do this, which we will use by calling their API with some LangChain code.\n",
"\n",
"This model is an example of an \"Auto-Encoding LLM\" which generates an output given a complete input.\n",
"It's different to all the other LLMs we've discussed today, which are known as \"Auto-Regressive LLMs\", and generate future tokens based only on past context.\n",
"\n",
"Another example of an Auto-Encoding LLMs is BERT from Google. In addition to embedding, Auto-encoding LLMs are often used for classification.\n",
"\n",
"### Sidenote\n",
"\n",
"In week 8 we will return to RAG and vector embeddings, and we will use an open-source vector encoder so that the data never leaves our computer - that's an important consideration when building enterprise systems and the data needs to remain internal."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "78998399-ac17-4e28-b15f-0b5f51e6ee23",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Vectorstore created with 217 documents\n"
]
}
],
"source": [
"# Put the chunks of data into a Vector Store that associates a Vector Embedding with each chunk\n",
"# Chroma is a popular open source Vector Database based on SQLLite\n",
"\n",
"embeddings = OpenAIEmbeddings()\n",
"\n",
"# If you would rather use the free Vector Embeddings from HuggingFace sentence-transformers\n",
"# Then replace embeddings = OpenAIEmbeddings()\n",
"# with:\n",
"# from langchain.embeddings import HuggingFaceEmbeddings\n",
"# embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-MiniLM-L6-v2\")\n",
"\n",
"# Delete if already exists\n",
"\n",
"if os.path.exists(db_name):\n",
" Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()\n",
"\n",
"# Create vectorstore\n",
"\n",
"vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)\n",
"print(f\"Vectorstore created with {vectorstore._collection.count()} documents\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "057868f6-51a6-4087-94d1-380145821550",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The vectors have 1,536 dimensions\n"
]
}
],
"source": [
"# Get one vector and find how many dimensions it has\n",
"\n",
"collection = vectorstore._collection\n",
"sample_embedding = collection.get(limit=1, include=[\"embeddings\"])[\"embeddings\"][0]\n",
"dimensions = len(sample_embedding)\n",
"print(f\"The vectors have {dimensions:,} dimensions\")"
]
},
{
"cell_type": "markdown",
"id": "b0d45462-a818-441c-b010-b85b32bcf618",
"metadata": {},
"source": [
"## Visualizing the Vector Store\n",
"\n",
"Let's take a minute to look at the documents and their embedding vectors to see what's going on."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "bf021654-a60b-4905-bdb5-d4517bd0c297",
"metadata": {},
"outputs": [],
"source": [
"# Convert the video numbers into unique colors that we can visualize\n",
"import hashlib\n",
"\n",
"def video_numbers_to_hex_colors(video_numbers):\n",
" return [f\"#{hashlib.sha256(v.encode()).hexdigest()[:6]}\" for v in video_numbers]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "b98adf5e-d464-4bd2-9bdf-bc5b6770263b",
"metadata": {},
"outputs": [],
"source": [
"# Prework\n",
"\n",
"result = collection.get(include=['embeddings', 'documents', 'metadatas'])\n",
"vectors = np.array(result['embeddings'])\n",
"documents = result['documents']\n",
"video_numbers = [metadata['video_number'] for metadata in result['metadatas']]\n",
"colors = video_numbers_to_hex_colors(video_numbers)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "427149d5-e5d8-4abd-bb6f-7ef0333cca21",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.plotly.v1+json": {
"config": {
"plotlyServerURL": "https://plot.ly"
},
"data": [
{
"hoverinfo": "text",
"marker": {
"color": [
"#f8d349",
"#d6d07a",
"#a958c9",
"#7341ee",
"#268bba",
"#4862ce",
"#dd8cd7",
"#6a6c06",
"#8a29da",
"#0d2037",
"#805527",
"#e69670",
"#75b5e3",
"#796278",
"#6d4052",
"#1f6ab0",
"#99fe53",
"#3f0a72",
"#fe8e92",
"#c3e1f2",
"#f645e0",
"#b43417",
"#e0a8df",
"#7740be",
"#43c2e8",
"#64f999",
"#2cde7f",
"#29fa15",
"#580c96",
"#10384a",
"#845aa9",
"#7f03bd",
"#2b3af3",
"#335dcf",
"#22398f",
"#c932c1",
"#d43c00",
"#e6f378",
"#08808d",
"#6a0fce",
"#e1b5db",
"#75195e",
"#6ff3c5",
"#4099c1",
"#b25d7b",
"#d65c3a",
"#9b9d6e",
"#fc2b74",
"#571122",
"#422abb",
"#efed10",
"#dfc6c7",
"#02cada",
"#3ec815",
"#8e8cab",
"#df5d2e",
"#c457d7",
"#ec0a37",
"#da28db",
"#2d7f7d",
"#b27d2e",
"#d01b19",
"#fb9dce",
"#35303c",
"#4f86b8",
"#fbfef2",
"#ca3592",
"#c1e3c5",
"#c97596",
"#091a90",
"#b280bb",
"#7b4427",
"#b2140a",
"#dbde1c",
"#7ea8e9",
"#539908",
"#8069bc",
"#d01f72",
"#4ce72d",
"#73e76a",
"#20f2c3",
"#996ff1",
"#91f4db",
"#d70d97",
"#3678a7",
"#5af098",
"#ae5204",
"#badd6d",
"#a9541c",
"#d4b1ce",
"#51d0da",
"#ff2d6a",
"#1c2c7e",
"#ae7afe",
"#d156c8",
"#480c89",
"#e2a239",
"#39821f",
"#7bee34",
"#92b4fa",
"#b9fd23",
"#591ab9",
"#0bdacc",
"#2a2d25",
"#dc152c",
"#ac9648",
"#6ad041",
"#fe62a5",
"#52b6df",
"#4aaf9f",
"#d34482",
"#2fef1a",
"#7dd58b",
"#987252",
"#94a85d",
"#2b9f18",
"#ee26df",
"#c6016b",
"#9df332",
"#9b5e28",
"#2ebca4",
"#1b312a",
"#2e1afc",
"#574e28",
"#ac55ba",
"#f090af",
"#5cb9ca",
"#2dcfac",
"#804ce2",
"#ce865d",
"#3e5237",
"#482281",
"#2ae342",
"#6df6ca",
"#85fa26",
"#793548",
"#bbfe83",
"#15ae86",
"#70d1d9",
"#bb0ee6",
"#a95826",
"#8afd40",
"#505bd9",
"#0c777d",
"#ed694d",
"#4e797a",
"#dc95ec",
"#612b32",
"#ad8b14",
"#474ff9",
"#71c500",
"#bd53b1",
"#11a70e",
"#144ada",
"#72e048",
"#188ca3",
"#b52bf6",
"#b64eac",
"#f59c06",
"#b1c27d",
"#ac5faf",
"#5b3f83",
"#108c41",
"#b61e76",
"#22463b",
"#c959de",
"#a64739",
"#659222",
"#0f8781",
"#2c168d",
"#0faf59",
"#68bece",
"#696eaa",
"#af0f59",
"#a9e927",
"#601568",
"#9780cf",
"#e01073",
"#dd889c",
"#046e5c",
"#c6eff5",
"#b3dba5",
"#426575",
"#913568",
"#de30e4",
"#50f10d",
"#9a5ba2",
"#cc8ec0",
"#79c82a",
"#9baca0",
"#1a5613",
"#246fa5",
"#cb725f",
"#682d42",
"#a03134",
"#d54222",
"#01f59b",
"#12897b",
"#74a788",
"#fcdcad",
"#048452",
"#3626a5",
"#4dfb77",
"#4212f1",
"#116019",
"#ad6bd0",
"#a63fa4",
"#d24e5d",
"#1a6fdf",
"#6f745a",
"#cf7e83",
"#4b9a93",
"#799a24",
"#e6e164",
"#011995",
"#4c4355",
"#d937bd"
],
"opacity": 0.8,
"size": 5
},
"mode": "markers",
"text": [
"Video: 59506507
Text: Well, I realized that was a whole lot of theory, but I hope it gave you a good intuition that will\nb...",
"Video: 59671315
Text: Okay, so here we are, back in Jupyter Lab, ready for the next use of a frontier model, and see this\n...",
"Video: 60616895
Text: It feels like 100 videos ago that I told you that we were going to have instant gratification with o...",
"Video: 60619275
Text: And we will conclude our expedition into the world of frontier models through their chat interface b...",
"Video: 59472693
Text: Friends.\nI am absolutely exhausted.\nI am exhausted and a little tiny bit traumatized.\nAnd you are so...",
"Video: 59670121
Text: So it's business time right now.\nWe are going to build a Rag pipeline to estimate the price of produ...",
"Video: 59295619
Text: Welcome back to the the moment when we bring it all together into a beautiful user interface.\nBut fi...",
"Video: 60617163
Text: And already that wraps up day two.\nNow that you have built that solution.\nAnd congratulations on tha...",
"Video: 60616423
Text: So I hope you've just enjoyed yourself experimenting with different LMS locally on your box using th...",
"Video: 59170227
Text: Welcome back to Google Colab.\nHere we are ready to explore the wonderful world of Tokenizers.\nSo, uh...",
"Video: 59169985
Text: So I hope you enjoyed that whirlwind tour of Google Colab.\nHere's just a little screenshot example o...",
"Video: 60616927
Text: It's time for our first LM experiment at this point.\nSo some of this you may know well, you may know...",
"Video: 59673721
Text: And here we are in JupyterLab for the last time, and we are looking here at day five, the last day\no...",
"Video: 59508055
Text: I'm so very happy that you've reached this epic moment in the course and that you're hanging in ther...",
"Video: 59670259
Text: It's remarkable.\nBut you are now at the 95% point.\nThere's 5% remaining of this course.\nUh, maybe it...",
"Video: 60616623
Text: So we're now going to start week one of the course when we are going to be looking at exploring fron...",
"Video: 59472383
Text: And welcome back to the week six folder.\nWe're now at day two, which is the second and final stage o...",
"Video: 59670171
Text: So as the very final step on this part four of day two of week eight, we are now going to build an\ne...",
"Video: 59297721
Text: And so now the time has come to talk about the most crucial aspect of Rag, which is the idea of vect...",
"Video: 59297599
Text: Well, that was a sneaky detour I took you on in the last one.\nI hope you enjoyed it though, and I ho...",
"Video: 59507635
Text: Look, I hope you're excited.\nYou really should be.\nYou've been through 80% of the course and it's al...",
"Video: 59669375
Text: Here we are for the day.\n2.1 notebook.\nAnd don't let it be said that I don't ever do anything for yo...",
"Video: 59297733
Text: Welcome back to JupyterLab and welcome to your first experiment with the world of Long Chain.\nLet me...",
"Video: 59670369
Text: It is terrific that you're hanging on in there and making such great progress with this course.\nAs w...",
"Video: 59166281
Text: And with that, amazingly, you completed day one of week two already and that gets you to the 15% poi...",
"Video: 59671567
Text: Well, the first thing you're going to notice is that I don't have a notebook open for you.\nAnd that'...",
"Video: 59297593
Text: And welcome to continuing our journey with Hrag.\nAnd today it's time to unveil Liang Chen.\nSo first,...",
"Video: 59166461
Text: And welcome back to the lab.\nHere we are in Jupyter Lab and we are going to go into week two.\nAnd we...",
"Video: 59167007
Text: Well, how fabulous is that?\nI hope that you are as wowed as I am by our new airline, I assistant and...",
"Video: 59508121
Text: The moment has arrived.\nHere we go.\nWe're in fine tuning.\nWe do fine tuning.\nTrain.\nThere is also a ...",
"Video: 59295579
Text: All right.\nAre you excited to see how this goes?\nLet's give it a try.\nSo in this next section, I cre...",
"Video: 60620375
Text: And with that, we've reached an important milestone.\nThe first week of our eight week journey is com...",
"Video: 59472491
Text: Welcome back.\nIf you are following along with me in JupyterLab, as I hope you are, then you will nee...",
"Video: 59472425
Text: Welcome to week six, day three.\nToday is going to be a day that you will either love or you will hat...",
"Video: 59508057
Text: Actually slight change in plan.\nI'm going to wrap up the day.\nDay three at this point, and say that ...",
"Video: 60619577
Text: And for the final piece of background information, I wanted to take another moment to talk about API...",
"Video: 59170291
Text: Welcome back to Colab and welcome back to our business project.\nSo again our assignment, we are due ...",
"Video: 60619651
Text: I mentioned before an AI company called vellum.\nWhen we were talking about the different questions, ...",
"Video: 59473191
Text: And you thought we'd never get here.\nHere we are in Jupyter Lab, running our fine tuning for a front...",
"Video: 59170297
Text: And here we are in Google Colab, ready for fun with models.\nSo first we do the usual Pip installs an...",
"Video: 59167015
Text: Welcome back to Jupyter Lab and welcome to Day Five's Lab.\nAnd this is going to be lots of creativit...",
"Video: 59170043
Text: Let me enthusiastically welcome you all back to week three of our LLM engineering journey.\nIf you en...",
"Video: 59473147
Text: Well, I'm very relieved.\nI've got that behind me.\nNo more human testing for me.\nWe'll have one final...",
"Video: 59166453
Text: Welcome back and welcome to our continuing JupyterLab experience.\nUh, I'm hopefully going to keep yo...",
"Video: 59166915
Text: Welcome back to the wonderful world of JupyterLab.\nAnd here we are in week two.\nDay three.\nUh, bring...",
"Video: 59667365
Text: Here we are back in Colab, looking at the week seven, day five of the Colab notebooks and I'm on a\nT...",
"Video: 60616845
Text: We're on the home stretch.\nThis is the final step in the environment setup, and it's an easy one.\nIt...",
"Video: 59295459
Text: And welcome back to More Leaderboard Fest as we go through some more leaderboards.\nBut this time we'...",
"Video: 59471979
Text: So we now turn to the parts of the problem, which is perhaps, let's say, not as glamorous as some\nof...",
"Video: 59503705
Text: And so now we talk about quantization the q and q Laura.\nQ stands for quantized quantized.\nLaura.\nAn...",
"Video: 59472505
Text: So the good news is that this is the very final video about data set curation.\nYou were probably fed...",
"Video: 59669217
Text: And welcome to the next part of visualizing the data.\nAnd just very quickly to show it to you in 3D....",
"Video: 59671221
Text: I gotta tell you, I don't like to toot my horn a whole lot, but I do think that I've done a great\njo...",
"Video: 59503703
Text: Well.\nHello there everybody.\nI am so grateful that you've made it through to the start of week seven...",
"Video: 59473201
Text: Well, before we do a postmortem on what happened, let's just quickly look at the standing the rankin...",
"Video: 60622463
Text: In this video, we're going to set up a full data science environment for Mac users.\nIn the next vide...",
"Video: 60619299
Text: Well, I hope you found that both educational and enjoyable.\nAs we went through and learned so much a...",
"Video: 59295607
Text: So to revisit then the solution that we built in the previous day and talk about the metrics.\nAs I s...",
"Video: 59297575
Text: Well, welcome to the final part on rag.\nAnd this is the session where you go from being a rag expert...",
"Video: 59507687
Text: It's time for action, everybody.\nWe've set up our colab.\nHere we are, week seven, day three.\nWe've g...",
"Video: 59671441
Text: And welcome once more to our favorite place to be Jupyter Lab, the Paradise for a data scientist exp...",
"Video: 59673431
Text: And here we have it.\nThe user interface is completed.\nThe extra notification came through on my phon...",
"Video: 59473137
Text: Let's get straight to it.\nSo the place where you can see everything that's going on and get knee dee...",
"Video: 59166421
Text: Welcome back to the radio day in the lab.\nMore to do.\nLet's keep going.\nWhere we left off is we had ...",
"Video: 59295599
Text: Welcome to the Jupyter Lab for day four.\nIt's going to look very familiar because it's actually I've...",
"Video: 59669631
Text: Here we are in our favorite place to be in JupyterLab, ready for some coding and a lot of coding tha...",
"Video: 59673663
Text: But wait, there's more.\nWe need to add some more to the user interface just to make it look more coo...",
"Video: 59506929
Text: And we return to the hugging face open LLM leaderboard.\nThe first place you go when selecting your b...",
"Video: 59504785
Text: So at this point we're going to talk about hyperparameters.\nAnd we're going to introduce three of th...",
"Video: 59505337
Text: So we're now going to look at four bit quantization, the rather remarkable effect of reducing the pr...",
"Video: 59271655
Text: So here we are on Hugging Face's main landing page at Hugging Face Core.\nA URL you know.\nWell, since...",
"Video: 59472883
Text: Okay, time to reveal the results.\nIt has run to completion.\nAnd here it is.\nSo a moment to pause.\nIt...",
"Video: 59673639
Text: And welcome now to the code for our user interface, which we will find in this Python module.\nPrice ...",
"Video: 59472463
Text: So last time we looked at a humble linear regression model with feature engineering, and now we say\n...",
"Video: 59297595
Text: So by the time you're watching this, hopefully you have played yourself with vectors.\nYou've created...",
"Video: 60619149
Text: So we're going to start our exploration into the world of frontier models by playing with the famous...",
"Video: 59297735
Text: And at last the time has come to see rag in action.\nAfter all of this talk, and here we are.\nWe're i...",
"Video: 60616407
Text: And now over to my Mac people.\nAnd I have news for you.\nIt's exactly the same thing.\nYou go to a fav...",
"Video: 59170235
Text: So here we are in Google Colab for our first collaborative session on the cloud using a GPU box.\nOn ...",
"Video: 59472067
Text: So we've covered steps 1 to 4 of the five step strategy.\nAnd that brings us to step five, which is p...",
"Video: 59472011
Text: Welcome everybody.\nSo in the past I've said quite a few times, I am excited to start this this week ...",
"Video: 59295553
Text: Welcome back.\nIn the last part, we gave our GPT four and clawed the challenge of converting a simple...",
"Video: 59297773
Text: Well, I hope you're eager with anticipation for this session in JupyterLab as we finally get to see\n...",
"Video: 59295583
Text: And here we are back in JupyterLab.\nIt's been a minute.\nWe've been working in Colab for last week, a...",
"Video: 59507329
Text: Okay.\nIt's moment of truth time.\nI have just taken our class tester.\nYou remember this class?\nUh, it...",
"Video: 59295429
Text: Continuing our investigation of benchmarks, and this will become more real when we actually see some...",
"Video: 60595637
Text: Here we are back in the Colab, which has been running overnight for me and probably for you too, I\nh...",
"Video: 59668027
Text: And so here we are at the home page for modal.\nAt modal.com spelt model not not model which is confu...",
"Video: 59295527
Text: I'm so happy to welcome you to week four, day four on our journey to LLM Engineering and Mastery.\nHe...",
"Video: 59295377
Text: Just before we go on to some of the more advanced metrics, I want to mention for a second something\n...",
"Video: 59666211
Text: So before we try our new model and one more recap on the models so far and keep notes of this so we\n...",
"Video: 59170107
Text: And once again, it's that moment when you take a pause and congratulate yourself on another day of\ns...",
"Video: 60616833
Text: So I realized that day one of week one has been a pretty long day, and I assure you that the other,\n...",
"Video: 59472413
Text: Wonderful.\nWhere we left off is we had just created the Get Features function, which builds our feat...",
"Video: 59297561
Text: And would you believe at this point you're 55% of the way along the journey?\nUh, it's been a while s...",
"Video: 59669211
Text: Well, we took on a lot today and we seem to have been successful.\nThese red icons that you see on th...",
"Video: 59166981
Text: Welcome to week two, day five.\nThe last day of week two where a lot is coming together.\nI am so grat...",
"Video: 60619227
Text: And now let's move to Claude from anthropic, my favorite model and typically the favorite model of\nm...",
"Video: 60620395
Text: Welcome back to Jupyter Lab, where I want to show you the assignment, the homework exercise for you\n...",
"Video: 59665127
Text: Well hi there everybody.\nI'm not going to give you my usual song and dance about how excited you are...",
"Video: 59668923
Text: Well, welcome back to Jupyter Lab for what will be an epic finale to our time in this platform.\nAnd ...",
"Video: 59504887
Text: Well, here we are again in Google Colab.\nIt's been a minute since we were here, and welcome back to ...",
"Video: 59170165
Text: Welcome, everybody to the last day of week three.\nWeek three.\nDay five.\nWe're here already wrapping ...",
"Video: 60617251
Text: Congratulations are definitely in order.\nYesterday was a mammoth first day on this course and you go...",
"Video: 59166951
Text: All right, back to the lab.\nBack to our project.\nTime to work with tools.\nI am in the week two folde...",
"Video: 60619619
Text: Well, day four was an information dense day.\nI do hope that you learned some something useful here, ...",
"Video: 60616663
Text: Well.\nHi there, this is time for PC people to get set up.\nSo all you Mac people out there, you don't...",
"Video: 59508175
Text: So I'm taking a moment now to explain that the training costs of optimizing a model for this course\n...",
"Video: 59670087
Text: And welcome to part four of day two of week eight.\nUh, there's a lot happening this week, and I have...",
"Video: 59506713
Text: Hi everyone.\nSo the reason I'm so fired up about week seven is that this is the time when we actuall...",
"Video: 60620169
Text: Hopefully you found this super satisfying to be able to have this nice business result and have it c...",
"Video: 59295435
Text: Well, just before we wrap up, let me introduce this week's challenge and talk about what we're going...",
"Video: 59297609
Text: Last week, we worked with models that were able to speed up code by a factor of 60,000 times, which\n...",
"Video: 59507489
Text: Continuing our adventure through hyperparameters for training.\nThe next one is pretty crucial and it...",
"Video: 59295549
Text: And welcome back to our challenge again.\nAnd this time we are working with our beautiful prototype.\n...",
"Video: 59665129
Text: And now let me make this real for you by showing you some, some diagrams, particularly now looking\na...",
"Video: 59169991
Text: Okay, so that was your introduction to Hugging Face.\nAnd now I'm going to turn to a different resour...",
"Video: 59472027
Text: And now the time has come to curate our data set.\nAnd the way we're going to do this is we're going ...",
"Video: 59472307
Text: Welcome to week six.\nDay two a day.\nWhen we get back into the data, we look back in anger at our dat...",
"Video: 59508289
Text: So here we are now, back in the Colab, in the same one that we kicked off in the previous day.\nIt's ...",
"Video: 59472333
Text: Thank you for putting up with me during my foray into traditional machine learning.\nI think it was u...",
"Video: 59295431
Text: Now I want to take a quick moment to give you a flyby of five different ways that llms are used comm...",
"Video: 59673449
Text: Well, I have to tell you that I'm a little bit sad.\nThis is the beginning of the beginning of the en...",
"Video: 59669389
Text: Well.\nHi there.\nSo you've made it to day two of week eight, and I am super grateful that you've been...",
"Video: 59170057
Text: And so at the beginning of this week, we started by talking about hugging face pipelines.\nAnd you us...",
"Video: 59166949
Text: Welcome back to making chatbots.\nLet's keep going.\nSo for the next part we're going to beef up the s...",
"Video: 59473019
Text: Welcome back to an action packed time of of training.\nSo now, after waiting about five minutes when ...",
"Video: 59297585
Text: Before we move on, let me show you one more time this fabulous slide that describes the simple three...",
"Video: 59170255
Text: And welcome back to us continuing our journey through the model class in Hugging Face Transformers l...",
"Video: 60614589
Text: So we're now going to run a large language model directly on your box using a platform called llama,...",
"Video: 59297601
Text: I'm not going to lie, at this point you have every reason to be impatient with me.\nWe've been yammer...",
"Video: 60616629
Text: And welcome back to team PC and Team Mac as we come back together again for a quick video.\nIn this o...",
"Video: 59297749
Text: It's always welcome back to JupyterLab, my favorite place to be.\nAnd now we are, of course in the we...",
"Video: 59170135
Text: Welcome.\nIt's week three.\nIt's day four.\nWe are back on the adventure in open source land, back inve...",
"Video: 59472017
Text: And this is the first time that we'll be coding against our big project of the course.\nWelcome to Ju...",
"Video: 59507017
Text: Welcome to Colab.\nWelcome to the week seven day two Colab.\nAnd just before we try our base model, we...",
"Video: 60619883
Text: And now we've arrived at an exciting moment in our first week.\nThe conclusion of the first week is w...",
"Video: 59508297
Text: What more is there to say, really?\nTomorrow is the day for results.\nA day that very excited indeed a...",
"Video: 60619247
Text: We're going to spend a little bit more time with GPT just to try out a few more interesting things.\n...",
"Video: 59504769
Text: Without further ado, we're going to get stuck into it.\nTalking about Laura.\nLow rank adaptation.\nAnd...",
"Video: 59170233
Text: Welcome back to our continued exploits with Tokenizers.\nWhat we're now going to look at is what's ca...",
"Video: 59671231
Text: And here we are back in the Jupyter Lab for the fast approaching conclusion with a really great proj...",
"Video: 60620397
Text: Well, that's a fantastic result to have now arrived towards the end of week one and having completed...",
"Video: 59170093
Text: I'm delighted to see you again.\nAs we get started with day three of week three of our adventure and ...",
"Video: 59473089
Text: Welcome back.\nSo hopefully you are still impressed by the GPT four mini results.\nThe frontier model ...",
"Video: 60395261
Text: Let's keep going with our project to equip our LM with a tool.\nWe just created this piece of code to...",
"Video: 60617259
Text: I'm excited to introduce you to your first exercise, and I'm looking forward to seeing what you make...",
"Video: 59507313
Text: And it's this time again, when we look at the podium of how our models are performing across the boa...",
"Video: 60619721
Text: Now it's time to talk for a minute about tokens.\nTokens are the individual units which get passed in...",
"Video: 59295451
Text: I know that everybody.\nIt seems like just the other day that we were embarking on our quest together...",
"Video: 59166919
Text: And with that, it concludes our session on tools.\nAnd at this point, you are probably an expert on t...",
"Video: 59295441
Text: Okay, so welcome to our leaderboard fast as we go through a ton of essential leaderboards for your\nc...",
"Video: 59295541
Text: And welcome back.\nYou've just seen GPT four zero spectacularly failed to work on our hard Python con...",
"Video: 59473101
Text: Welcome back.\nSo about ten minutes later, maybe 15 minutes later, the run has completed.\nAnd how do ...",
"Video: 59507423
Text: So you may remember eons ago when we were building our data set.\nAt the end of that, we uploaded our...",
"Video: 59295545
Text: I really hope you've enjoyed this week.\nWe've got tons done.\nWe've experimented with all sorts of ne...",
"Video: 59472503
Text: Welcome back to Jupyter Lab.\nLast time, we looked at some silly models for predicting the price of p...",
"Video: 60614591
Text: The mantra of this course is that the best way to learn is by doing, and we will be doing stuff toge...",
"Video: 59473021
Text: Welcome to our favorite place to be to JupyterLab.\nHere we are again now in day three.\nIn week six.\n...",
"Video: 60617255
Text: I'm now going to talk for a bit about models.\nA term you often hear is the term frontier models, whi...",
"Video: 59667829
Text: Well.\nHello there.\nLook, I know what you're thinking.\nYou're thinking I peaked too early.\nLast week ...",
"Video: 59505329
Text: Welcome back.\nYou may, like me, have just gone off and got a coffee while things loaded back up agai...",
"Video: 59669049
Text: So what you just saw was an ephemeral app, as it's called, which means just a temporary app that you...",
"Video: 60619439
Text: This now brings us to an extremely important property of LMS called the context window that I want t...",
"Video: 59668181
Text: And so it gives me great pleasure to introduce to you the project that I've lined up for you this we...",
"Video: 59472441
Text: Welcome back.\nSo we've been doing the thoroughly distasteful, unsavory work of feature engineering.\n...",
"Video: 59507785
Text: Well, I'm sure you're fed up of me saying that the moment of truth has arrived, but it really has.\nT...",
"Video: 59295587
Text: When I left you, we had just created this simple user interface for converting from Python to C plus...",
"Video: 59166465
Text: Welcome back to the JupyterLab on Gradio day, so you'll remember where we left off.\nWe'd written two...",
"Video: 59473071
Text: Hey, gang.\nLook, I know what you're thinking.\nThis week was supposed to be training week.\nI set it a...",
"Video: 59295423
Text: Welcome to day two of week four, when we get more into leaderboards so that by the end of this, you'...",
"Video: 59297723
Text: So I know what you're thinking.\nYou're thinking, what's going on here?\nWe're on day five.\nWe're on d...",
"Video: 59166947
Text: Well, thank you for coming along for week two, day four.\nWe have lots of good stuff in store today.\n...",
"Video: 59666831
Text: Take one more moment to look at this very nice diagram that lays it all out, and we will move on.\nNo...",
"Video: 59295493
Text: And welcome to week four, day three.\nAs we are about to embark upon another business project which w...",
"Video: 60616855
Text: Now I know what you're thinking.\nWe've been building environments for so long.\nAre we not done yet?\n...",
"Video: 59506611
Text: So in a future day, I'm going to be training, fine tuning a model and creating a fine tuned model.\nA...",
"Video: 60616493
Text: I'll just take a quick moment to introduce myself to convince you that I am actually qualified to be...",
"Video: 59166317
Text: And welcome to week two, day two, as we continue our adventure into the realm of LMS.\nUh, so today, ...",
"Video: 59295439
Text: So I'm aware that there's a big risk that you are getting fed up of leaderboards, because we've done...",
"Video: 59472421
Text: And welcome back to our final time in Jupyter Lab with traditional machine learning.\nIt's almost ove...",
"Video: 59472137
Text: Well, well, well, it's been a long day, but congratulations, you've made it.\nWe've gone through and ...",
"Video: 59297693
Text: So at the end of each week, it's customary for me to give you a challenge, an assignment to do on\nyo...",
"Video: 60620143
Text: So we're going to make a call to GPT four.\nOh, that's going to ask it to look through a set of links...",
"Video: 60619501
Text: I welcome to day four of our time together.\nThis is a very important day.\nToday we're going to be lo...",
"Video: 59297743
Text: And welcome to day five.\nFor reals.\nWe're actually in the proper Jupyter notebook.\nThis time we're i...",
"Video: 59166847
Text: Well, they say that time flies when you're having fun, and it certainly feels like time is flying.\nU...",
"Video: 59170223
Text: Well.\nFantastic.\nIt's coming up to the end of the week, and that means it's coming up to a challenge...",
"Video: 59170037
Text: So how does it feel to be 30% of the way down the journey to being a proficient LLM engineer?\nTake a...",
"Video: 59295609
Text: You must be feeling absolutely exhausted at this point.\nAnd if you are, that is okay.\nYou have done ...",
"Video: 60619281
Text: Well, I'm delighted to welcome you to day three of our eight week journey together.\nAnd today we're ...",
"Video: 59472429
Text: And continuing on our strategy to solve commercial problems with LMS, we get to step four, which is\n...",
"Video: 59167009
Text: Welcome back.\nIt's time to make our full agent framework.\nI'm super excited about this.\nIt's pulling...",
"Video: 59166481
Text: And here, once more we find ourselves in our favorite place, the Jupyter Lab.\nReady to go with weeks...",
"Video: 59670933
Text: I realized my enthusiasm for this project is a bit insane, but I have to tell you that I am very sat...",
"Video: 59670073
Text: Okay, it's time to complete the Rag workflow in our Jupyter Lab on day 2.3.\nWe've got this function ...",
"Video: 59673595
Text: That concludes a mammoth project.\nThree weeks in the making.\nIn the course of those three weeks, sta...",
"Video: 59297603
Text: And I'm delighted to welcome you back to LM engineering on the day that we turn to vectors.\nFinally,...",
"Video: 60614541
Text: I am delighted to welcome you to the first day of our eight weeks together as you join me on this ad...",
"Video: 59667357
Text: Let's now see our results side by side.\nWe started our journey with a constant model that was at $1....",
"Video: 59667841
Text: Now, look, I know that I went through that very fast, but maybe, uh, you're still, uh, blinking\nat t...",
"Video: 59472007
Text: So I hope you enjoyed our first bash at Scrubbing Data, and that you are now looking through the cod...",
"Video: 59507435
Text: So I'm now going to talk about five important hyperparameters for the training process.\nAnd some of ...",
"Video: 59509185
Text: So this is where I left you looking at this satisfying chart on training loss and seeing the trainin...",
"Video: 59473159
Text: Welcome to Jupyter Lab and welcome to our experiments at the frontier.\nSo we are going to put our fr...",
"Video: 60619447
Text: I want to take a moment to talk about something that's very fundamental to an LLM, which is the numb...",
"Video: 59166353
Text: Well, congratulations on leveling up yet again.\nYou've got some real hard skills that you've added t...",
"Video: 60619123
Text: So what we're now going to do is we're going to look at some models in practice and start to compare...",
"Video: 59295363
Text: Well, another congratulations moment.\nYou have 40% on the way to being an LM engineer at a high leve...",
"Video: 60619289
Text: And now we'll go a bit faster through the other models.\nWe'll start with Google's Gemini.\nI have the...",
"Video: 59472873
Text: So it's quite an adventure that we had at the frontier of what's capable with Llms today, solving a\n...",
"Video: 60619429
Text: Let me talk about some other phenomena that have happened over the last few years.\nOne of them has b...",
"Video: 59295601
Text: So it's time to continue our journey into the world of open source and understand which models we sh...",
"Video: 59170025
Text: And a massive welcome back one more time to LM engineering.\nWe are in week three, day two and we are...",
"Video: 59166443
Text: And welcome back everybody.\nWelcome to week two day three.\nIt's a continuation of our enjoyment of r...",
"Video: 60620025
Text: And welcome back to Jupyter Lab, one of my very favorite places to be.\nWhen Jupyter Lab sprung up on...",
"Video: 59170055
Text: Welcome to the world of Google Colab.\nYou may already be very familiar with Google Colab, even if so..."
],
"type": "scatter",
"x": [
-12.833365,
-6.9742827,
12.4054785,
0.7444725,
-3.2209346,
-1.8923138,
12.045013,
3.3449032,
3.1842198,
-4.9479027,
-5.4305677,
8.906914,
7.4986606,
-8.522678,
-0.6965641,
6.603374,
-11.045361,
-4.2061296,
-0.6122766,
4.145742,
-15.19937,
-3.4401643,
1.4189938,
-1.4075196,
2.407112,
-2.5531256,
3.4384673,
8.128717,
2.1237493,
-12.902143,
15.229833,
2.7304206,
-10.246402,
-3.2447436,
-8.882521,
8.555937,
5.628159,
7.8938856,
-5.265052,
-8.822166,
7.8464785,
-3.648399,
-8.064129,
9.394255,
8.501753,
-9.501365,
15.182271,
4.720065,
-1.1797574,
-13.243277,
-9.353854,
-2.998534,
-1.1271738,
0.3913053,
-8.308189,
14.194027,
1.6540549,
1.3559673,
4.259716,
-9.247647,
-5.802019,
-3.195949,
-10.075436,
9.626325,
11.068077,
-3.1101823,
6.4528036,
5.0787916,
-15.360518,
-12.8956175,
-5.790258,
-9.99366,
6.8768044,
-4.6994433,
0.35191682,
-0.29200283,
3.0990727,
12.57883,
-5.6075945,
-1.0033067,
-2.449439,
16.036858,
0.14201127,
10.2873335,
-10.185286,
1.0699235,
-11.33001,
9.997939,
5.053496,
-0.6908192,
-7.4411364,
-1.8156531,
4.695986,
-7.3850956,
0.85939574,
-0.68879485,
0.79399765,
2.6232824,
10.725368,
-14.1221,
9.375242,
-9.608614,
-1.8901383,
5.7741113,
6.4975615,
3.5574346,
14.212662,
-11.486093,
-4.2505164,
-2.822659,
10.812861,
5.9373355,
4.6210785,
-14.758913,
14.809078,
-14.101901,
-8.283896,
-8.942637,
-1.4648409,
-12.052869,
-6.616761,
4.2436285,
0.8798934,
1.789862,
-2.2955062,
8.728576,
-11.620666,
3.6742375,
-7.761937,
12.48991,
3.6297722,
14.6792555,
2.5280774,
-3.2109888,
-10.203885,
-5.4021983,
8.246243,
-3.1352522,
12.564423,
-13.406111,
-3.866553,
-2.1669235,
7.9661245,
-3.791727,
-8.225956,
5.954079,
10.361685,
-7.5399003,
-3.2611566,
-0.9431268,
1.2448666,
4.4184537,
14.7139845,
-10.79534,
-9.544763,
4.5476527,
-7.414183,
3.5664093,
-6.974854,
2.978243,
2.393447,
-9.970659,
9.268733,
8.52153,
2.8192813,
-7.411628,
-10.112688,
13.632619,
9.394551,
-4.6803446,
3.9642556,
-0.22321175,
5.192608,
-15.408804,
6.085784,
9.131328,
-12.507938,
13.225102,
7.411992,
2.4457388,
-5.3649106,
-2.1621914,
2.9738903,
11.734665,
1.3640592,
2.8509138,
1.5292069,
3.109312,
0.31427717,
0.59937334,
1.9934503,
5.054161,
-0.7211345,
9.357517,
1.1712533,
-1.6295905,
1.4415473,
-0.5701214,
13.127944,
-7.282712,
8.714061,
-0.2947172,
-14.72166,
-12.058422,
-7.3617206,
-2.8723657,
5.6522145,
1.3458288,
4.7146225,
0.14565246,
-6.5029964,
1.4029636,
5.10695,
-4.3713784,
7.316387,
12.153176,
-8.246752
],
"y": [
5.864612,
-7.79562,
2.1185772,
10.241048,
-4.6602664,
-10.380204,
-3.3814008,
5.1946826,
1.7420042,
8.918891,
5.260133,
0.1811261,
-5.5230923,
0.5748871,
1.231967,
3.553936,
-10.655771,
-8.0794115,
-13.241925,
-14.984945,
4.7148366,
-13.97179,
-13.19601,
-0.2265177,
3.8162532,
2.1463737,
-14.238365,
-4.559269,
2.1515036,
-1.085198,
-4.2104445,
3.3605366,
-10.949242,
-5.0520687,
0.5021872,
10.118524,
1.5675689,
11.071112,
-1.8434283,
4.0219116,
-1.0825654,
5.961061,
-5.838909,
-2.6683056,
-1.9608945,
-7.612094,
4.54624,
12.01477,
-6.5574946,
5.990393,
-9.988611,
-14.277355,
2.9967263,
-1.1712778,
-3.7443178,
3.6448686,
9.226036,
-3.7033923,
-14.053265,
2.5498354,
-9.518535,
1.6401825,
-0.36512238,
-4.9813704,
-2.726482,
-10.685461,
-6.5958095,
10.8004055,
4.859266,
6.9649606,
7.024944,
-4.250888,
-6.3098636,
-11.0815115,
-14.593737,
11.150167,
-11.672057,
6.443364,
5.543199,
-3.852712,
-2.6978295,
-5.126513,
-13.7175045,
-2.0199032,
-5.6320567,
14.843209,
0.2881268,
5.7191358,
7.526985,
14.6844635,
-3.2138662,
6.6662474,
3.171249,
-13.094588,
-14.7442875,
0.5794834,
2.99146,
10.943796,
1.3510485,
2.100339,
3.2113767,
3.7474568,
5.7545915,
3.5693796,
-0.9383067,
4.0061,
3.5728343,
-8.674493,
-8.300964,
-2.2709742,
-0.603111,
6.185632,
-11.0190115,
1.3625672,
-4.850173,
2.9171705,
8.1604395,
-10.25015,
-3.9398847,
-0.23160458,
-5.392693,
15.28234,
1.2750401,
-1.3851596,
7.5546064,
-8.560972,
-1.8034146,
-12.882853,
4.640706,
6.449833,
-12.572372,
3.1180751,
-10.773977,
6.802127,
-9.868545,
9.253048,
1.3396845,
-0.74683595,
-7.180224,
4.771069,
9.654162,
3.1239467,
1.4051272,
8.177503,
-5.7268376,
-0.7003263,
2.7622976,
-3.1645548,
13.3046,
-2.2131858,
3.1262445,
12.838138,
-5.2419405,
-2.8829832,
-8.004557,
7.4833393,
-12.2402,
-4.5172586,
-9.0768795,
9.612813,
0.04776096,
4.9612007,
4.990355,
12.433644,
-2.141872,
-12.758332,
1.4486425,
-4.086392,
-4.481818,
-1.9323591,
14.265009,
-15.393123,
-0.31127125,
2.5777261,
6.3160987,
9.038766,
4.5779753,
10.014262,
-4.2199383,
14.254804,
-6.665484,
-5.69532,
-5.496155,
-0.40160426,
8.305916,
-8.923462,
4.5406356,
0.7675378,
5.6171103,
-4.578082,
9.9752655,
-10.363342,
3.227578,
-0.91156125,
0.1750337,
-10.112299,
0.7475936,
-14.1882,
9.756163,
-4.082387,
4.626093,
-5.5265136,
0.31286407,
0.15795733,
-7.157549,
13.754237,
-2.7781584,
11.642487,
14.187494,
11.508914,
-4.578478,
6.9590425,
8.829999,
6.39372,
-2.4645948,
1.3561549,
8.1304245
]
}
],
"layout": {
"height": 600,
"margin": {
"b": 10,
"l": 10,
"r": 20,
"t": 40
},
"scene": {
"xaxis": {
"title": {
"text": "x"
}
},
"yaxis": {
"title": {
"text": "y"
}
}
},
"template": {
"data": {
"bar": [
{
"error_x": {
"color": "#2a3f5f"
},
"error_y": {
"color": "#2a3f5f"
},
"marker": {
"line": {
"color": "#E5ECF6",
"width": 0.5
},
"pattern": {
"fillmode": "overlay",
"size": 10,
"solidity": 0.2
}
},
"type": "bar"
}
],
"barpolar": [
{
"marker": {
"line": {
"color": "#E5ECF6",
"width": 0.5
},
"pattern": {
"fillmode": "overlay",
"size": 10,
"solidity": 0.2
}
},
"type": "barpolar"
}
],
"carpet": [
{
"aaxis": {
"endlinecolor": "#2a3f5f",
"gridcolor": "white",
"linecolor": "white",
"minorgridcolor": "white",
"startlinecolor": "#2a3f5f"
},
"baxis": {
"endlinecolor": "#2a3f5f",
"gridcolor": "white",
"linecolor": "white",
"minorgridcolor": "white",
"startlinecolor": "#2a3f5f"
},
"type": "carpet"
}
],
"choropleth": [
{
"colorbar": {
"outlinewidth": 0,
"ticks": ""
},
"type": "choropleth"
}
],
"contour": [
{
"colorbar": {
"outlinewidth": 0,
"ticks": ""
},
"colorscale": [
[
0,
"#0d0887"
],
[
0.1111111111111111,
"#46039f"
],
[
0.2222222222222222,
"#7201a8"
],
[
0.3333333333333333,
"#9c179e"
],
[
0.4444444444444444,
"#bd3786"
],
[
0.5555555555555556,
"#d8576b"
],
[
0.6666666666666666,
"#ed7953"
],
[
0.7777777777777778,
"#fb9f3a"
],
[
0.8888888888888888,
"#fdca26"
],
[
1,
"#f0f921"
]
],
"type": "contour"
}
],
"contourcarpet": [
{
"colorbar": {
"outlinewidth": 0,
"ticks": ""
},
"type": "contourcarpet"
}
],
"heatmap": [
{
"colorbar": {
"outlinewidth": 0,
"ticks": ""
},
"colorscale": [
[
0,
"#0d0887"
],
[
0.1111111111111111,
"#46039f"
],
[
0.2222222222222222,
"#7201a8"
],
[
0.3333333333333333,
"#9c179e"
],
[
0.4444444444444444,
"#bd3786"
],
[
0.5555555555555556,
"#d8576b"
],
[
0.6666666666666666,
"#ed7953"
],
[
0.7777777777777778,
"#fb9f3a"
],
[
0.8888888888888888,
"#fdca26"
],
[
1,
"#f0f921"
]
],
"type": "heatmap"
}
],
"heatmapgl": [
{
"colorbar": {
"outlinewidth": 0,
"ticks": ""
},
"colorscale": [
[
0,
"#0d0887"
],
[
0.1111111111111111,
"#46039f"
],
[
0.2222222222222222,
"#7201a8"
],
[
0.3333333333333333,
"#9c179e"
],
[
0.4444444444444444,
"#bd3786"
],
[
0.5555555555555556,
"#d8576b"
],
[
0.6666666666666666,
"#ed7953"
],
[
0.7777777777777778,
"#fb9f3a"
],
[
0.8888888888888888,
"#fdca26"
],
[
1,
"#f0f921"
]
],
"type": "heatmapgl"
}
],
"histogram": [
{
"marker": {
"pattern": {
"fillmode": "overlay",
"size": 10,
"solidity": 0.2
}
},
"type": "histogram"
}
],
"histogram2d": [
{
"colorbar": {
"outlinewidth": 0,
"ticks": ""
},
"colorscale": [
[
0,
"#0d0887"
],
[
0.1111111111111111,
"#46039f"
],
[
0.2222222222222222,
"#7201a8"
],
[
0.3333333333333333,
"#9c179e"
],
[
0.4444444444444444,
"#bd3786"
],
[
0.5555555555555556,
"#d8576b"
],
[
0.6666666666666666,
"#ed7953"
],
[
0.7777777777777778,
"#fb9f3a"
],
[
0.8888888888888888,
"#fdca26"
],
[
1,
"#f0f921"
]
],
"type": "histogram2d"
}
],
"histogram2dcontour": [
{
"colorbar": {
"outlinewidth": 0,
"ticks": ""
},
"colorscale": [
[
0,
"#0d0887"
],
[
0.1111111111111111,
"#46039f"
],
[
0.2222222222222222,
"#7201a8"
],
[
0.3333333333333333,
"#9c179e"
],
[
0.4444444444444444,
"#bd3786"
],
[
0.5555555555555556,
"#d8576b"
],
[
0.6666666666666666,
"#ed7953"
],
[
0.7777777777777778,
"#fb9f3a"
],
[
0.8888888888888888,
"#fdca26"
],
[
1,
"#f0f921"
]
],
"type": "histogram2dcontour"
}
],
"mesh3d": [
{
"colorbar": {
"outlinewidth": 0,
"ticks": ""
},
"type": "mesh3d"
}
],
"parcoords": [
{
"line": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"type": "parcoords"
}
],
"pie": [
{
"automargin": true,
"type": "pie"
}
],
"scatter": [
{
"fillpattern": {
"fillmode": "overlay",
"size": 10,
"solidity": 0.2
},
"type": "scatter"
}
],
"scatter3d": [
{
"line": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"marker": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"type": "scatter3d"
}
],
"scattercarpet": [
{
"marker": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"type": "scattercarpet"
}
],
"scattergeo": [
{
"marker": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"type": "scattergeo"
}
],
"scattergl": [
{
"marker": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"type": "scattergl"
}
],
"scattermapbox": [
{
"marker": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"type": "scattermapbox"
}
],
"scatterpolar": [
{
"marker": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"type": "scatterpolar"
}
],
"scatterpolargl": [
{
"marker": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"type": "scatterpolargl"
}
],
"scatterternary": [
{
"marker": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"type": "scatterternary"
}
],
"surface": [
{
"colorbar": {
"outlinewidth": 0,
"ticks": ""
},
"colorscale": [
[
0,
"#0d0887"
],
[
0.1111111111111111,
"#46039f"
],
[
0.2222222222222222,
"#7201a8"
],
[
0.3333333333333333,
"#9c179e"
],
[
0.4444444444444444,
"#bd3786"
],
[
0.5555555555555556,
"#d8576b"
],
[
0.6666666666666666,
"#ed7953"
],
[
0.7777777777777778,
"#fb9f3a"
],
[
0.8888888888888888,
"#fdca26"
],
[
1,
"#f0f921"
]
],
"type": "surface"
}
],
"table": [
{
"cells": {
"fill": {
"color": "#EBF0F8"
},
"line": {
"color": "white"
}
},
"header": {
"fill": {
"color": "#C8D4E3"
},
"line": {
"color": "white"
}
},
"type": "table"
}
]
},
"layout": {
"annotationdefaults": {
"arrowcolor": "#2a3f5f",
"arrowhead": 0,
"arrowwidth": 1
},
"autotypenumbers": "strict",
"coloraxis": {
"colorbar": {
"outlinewidth": 0,
"ticks": ""
}
},
"colorscale": {
"diverging": [
[
0,
"#8e0152"
],
[
0.1,
"#c51b7d"
],
[
0.2,
"#de77ae"
],
[
0.3,
"#f1b6da"
],
[
0.4,
"#fde0ef"
],
[
0.5,
"#f7f7f7"
],
[
0.6,
"#e6f5d0"
],
[
0.7,
"#b8e186"
],
[
0.8,
"#7fbc41"
],
[
0.9,
"#4d9221"
],
[
1,
"#276419"
]
],
"sequential": [
[
0,
"#0d0887"
],
[
0.1111111111111111,
"#46039f"
],
[
0.2222222222222222,
"#7201a8"
],
[
0.3333333333333333,
"#9c179e"
],
[
0.4444444444444444,
"#bd3786"
],
[
0.5555555555555556,
"#d8576b"
],
[
0.6666666666666666,
"#ed7953"
],
[
0.7777777777777778,
"#fb9f3a"
],
[
0.8888888888888888,
"#fdca26"
],
[
1,
"#f0f921"
]
],
"sequentialminus": [
[
0,
"#0d0887"
],
[
0.1111111111111111,
"#46039f"
],
[
0.2222222222222222,
"#7201a8"
],
[
0.3333333333333333,
"#9c179e"
],
[
0.4444444444444444,
"#bd3786"
],
[
0.5555555555555556,
"#d8576b"
],
[
0.6666666666666666,
"#ed7953"
],
[
0.7777777777777778,
"#fb9f3a"
],
[
0.8888888888888888,
"#fdca26"
],
[
1,
"#f0f921"
]
]
},
"colorway": [
"#636efa",
"#EF553B",
"#00cc96",
"#ab63fa",
"#FFA15A",
"#19d3f3",
"#FF6692",
"#B6E880",
"#FF97FF",
"#FECB52"
],
"font": {
"color": "#2a3f5f"
},
"geo": {
"bgcolor": "white",
"lakecolor": "white",
"landcolor": "#E5ECF6",
"showlakes": true,
"showland": true,
"subunitcolor": "white"
},
"hoverlabel": {
"align": "left"
},
"hovermode": "closest",
"mapbox": {
"style": "light"
},
"paper_bgcolor": "white",
"plot_bgcolor": "#E5ECF6",
"polar": {
"angularaxis": {
"gridcolor": "white",
"linecolor": "white",
"ticks": ""
},
"bgcolor": "#E5ECF6",
"radialaxis": {
"gridcolor": "white",
"linecolor": "white",
"ticks": ""
}
},
"scene": {
"xaxis": {
"backgroundcolor": "#E5ECF6",
"gridcolor": "white",
"gridwidth": 2,
"linecolor": "white",
"showbackground": true,
"ticks": "",
"zerolinecolor": "white"
},
"yaxis": {
"backgroundcolor": "#E5ECF6",
"gridcolor": "white",
"gridwidth": 2,
"linecolor": "white",
"showbackground": true,
"ticks": "",
"zerolinecolor": "white"
},
"zaxis": {
"backgroundcolor": "#E5ECF6",
"gridcolor": "white",
"gridwidth": 2,
"linecolor": "white",
"showbackground": true,
"ticks": "",
"zerolinecolor": "white"
}
},
"shapedefaults": {
"line": {
"color": "#2a3f5f"
}
},
"ternary": {
"aaxis": {
"gridcolor": "white",
"linecolor": "white",
"ticks": ""
},
"baxis": {
"gridcolor": "white",
"linecolor": "white",
"ticks": ""
},
"bgcolor": "#E5ECF6",
"caxis": {
"gridcolor": "white",
"linecolor": "white",
"ticks": ""
}
},
"title": {
"x": 0.05
},
"xaxis": {
"automargin": true,
"gridcolor": "white",
"linecolor": "white",
"ticks": "",
"title": {
"standoff": 15
},
"zerolinecolor": "white",
"zerolinewidth": 2
},
"yaxis": {
"automargin": true,
"gridcolor": "white",
"linecolor": "white",
"ticks": "",
"title": {
"standoff": 15
},
"zerolinecolor": "white",
"zerolinewidth": 2
}
}
},
"title": {
"text": "2D Chroma Vector Store Visualization"
},
"width": 800
}
},
"image/png": "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",
"text/html": [
"