{
"cells": [
{
"cell_type": "markdown",
"id": "dfe37963-1af6-44fc-a841-8e462443f5e6",
"metadata": {},
"source": [
"## Expert Knowledge Worker\n",
"\n",
"### A question answering agent that is an expert knowledge worker\n",
"### To be used by employees of Insurellm, an Insurance Tech company\n",
"### The agent needs to be accurate and the solution should be low cost.\n",
"\n",
"This project will use RAG (Retrieval Augmented Generation) to ensure our question/answering assistant has high accuracy."
]
},
{
"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"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "802137aa-8a74-45e0-a487-d1974927d7ca",
"metadata": {},
"outputs": [],
"source": [
"# imports for langchain and Chroma and plotly\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"
]
},
{
"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(\"knowledge-base/*\")\n",
"\n",
"documents = []\n",
"for folder in folders:\n",
" doc_type = os.path.basename(folder)\n",
" loader = DirectoryLoader(folder, glob=\"**/*.md\", loader_cls=TextLoader)\n",
" folder_docs = loader.load()\n",
" for doc in folder_docs:\n",
" doc.metadata[\"doc_type\"] = doc_type\n",
" documents.append(doc)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7310c9c8-03c1-4efc-a104-5e89aec6db1a",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Created a chunk of size 1088, which is longer than the specified 1000\n"
]
}
],
"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": [
"123"
]
},
"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": [
"Document types found: contracts, products, employees, company\n"
]
}
],
"source": [
"doc_types = set(chunk.metadata['doc_type'] for chunk in chunks)\n",
"print(f\"Document types found: {', '.join(doc_types)}\")"
]
},
{
"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."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "78998399-ac17-4e28-b15f-0b5f51e6ee23",
"metadata": {},
"outputs": [],
"source": [
"# Put the chunks of data into a Vector Store that associates a Vector Embedding with each chunk\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "763e51ff-5787-4a56-8176-36b7c5796fe3",
"metadata": {},
"outputs": [],
"source": [
"# Check if a Chroma Datastore already exists - if so, delete the collection to start from scratch\n",
"\n",
"if os.path.exists(db_name):\n",
" Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "99fe3a37-480f-4d55-be48-120588d5846b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Vectorstore created with 123 documents\n"
]
}
],
"source": [
"# Create our Chroma 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": 12,
"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": "code",
"execution_count": null,
"id": "61e393a0-dd4c-419f-842f-60c1cb3b716b",
"metadata": {},
"outputs": [],
"source": []
},
{
"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": 14,
"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",
"doc_types = [metadata['doc_type'] for metadata in result['metadatas']]\n",
"colors = [['blue', 'green', 'red', 'orange'][['products', 'employees', 'contracts', 'company'].index(t)] for t in doc_types]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"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": [
"red",
"red",
"red",
"red",
"red",
"green",
"red",
"orange",
"green",
"red",
"red",
"red",
"red",
"blue",
"green",
"blue",
"red",
"red",
"green",
"green",
"blue",
"red",
"red",
"green",
"red",
"green",
"green",
"blue",
"red",
"red",
"green",
"red",
"blue",
"red",
"blue",
"green",
"red",
"red",
"red",
"orange",
"blue",
"red",
"green",
"green",
"red",
"green",
"red",
"red",
"green",
"blue",
"green",
"green",
"red",
"red",
"green",
"red",
"green",
"red",
"green",
"green",
"red",
"red",
"red",
"red",
"blue",
"green",
"green",
"green",
"red",
"blue",
"red",
"blue",
"green",
"red",
"green",
"red",
"orange",
"green",
"red",
"green",
"green",
"green",
"green",
"red",
"green",
"green",
"green",
"green",
"green",
"red",
"blue",
"green",
"red",
"green",
"green",
"green",
"blue",
"green",
"red",
"blue",
"red",
"red",
"green",
"red",
"blue",
"blue",
"blue",
"red",
"green",
"blue",
"red",
"green",
"red",
"green",
"red",
"blue",
"green",
"red",
"green",
"blue",
"green",
"red",
"blue"
],
"opacity": 0.8,
"size": 5
},
"mode": "markers",
"text": [
"Type: contracts
Text: ## Support\n\n1. **Customer Support**: Insurellm will provide 24/7 customer support to TechDrive Insur...",
"Type: contracts
Text: 1. **Core Functionality**: Rellm provides EverGuard Insurance with advanced AI-driven analytics, sea...",
"Type: contracts
Text: ## Features\n1. **AI-Powered Matching**: Belvedere Insurance will benefit from Markellm's AI-powered ...",
"Type: contracts
Text: 1. **Technical Support**: Provider shall offer dedicated technical support to the Client via phone, ...",
"Type: contracts
Text: 1. **AI-Powered Risk Assessment:** Access to advanced AI algorithms for real-time risk evaluations.\n...",
"Type: employees
Text: - **2017-2019:** Marketing Intern \n - Assisted with market research and campaign development for s...",
"Type: contracts
Text: ## Renewal\n1. **Renewal Terms**: This Agreement may be renewed for additional one-year terms upon mu...",
"Type: company
Text: # Overview of Insurellm\n\nInsurellm is an innovative insurance tech firm with 200 employees across th...",
"Type: employees
Text: - **January 2017 - May 2018**: Marketing Intern \n - Supported the Marketing team by collaborating ...",
"Type: contracts
Text: # Contract with Greenstone Insurance for Homellm\n\n---\n\n## Terms\n\n1. **Parties**: This Contract (\"Agr...",
"Type: contracts
Text: ## Features\nStellar Insurance Co. will receive access to the following features of the Rellm product...",
"Type: contracts
Text: 1. **Customer Support**: Insurellm will provide EverGuard Insurance with 24/7 customer support, incl...",
"Type: contracts
Text: ---\n\n## Features\n\n1. **Access to Core Features**: Roadway Insurance Inc. will have access to all Pro...",
"Type: products
Text: ### 5. Multi-Channel Integration\nHomellm seamlessly integrates into existing insurance platforms, pr...",
"Type: employees
Text: - **2021**: *Exceeds Expectations* \n Maxine spearheaded the transition to a new data warehousing s...",
"Type: products
Text: # Product Summary\n\n# Markellm\n\n## Summary\n\nMarkellm is an innovative two-sided marketplace designed ...",
"Type: contracts
Text: ## Renewal\n\n1. **Automatic Renewal**: This Agreement will automatically renew for successive one-yea...",
"Type: contracts
Text: ## Support\n1. **Technical Support**: Insurellm shall provide 24/7 technical support via an email and...",
"Type: employees
Text: ## Compensation History\n- **2020:** Base Salary: $80,000 \n- **2021:** Base Salary Increase to $90,0...",
"Type: employees
Text: # Avery Lancaster\n\n## Summary\n- **Date of Birth**: March 15, 1985 \n- **Job Title**: Co-Founder & Ch...",
"Type: products
Text: Join the growing number of organizations leveraging Rellm to enhance their reinsurance processes whi...",
"Type: contracts
Text: # Contract with Apex Reinsurance for Rellm: AI-Powered Enterprise Reinsurance Solution\n\n## Terms\n\n1....",
"Type: contracts
Text: ## Renewal\n\n1. **Automatic Renewal**: This contract shall automatically renew for additional one-yea...",
"Type: employees
Text: ## Compensation History\n| Year | Base Salary | Bonus | Total Compensation |\n|------|--------...",
"Type: contracts
Text: # Contract with TechDrive Insurance for Carllm\n\n**Contract Date:** October 1, 2024 \n**Contract Dura...",
"Type: employees
Text: Emily Carter exemplifies the kind of talent that drives Insurellm's success and is an invaluable ass...",
"Type: employees
Text: - **2018**: **Exceeds Expectations** \n Under Avery’s pivoted vision, Insurellm launched two new su...",
"Type: products
Text: # Product Summary\n\n# Carllm\n\n## Summary\n\nCarllm is an innovative auto insurance product developed by...",
"Type: contracts
Text: ### Termination\nEither party may terminate this agreement with a **30-day written notice**. In the e...",
"Type: contracts
Text: **Signatures:** \n_________________________ _________________________ \n**...",
"Type: employees
Text: ## Compensation History\n- **2020:** Base Salary - $55,000 \n The entry-level salary matched industr...",
"Type: contracts
Text: # Contract with GreenValley Insurance for Homellm\n\n**Contract Date:** October 6, 2023 \n**Contract N...",
"Type: products
Text: ### For Insurance Companies:\n- **Basic Listing Fee**: $199/month for a featured listing on the platf...",
"Type: contracts
Text: ## Support\nInsurellm provides Stellar Insurance Co. with the following support services:\n\n- **24/7 T...",
"Type: products
Text: Experience the future of reinsurance with Rellm, where innovation meets reliability. Let Insurellm h...",
"Type: employees
Text: ## Compensation History\n- **2015**: $150,000 base salary + Significant equity stake \n- **2016**: $1...",
"Type: contracts
Text: **TechDrive Insurance Representative:** \nName: Sarah Johnson \nTitle: Operations Director \nDate: _...",
"Type: contracts
Text: 3. **Training and Onboarding:** \n Insurellm agrees to provide one free training session on how to...",
"Type: contracts
Text: ## Support\n1. **Customer Support Access**: The Client will have access to dedicated support through ...",
"Type: company
Text: # Careers at Insurellm\n\nInsurellm is hiring! We are looking for talented software engineers, data sc...",
"Type: products
Text: # Product Summary\n\n# Rellm: AI-Powered Enterprise Reinsurance Solution\n\n## Summary\n\nRellm is an inno...",
"Type: contracts
Text: 4. **Payment Terms**: \n - The Customer shall pay an amount of $10,000 per month for the Standard T...",
"Type: employees
Text: # HR Record\n\n# Samuel Trenton\n\n## Summary\n- **Date of Birth:** April 12, 1989 \n- **Job Title:** Sen...",
"Type: employees
Text: ## Annual Performance History\n- **2018**: **3/5** - Adaptable team player but still learning to take...",
"Type: contracts
Text: # Contract with Pinnacle Insurance Co. for Homellm\n\n## Terms\nThis contract (\"Contract\") is entered i...",
"Type: employees
Text: ## Annual Performance History\n- **2023:** Rating: 4.5/5 \n *Samuel exceeded expectations, successfu...",
"Type: contracts
Text: **Insurellm, Inc.** \n_____________________________ \nAuthorized Signature \nDate: ________________...",
"Type: contracts
Text: ---\n\n## Features\n\n- **AI-Powered Risk Assessment**: Customer will have access to enhanced risk evalu...",
"Type: employees
Text: - **2022**: **Satisfactory** \n Avery focused on rebuilding team dynamics and addressing employee c...",
"Type: products
Text: ### Q3 2025\n- Initiate a comprehensive marketing campaign targeting both consumers and insurers to i...",
"Type: employees
Text: # HR Record\n\n# Oliver Spencer\n\n## Summary\n- **Date of Birth**: May 14, 1990 \n- **Job Title**: Backe...",
"Type: employees
Text: # HR Record\n\n# Jordan K. Bishop\n\n## Summary\n- **Date of Birth:** March 15, 1990\n- **Job Title:** Fro...",
"Type: contracts
Text: ## Features\n1. **AI-Powered Risk Assessment**: Utilized for tailored underwriting decisions specific...",
"Type: contracts
Text: # Contract with Belvedere Insurance for Markellm\n\n## Terms\nThis Contract (\"Agreement\") is made and e...",
"Type: employees
Text: ## Annual Performance History\n- **2019:** Exceeds Expectations - Continuously delivered high-quality...",
"Type: contracts
Text: ## Support\n1. **Technical Support**: Technical support will be available from 9 AM to 7 PM EST, Mond...",
"Type: employees
Text: ## Other HR Notes\n- Jordan K. Bishop has been an integral part of club initiatives, including the In...",
"Type: contracts
Text: 4. **Usage Rights**: EverGuard Insurance is granted a non-exclusive, non-transferable license to acc...",
"Type: employees
Text: ## Compensation History\n- **March 2018**: Initial salary of $80,000.\n- **July 2019**: Salary increas...",
"Type: employees
Text: ## Compensation History\n- **2023:** Base Salary: $115,000 + Bonus: $15,000 \n *Annual bonus based o...",
"Type: contracts
Text: ---\n\n**Signatures** \n**For Insurellm**: __________________________ \n**Name**: John Smith \n**Title...",
"Type: contracts
Text: # Contract with Velocity Auto Solutions for Carllm\n\n**Contract Date:** October 1, 2023 \n**Contract ...",
"Type: contracts
Text: 4. **Confidentiality:** Both parties agree to maintain the confidentiality of proprietary informatio...",
"Type: contracts
Text: ---\n\n## Support\n\n1. **Technical Support**: Roadway Insurance Inc. will receive priority technical su...",
"Type: products
Text: - **Professional Tier**: $2,500/month\n - For medium-sized companies.\n - All Basic Tier features pl...",
"Type: employees
Text: # HR Record\n\n# Alex Harper\n\n## Summary\n- **Date of Birth**: March 15, 1993 \n- **Job Title**: Sales ...",
"Type: employees
Text: - **Engagement in Company Culture:** Regularly participates in team-building events and contributes ...",
"Type: employees
Text: ## Other HR Notes\n- Jordan has shown an interest in continuing education, actively participating in ...",
"Type: contracts
Text: # Contract with EverGuard Insurance for Rellm: AI-Powered Enterprise Reinsurance Solution\n\n**Contrac...",
"Type: products
Text: All tiers include a comprehensive training program and ongoing updates to ensure optimal performance...",
"Type: contracts
Text: ## Support\n\n1. **Customer Support**: Velocity Auto Solutions will have access to Insurellm’s custome...",
"Type: products
Text: # Product Summary\n\n# Homellm\n\n## Summary\nHomellm is an innovative home insurance product developed b...",
"Type: employees
Text: - **2021**: \n - Performance Rating: Meets Expectations \n - Key Achievements: Contributed to the ...",
"Type: contracts
Text: # Contract with Roadway Insurance Inc. for Carllm\n\n---\n\n## Terms\n\n1. **Agreement Effective Date**: T...",
"Type: employees
Text: - **2023:** Base Salary - $70,000 \n Recognized for substantial improvement in employee relations m...",
"Type: contracts
Text: # Contract with Stellar Insurance Co. for Rellm\n\n## Terms\nThis contract is made between **Insurellm*...",
"Type: company
Text: # About Insurellm\n\nInsurellm was founded by Avery Lancaster in 2015 as an insurance tech startup des...",
"Type: employees
Text: # Samantha Greene\n\n## Summary\n- **Date of Birth:** October 14, 1990\n- **Job Title:** HR Generalist\n-...",
"Type: contracts
Text: # Contract with GreenField Holdings for Markellm\n\n**Effective Date:** November 15, 2023 \n**Contract...",
"Type: employees
Text: ## Annual Performance History\n- **2017**: *Meets Expectations* \n Maxine showed potential in her ro...",
"Type: employees
Text: ## Insurellm Career Progression\n- **January 2017 - October 2018**: **Junior Data Engineer** \n * Ma...",
"Type: employees
Text: Alex Chen continues to be a vital asset at Insurellm, contributing significantly to innovative backe...",
"Type: employees
Text: - **2010 - 2013**: Business Analyst at Edge Analytics \n Prior to joining Innovate, Avery worked as...",
"Type: contracts
Text: ## Renewal\n1. **Automatic Renewal**: This contract will automatically renew for sequential one-year ...",
"Type: employees
Text: ## Annual Performance History\n- **2020:** \n - Completed onboarding successfully. \n - Met expecta...",
"Type: employees
Text: ## Compensation History\n- **June 2018:** Starting Salary - $85,000\n- **June 2019:** Salary Increase ...",
"Type: employees
Text: ## Annual Performance History \n- **2022** - Rated as \"Exceeds Expectations.\" Alex Thomson achieved ...",
"Type: employees
Text: ## Annual Performance History \n- **2021**: \n - **Performance Rating**: 4.5/5 \n - **Key Achievem...",
"Type: employees
Text: # HR Record\n\n# Maxine Thompson\n\n## Summary\n- **Date of Birth:** January 15, 1991 \n- **Job Title:** ...",
"Type: contracts
Text: 2. **Seamless Integrations**: The architecture of Rellm allows for easy integration with existing sy...",
"Type: products
Text: - **Basic Tier:** Starting at $5,000/month for small insurers with basic integration features.\n- **S...",
"Type: employees
Text: ## Annual Performance History\n- **2020:** Exceeds Expectations \n Samantha Greene demonstrated exce...",
"Type: contracts
Text: 3. **Service Level Agreement (SLA):** \n Insurellm commits to a 99.9% uptime for the platform with...",
"Type: employees
Text: # HR Record\n\n# Jordan Blake\n\n## Summary\n- **Date of Birth:** March 15, 1993 \n- **Job Title:** Sales...",
"Type: employees
Text: # HR Record\n\n# Alex Chen\n\n## Summary\n- **Date of Birth:** March 15, 1990 \n- **Job Title:** Backend ...",
"Type: employees
Text: ## Other HR Notes\n- Alex Thomson is an active member of the Diversity and Inclusion committee at Ins...",
"Type: products
Text: - **Mobile Integration**: Carllm is designed to work seamlessly with mobile applications, providing ...",
"Type: employees
Text: ## Other HR Notes\n- **Professional Development**: Avery has actively participated in leadership trai...",
"Type: contracts
Text: ## Features\n1. **AI-Powered Matching**: Access to advanced algorithms that connect GreenField Holdin...",
"Type: products
Text: ### Regulatory Compliance Tools\nRellm includes built-in compliance tracking features to help organiz...",
"Type: contracts
Text: ## Renewal\n\n1. **Automatic Renewal**: This contract will automatically renew for successive 12-month...",
"Type: contracts
Text: 3. **Regular Updates:** Insurellm will offer ongoing updates and enhancements to the Homellm platfor...",
"Type: employees
Text: ## Annual Performance History\n- **2021:** First year at Insurellm; achieved 90% of monthly targets. ...",
"Type: contracts
Text: ______________________________ \n[Name], [Title] \nDate: ______________________\n\n**For Greenstone In...",
"Type: products
Text: With Homellm, Insurellm is committed to transforming the landscape of home insurance, ensuring both ...",
"Type: products
Text: - **Customer Support**: Our dedicated support team is always available to assist both consumers and ...",
"Type: products
Text: ### Q2 2025: Customer Experience Improvements\n- Launch of a new **mobile app** for end-users.\n- Intr...",
"Type: contracts
Text: ---\n\n## Renewal\n\n1. **Automatic Renewal**: This agreement will automatically renew for an additional...",
"Type: employees
Text: - **Professional Development Goals**: \n - Emily Tran aims to become a Marketing Manager within the...",
"Type: products
Text: - **Instant Quoting**: With Carllm, insurance companies can offer near-instant quotes to customers, ...",
"Type: contracts
Text: - **Customer Portal**: A dedicated portal will be provided, allowing the Customer's clients to manag...",
"Type: employees
Text: # HR Record\n\n# Emily Tran\n\n## Summary\n- **Date of Birth:** March 18, 1991 \n- **Job Title:** Digital...",
"Type: contracts
Text: ## Renewal\n1. **Renewal Terms**: At the end of the initial term, this Contract shall automatically r...",
"Type: employees
Text: - **2022**: \n - **Base Salary**: $65,000 (Promotion to Senior SDR) \n - **Bonus**: $13,000 (20% o...",
"Type: contracts
Text: 2. **Real-Time Quote Availability:** \n Consumers sourced via BrightWay Solutions will receive rea...",
"Type: products
Text: - **User-Friendly Interface**: Designed with user experience in mind, Markellm features an intuitive...",
"Type: employees
Text: # HR Record\n\n# Emily Carter\n\n## Summary\n- **Date of Birth:** August 12, 1990 \n- **Job Title:** Acco...",
"Type: contracts
Text: # Contract with BrightWay Solutions for Markellm\n\n**Contract Date:** October 5, 2023 \n**Contract ID...",
"Type: employees
Text: # HR Record\n\n# Alex Thomson\n\n## Summary\n- **Date of Birth:** March 15, 1995 \n- **Job Title:** Sales...",
"Type: products
Text: ### Seamless Integrations\nRellm's architecture is designed for effortless integration with existing ...",
"Type: employees
Text: ## Compensation History\n- **2017**: $70,000 (Junior Data Engineer) \n- **2018**: $75,000 (Junior Dat...",
"Type: contracts
Text: **Belvedere Insurance** \nSignature: ______________________ \nName: [Authorized Signatory] \nTitle: ...",
"Type: products
Text: ### 2. Dynamic Pricing Model\nWith Homellm's innovative dynamic pricing model, insurance providers ca..."
],
"type": "scatter",
"x": [
-8.071104,
-6.2519703,
-1.8580668,
-6.436127,
-0.6904994,
10.130567,
-12.429563,
0.08344886,
9.76927,
-5.9893513,
-5.7498426,
-6.885394,
-5.8710027,
-1.6460683,
8.309161,
-0.6193017,
-7.80085,
-6.847732,
13.126606,
5.324947,
-4.0730667,
-8.945796,
-8.128535,
12.312359,
-9.230899,
4.4518313,
6.9866157,
-3.3632085,
-9.421097,
-10.381586,
13.040782,
-6.9263716,
-1.5311053,
-6.9470024,
-2.942015,
14.603296,
-8.931177,
-4.720853,
-1.7678646,
1.353522,
-4.276341,
-5.905624,
9.807923,
10.614696,
-5.8416805,
12.296406,
-10.367664,
-1.4945257,
6.8976645,
0.342791,
9.335933,
8.303513,
-1.4391268,
-3.58222,
10.020635,
-6.911788,
7.0954995,
-7.301257,
13.4010515,
13.705383,
-10.170157,
-9.219992,
-7.2120805,
-6.8258886,
-4.641127,
8.424806,
7.9604635,
6.829996,
-8.214355,
-2.8727412,
-7.5102572,
-1.3124497,
11.636429,
-10.183806,
12.341001,
-8.668994,
0.4821271,
11.663062,
-4.102811,
9.26108,
8.463315,
4.211969,
6.785783,
-11.887801,
10.624305,
14.721668,
12.691266,
12.924206,
10.893478,
-6.0467463,
-3.0542178,
10.258011,
-4.1896935,
8.572656,
9.204262,
7.152999,
-4.3750257,
5.5449634,
-0.12708236,
-5.304075,
-7.869064,
-7.5764885,
12.494096,
-10.284406,
-1.310298,
-1.452017,
-4.2100368,
-10.763239,
9.471508,
-3.4186995,
-6.4836793,
9.771511,
-12.165046,
13.8430805,
-3.105149,
-0.94607294,
9.828463,
-4.0742583,
7.9726176,
-5.4842634,
14.348989,
-9.427354,
-1.1870847
],
"y": [
1.5902514,
-3.5992181,
1.8065181,
2.222174,
-0.8966787,
-1.4253742,
-1.221891,
-4.0924973,
-2.557773,
5.598769,
-2.7837224,
-2.3674812,
-0.27511686,
-2.4927423,
0.25777915,
1.767931,
-4.053594,
3.416252,
-2.3764908,
-1.5142679,
-3.1539073,
-3.7365606,
0.0063864263,
-2.8577769,
1.0260776,
-4.2089653,
0.97690046,
-0.15132362,
-2.035713,
5.513457,
-4.1340413,
5.7823067,
3.6807516,
-1.7526506,
-4.9345284,
-1.5680406,
2.1363566,
3.4425445,
4.575071,
-4.3501062,
-4.5625734,
6.9895754,
-5.565334,
1.0561501,
5.15573,
-0.5245365,
4.905023,
-1.2498422,
1.1531521,
1.9650984,
-6.708022,
-6.7171946,
-0.40709332,
4.6162,
1.5808111,
2.8648286,
-6.5857615,
-3.428619,
-2.7383366,
-1.5134356,
3.429126,
0.46467334,
5.3535476,
0.5220494,
-0.55356896,
-4.8343368,
-2.3620856,
-5.916163,
-3.1133218,
-2.527424,
1.3960353,
-2.8949306,
-2.216425,
0.37436485,
-4.269915,
-1.8885767,
-4.070706,
-4.9224176,
5.2717934,
0.7036075,
-0.74303395,
-3.657771,
0.21052341,
-1.5309354,
1.3039184,
-2.3333063,
0.33577925,
-0.81413126,
-6.8172393,
-4.9814715,
-1.7771184,
0.02913107,
2.2616448,
-5.4093633,
-6.320122,
-4.430528,
-0.18062231,
-1.3993918,
0.036958076,
-3.925734,
-0.23834208,
4.7376623,
-1.7152996,
5.924522,
-3.9765553,
2.7250137,
-1.4355923,
-0.86104953,
-2.894225,
0.08414796,
4.1407557,
-3.584049,
-1.2970203,
-0.34048915,
2.545294,
2.056669,
-4.4441853,
3.6039774,
-4.7505445,
-4.868258,
-3.066253,
5.036427,
-1.8640015
]
}
],
"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,
"xaxis": {
"autorange": true,
"range": [
-14.078558425359779,
16.37066342535978
],
"type": "linear"
},
"yaxis": {
"autorange": true,
"range": [
-7.685158477617043,
7.857494577617043
],
"type": "linear"
}
}
},
"image/png": "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",
"text/html": [
"