{ "cells": [ { "cell_type": "markdown", "id": "dfe37963-1af6-44fc-a841-8e462443f5e6", "metadata": {}, "source": [ "## Expert Knowledge Worker\n", "\n", "## Extra Jupyter Notebook - Day 4.5 - switch out Chroma for FAISS!\n", "\n", "FAISS is Facebook AI Similarity Search" ] }, { "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\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", "from langchain.vectorstores import FAISS\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(\"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: employees, products, company, contracts\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.\n", "\n", "More details in the resources." ] }, { "cell_type": "code", "execution_count": 9, "id": "78998399-ac17-4e28-b15f-0b5f51e6ee23", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "There are 123 vectors with 1,536 dimensions in the vector store\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", "# Create vectorstore\n", "\n", "# BEFORE\n", "# vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)\n", "\n", "# AFTER\n", "vectorstore = FAISS.from_documents(chunks, embedding=embeddings)\n", "\n", "total_vectors = vectorstore.index.ntotal\n", "dimensions = vectorstore.index.d\n", "\n", "print(f\"There are {total_vectors} vectors with {dimensions:,} dimensions in the vector store\")" ] }, { "cell_type": "code", "execution_count": 10, "id": "057868f6-51a6-4087-94d1-380145821550", "metadata": {}, "outputs": [], "source": [ "# Prework\n", "vectors = []\n", "documents = []\n", "doc_types = []\n", "colors = []\n", "color_map = {'products':'blue', 'employees':'green', 'contracts':'red', 'company':'orange'}\n", "\n", "for i in range(total_vectors):\n", " vectors.append(vectorstore.index.reconstruct(i))\n", " doc_id = vectorstore.index_to_docstore_id[i]\n", " document = vectorstore.docstore.search(doc_id)\n", " documents.append(document.page_content)\n", " doc_type = document.metadata['doc_type']\n", " doc_types.append(doc_type)\n", " colors.append(color_map[doc_type])\n", " \n", "vectors = np.array(vectors)" ] }, { "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": "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": [ "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "orange", "orange", "orange", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green" ], "opacity": 0.8, "size": 5 }, "mode": "markers", "text": [ "Type: products
Text: # Product Summary\n\n# Rellm: AI-Powered Enterprise Reinsurance Solution\n\n## Summary\n\nRellm is an inno...", "Type: products
Text: ### Seamless Integrations\nRellm's architecture is designed for effortless integration with existing ...", "Type: products
Text: ### Regulatory Compliance Tools\nRellm includes built-in compliance tracking features to help organiz...", "Type: products
Text: Join the growing number of organizations leveraging Rellm to enhance their reinsurance processes whi...", "Type: products
Text: Experience the future of reinsurance with Rellm, where innovation meets reliability. Let Insurellm h...", "Type: products
Text: # Product Summary\n\n# Markellm\n\n## Summary\n\nMarkellm is an innovative two-sided marketplace designed ...", "Type: products
Text: - **User-Friendly Interface**: Designed with user experience in mind, Markellm features an intuitive...", "Type: products
Text: - **Customer Support**: Our dedicated support team is always available to assist both consumers and ...", "Type: products
Text: ### For Insurance Companies:\n- **Basic Listing Fee**: $199/month for a featured listing on the platf...", "Type: products
Text: ### Q3 2025\n- Initiate a comprehensive marketing campaign targeting both consumers and insurers to i...", "Type: products
Text: # Product Summary\n\n# Homellm\n\n## Summary\nHomellm is an innovative home insurance product developed b...", "Type: products
Text: ### 2. Dynamic Pricing Model\nWith Homellm's innovative dynamic pricing model, insurance providers ca...", "Type: products
Text: ### 5. Multi-Channel Integration\nHomellm seamlessly integrates into existing insurance platforms, pr...", "Type: products
Text: - **Basic Tier:** Starting at $5,000/month for small insurers with basic integration features.\n- **S...", "Type: products
Text: All tiers include a comprehensive training program and ongoing updates to ensure optimal performance...", "Type: products
Text: With Homellm, Insurellm is committed to transforming the landscape of home insurance, ensuring both ...", "Type: products
Text: # Product Summary\n\n# Carllm\n\n## Summary\n\nCarllm is an innovative auto insurance product developed by...", "Type: products
Text: - **Instant Quoting**: With Carllm, insurance companies can offer near-instant quotes to customers, ...", "Type: products
Text: - **Mobile Integration**: Carllm is designed to work seamlessly with mobile applications, providing ...", "Type: products
Text: - **Professional Tier**: $2,500/month\n - For medium-sized companies.\n - All Basic Tier features pl...", "Type: products
Text: ### Q2 2025: Customer Experience Improvements\n- Launch of a new **mobile app** for end-users.\n- Intr...", "Type: contracts
Text: # Contract with GreenField Holdings for Markellm\n\n**Effective Date:** November 15, 2023 \n**Contract...", "Type: contracts
Text: ## Renewal\n1. **Automatic Renewal**: This contract will automatically renew for sequential one-year ...", "Type: contracts
Text: ## Features\n1. **AI-Powered Matching**: Access to advanced algorithms that connect GreenField Holdin...", "Type: contracts
Text: ## Support\n1. **Customer Support Access**: The Client will have access to dedicated support through ...", "Type: contracts
Text: **Signatures:** \n_________________________ _________________________ \n**...", "Type: contracts
Text: # Contract with Greenstone Insurance for Homellm\n\n---\n\n## Terms\n\n1. **Parties**: This Contract (\"Agr...", "Type: contracts
Text: 4. **Payment Terms**: \n - The Customer shall pay an amount of $10,000 per month for the Standard T...", "Type: contracts
Text: ---\n\n## Features\n\n- **AI-Powered Risk Assessment**: Customer will have access to enhanced risk evalu...", "Type: contracts
Text: - **Customer Portal**: A dedicated portal will be provided, allowing the Customer's clients to manag...", "Type: contracts
Text: ______________________________ \n[Name], [Title] \nDate: ______________________\n\n**For Greenstone In...", "Type: contracts
Text: # Contract with Roadway Insurance Inc. for Carllm\n\n---\n\n## Terms\n\n1. **Agreement Effective Date**: T...", "Type: contracts
Text: ---\n\n## Renewal\n\n1. **Automatic Renewal**: This agreement will automatically renew for an additional...", "Type: contracts
Text: ---\n\n## Features\n\n1. **Access to Core Features**: Roadway Insurance Inc. will have access to all Pro...", "Type: contracts
Text: ---\n\n## Support\n\n1. **Technical Support**: Roadway Insurance Inc. will receive priority technical su...", "Type: contracts
Text: # Contract with Stellar Insurance Co. for Rellm\n\n## Terms\nThis contract is made between **Insurellm*...", "Type: contracts
Text: ### Termination\nEither party may terminate this agreement with a **30-day written notice**. In the e...", "Type: contracts
Text: ## Features\nStellar Insurance Co. will receive access to the following features of the Rellm product...", "Type: contracts
Text: ## Support\nInsurellm provides Stellar Insurance Co. with the following support services:\n\n- **24/7 T...", "Type: contracts
Text: # Contract with TechDrive Insurance for Carllm\n\n**Contract Date:** October 1, 2024 \n**Contract Dura...", "Type: contracts
Text: ## Renewal\n\n1. **Automatic Renewal**: This contract shall automatically renew for additional one-yea...", "Type: contracts
Text: ## Support\n\n1. **Customer Support**: Insurellm will provide 24/7 customer support to TechDrive Insur...", "Type: contracts
Text: **TechDrive Insurance Representative:** \nName: Sarah Johnson \nTitle: Operations Director \nDate: _...", "Type: contracts
Text: # Contract with EverGuard Insurance for Rellm: AI-Powered Enterprise Reinsurance Solution\n\n**Contrac...", "Type: contracts
Text: 4. **Usage Rights**: EverGuard Insurance is granted a non-exclusive, non-transferable license to acc...", "Type: contracts
Text: 1. **Core Functionality**: Rellm provides EverGuard Insurance with advanced AI-driven analytics, sea...", "Type: contracts
Text: 1. **Customer Support**: Insurellm will provide EverGuard Insurance with 24/7 customer support, incl...", "Type: contracts
Text: ---\n\n**Signatures** \n**For Insurellm**: __________________________ \n**Name**: John Smith \n**Title...", "Type: contracts
Text: # Contract with Belvedere Insurance for Markellm\n\n## Terms\nThis Contract (\"Agreement\") is made and e...", "Type: contracts
Text: ## Renewal\n1. **Renewal Terms**: This Agreement may be renewed for additional one-year terms upon mu...", "Type: contracts
Text: ## Features\n1. **AI-Powered Matching**: Belvedere Insurance will benefit from Markellm's AI-powered ...", "Type: contracts
Text: ## Support\n1. **Technical Support**: Technical support will be available from 9 AM to 7 PM EST, Mond...", "Type: contracts
Text: **Belvedere Insurance** \nSignature: ______________________ \nName: [Authorized Signatory] \nTitle: ...", "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 Agreement will automatically renew for successive one-yea...", "Type: contracts
Text: 2. **Seamless Integrations**: The architecture of Rellm allows for easy integration with existing sy...", "Type: contracts
Text: 1. **Technical Support**: Provider shall offer dedicated technical support to the Client via phone, ...", "Type: contracts
Text: **Insurellm, Inc.** \n_____________________________ \nAuthorized Signature \nDate: ________________...", "Type: contracts
Text: # Contract with Velocity Auto Solutions for Carllm\n\n**Contract Date:** October 1, 2023 \n**Contract ...", "Type: contracts
Text: ## Renewal\n\n1. **Automatic Renewal**: This contract will automatically renew for successive 12-month...", "Type: contracts
Text: ## Support\n\n1. **Customer Support**: Velocity Auto Solutions will have access to Insurellm’s custome...", "Type: contracts
Text: # Contract with GreenValley Insurance for Homellm\n\n**Contract Date:** October 6, 2023 \n**Contract N...", "Type: contracts
Text: 4. **Confidentiality:** Both parties agree to maintain the confidentiality of proprietary informatio...", "Type: contracts
Text: 1. **AI-Powered Risk Assessment:** Access to advanced AI algorithms for real-time risk evaluations.\n...", "Type: contracts
Text: 3. **Regular Updates:** Insurellm will offer ongoing updates and enhancements to the Homellm platfor...", "Type: contracts
Text: # Contract with BrightWay Solutions for Markellm\n\n**Contract Date:** October 5, 2023 \n**Contract ID...", "Type: contracts
Text: 3. **Service Level Agreement (SLA):** \n Insurellm commits to a 99.9% uptime for the platform with...", "Type: contracts
Text: 2. **Real-Time Quote Availability:** \n Consumers sourced via BrightWay Solutions will receive rea...", "Type: contracts
Text: 3. **Training and Onboarding:** \n Insurellm agrees to provide one free training session on how to...", "Type: contracts
Text: # Contract with Pinnacle Insurance Co. for Homellm\n\n## Terms\nThis contract (\"Contract\") is entered i...", "Type: contracts
Text: ## Renewal\n1. **Renewal Terms**: At the end of the initial term, this Contract shall automatically r...", "Type: contracts
Text: ## Features\n1. **AI-Powered Risk Assessment**: Utilized for tailored underwriting decisions specific...", "Type: contracts
Text: ## Support\n1. **Technical Support**: Insurellm shall provide 24/7 technical support via an email and...", "Type: company
Text: # Overview of Insurellm\n\nInsurellm is an innovative insurance tech firm with 200 employees across th...", "Type: company
Text: # Careers at Insurellm\n\nInsurellm is hiring! We are looking for talented software engineers, data sc...", "Type: company
Text: # About Insurellm\n\nInsurellm was founded by Avery Lancaster in 2015 as an insurance tech startup des...", "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: ## Annual Performance History\n- **2020:** \n - Completed onboarding successfully. \n - Met expecta...", "Type: employees
Text: ## Compensation History\n- **2020:** Base Salary: $80,000 \n- **2021:** Base Salary Increase to $90,0...", "Type: employees
Text: Alex Chen continues to be a vital asset at Insurellm, contributing significantly to innovative backe...", "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: ## Annual Performance History\n- **2018**: **3/5** - Adaptable team player but still learning to take...", "Type: employees
Text: ## Compensation History\n- **March 2018**: Initial salary of $80,000.\n- **July 2019**: Salary increas...", "Type: employees
Text: # HR Record\n\n# Emily Tran\n\n## Summary\n- **Date of Birth:** March 18, 1991 \n- **Job Title:** Digital...", "Type: employees
Text: - **January 2017 - May 2018**: Marketing Intern \n - Supported the Marketing team by collaborating ...", "Type: employees
Text: - **2021**: \n - Performance Rating: Meets Expectations \n - Key Achievements: Contributed to the ...", "Type: employees
Text: - **Professional Development Goals**: \n - Emily Tran aims to become a Marketing Manager within the...", "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: ## Annual Performance History\n- **2021:** First year at Insurellm; achieved 90% of monthly targets. ...", "Type: employees
Text: ## Other HR Notes\n- Jordan has shown an interest in continuing education, actively participating in ...", "Type: employees
Text: # Avery Lancaster\n\n## Summary\n- **Date of Birth**: March 15, 1985 \n- **Job Title**: Co-Founder & Ch...", "Type: employees
Text: - **2010 - 2013**: Business Analyst at Edge Analytics \n Prior to joining Innovate, Avery worked as...", "Type: employees
Text: - **2018**: **Exceeds Expectations** \n Under Avery’s pivoted vision, Insurellm launched two new su...", "Type: employees
Text: - **2022**: **Satisfactory** \n Avery focused on rebuilding team dynamics and addressing employee c...", "Type: employees
Text: ## Compensation History\n- **2015**: $150,000 base salary + Significant equity stake \n- **2016**: $1...", "Type: employees
Text: ## Other HR Notes\n- **Professional Development**: Avery has actively participated in leadership trai...", "Type: employees
Text: # HR Record\n\n# Maxine Thompson\n\n## Summary\n- **Date of Birth:** January 15, 1991 \n- **Job Title:** ...", "Type: employees
Text: ## Insurellm Career Progression\n- **January 2017 - October 2018**: **Junior Data Engineer** \n * Ma...", "Type: employees
Text: ## Annual Performance History\n- **2017**: *Meets Expectations* \n Maxine showed potential in her ro...", "Type: employees
Text: - **2021**: *Exceeds Expectations* \n Maxine spearheaded the transition to a new data warehousing s...", "Type: employees
Text: ## Compensation History\n- **2017**: $70,000 (Junior Data Engineer) \n- **2018**: $75,000 (Junior Dat...", "Type: employees
Text: # Samantha Greene\n\n## Summary\n- **Date of Birth:** October 14, 1990\n- **Job Title:** HR Generalist\n-...", "Type: employees
Text: ## Annual Performance History\n- **2020:** Exceeds Expectations \n Samantha Greene demonstrated exce...", "Type: employees
Text: ## Compensation History\n- **2020:** Base Salary - $55,000 \n The entry-level salary matched industr...", "Type: employees
Text: - **2023:** Base Salary - $70,000 \n Recognized for substantial improvement in employee relations m...", "Type: employees
Text: # HR Record\n\n# Alex Thomson\n\n## Summary\n- **Date of Birth:** March 15, 1995 \n- **Job Title:** Sales...", "Type: employees
Text: ## Annual Performance History \n- **2022** - Rated as \"Exceeds Expectations.\" Alex Thomson achieved ...", "Type: employees
Text: ## Other HR Notes\n- Alex Thomson is an active member of the Diversity and Inclusion committee at Ins...", "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- **2023:** Rating: 4.5/5 \n *Samuel exceeded expectations, successfu...", "Type: employees
Text: ## Compensation History\n- **2023:** Base Salary: $115,000 + Bonus: $15,000 \n *Annual bonus based o...", "Type: employees
Text: - **Engagement in Company Culture:** Regularly participates in team-building events and contributes ...", "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: ## Annual Performance History \n- **2021**: \n - **Performance Rating**: 4.5/5 \n - **Key Achievem...", "Type: employees
Text: - **2022**: \n - **Base Salary**: $65,000 (Promotion to Senior SDR) \n - **Bonus**: $13,000 (20% o...", "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: employees
Text: ## Annual Performance History\n- **2019:** Exceeds Expectations - Continuously delivered high-quality...", "Type: employees
Text: ## Compensation History\n- **June 2018:** Starting Salary - $85,000\n- **June 2019:** Salary Increase ...", "Type: employees
Text: ## Other HR Notes\n- Jordan K. Bishop has been an integral part of club initiatives, including the In...", "Type: employees
Text: # HR Record\n\n# Emily Carter\n\n## Summary\n- **Date of Birth:** August 12, 1990 \n- **Job Title:** Acco...", "Type: employees
Text: - **2017-2019:** Marketing Intern \n - Assisted with market research and campaign development for s...", "Type: employees
Text: ## Compensation History\n| Year | Base Salary | Bonus | Total Compensation |\n|------|--------...", "Type: employees
Text: Emily Carter exemplifies the kind of talent that drives Insurellm's success and is an invaluable ass..." ], "type": "scatter", "x": [ -5.657416, -5.351562, -4.974328, -6.758723, -5.1783767, -8.013705, -7.724633, -7.009421, -6.2622795, -7.9906154, -6.5681453, -7.1537523, -6.2945085, -6.160263, -6.581191, -5.3914347, -8.6511, -8.733992, -7.8306694, -7.409052, -7.850587, -3.530956, -0.3459931, -9.164472, -5.58201, -0.42522067, -2.365495, -2.261155, -7.4755054, -1.9723155, -0.5107074, 1.3728929, 0.13096334, -4.7760177, 0.39533168, -1.5076412, -1.1420527, -3.9531612, -2.2061682, 1.4366357, -0.0283329, 1.1999503, 1.9628308, -2.8523593, -3.594074, -4.188691, -2.7429156, -0.9163674, -3.9898236, -0.10057961, -7.456868, -0.85561204, -1.487623, -2.7916193, -3.697631, -5.029476, -1.3533958, -0.5565509, 1.0467838, -0.31597954, 0.58721346, -2.8429143, -3.255299, -7.970828, -3.3990865, -3.9981933, -4.9977264, -5.7905965, -3.4425216, -1.8723228, -0.18046375, -8.393366, -1.232387, 1.1742404, 2.166663, 1.3753349, 6.3670363, 11.381568, 11.183392, 4.079516, 6.262372, 11.423692, 11.232132, 7.7912073, 8.14449, 10.054505, 7.760033, 6.486052, 10.746775, 4.7841415, 5.8416777, 7.727125, 8.072181, 8.027484, 12.168078, 6.0563207, 7.114507, 9.875833, 10.239397, 9.473044, 12.688811, 8.840358, 10.427024, 10.3331375, 9.706115, 6.3000236, 10.958657, 5.7937546, 7.3150578, 11.871614, 11.910032, 13.061915, 6.655021, 11.099371, 9.484625, 5.4972415, 11.272516, 12.569222, 4.6411586, 7.664327, 9.094102, 10.352197, 4.157297 ], "y": [ 0.7798145, -0.4125835, 0.22908512, -0.1450787, 1.5344744, -2.1764004, -2.41252, -2.737259, -2.7436514, -1.3173401, 2.8930082, 3.5930097, 3.459859, 4.7082214, 5.0432906, 2.8561232, 0.80448514, 0.9469641, 1.1897537, 1.2518775, -0.080258876, -2.737328, 6.3525867, 3.1305952, -2.9265158, -4.270697, 3.4452105, 5.347361, 4.0795245, 2.4435525, -4.6639924, 4.209005, 5.227655, 5.0731006, 2.2517204, -0.7313133, -0.47301573, -0.76657516, -0.6829508, 3.0451128, 3.5946355, 1.623684, 1.5679804, 0.45906195, 0.49434322, -0.11256464, -0.41779423, -2.4533215, -3.2616763, 6.742018, -3.3956776, 0.9610314, -4.0819, 1.1845034, 1.231206, -0.7055925, 0.81709856, -3.8108573, 3.4220817, 3.589021, 1.459784, 3.9098797, 3.5756776, 3.4562, 3.0881908, -4.189291, -4.884311, -4.4303226, -4.382128, 3.4798448, 6.542574, 4.3561063, 1.6589234, -1.2312827, -1.6579704, -1.3990626, -7.7941036, -2.9172833, -7.0027833, -3.0962424, -8.113277, -3.001593, -7.4111953, -5.2768683, -4.462352, -5.668144, -4.534077, -6.814041, -6.3125286, -6.295914, -2.1399581, -1.7445399, -1.214211, -1.0575716, -7.6512303, -2.1686187, -9.198332, -1.1552562, -2.2693605, -1.583731, -6.318401, -8.300538, -3.3643255, -8.334439, -8.15388, -6.096204, -4.844879, -5.4305058, -7.6300592, -5.20332, -6.3011627, -3.9755912, -6.398866, -5.650257, -6.393014, -7.6237082, -2.4054966, -7.1599183, -6.897935, -6.2120833, -3.916245, -7.0163136, -3.5302787 ] } ], "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 FAISS Vector Store Visualization" }, "width": 800, "xaxis": { "autorange": true, "range": [ -10.51561250768825, 14.41305550768825 ], "type": "linear" }, "yaxis": { "autorange": true, "range": [ -10.200368730668071, 7.744054730668069 ], "type": "linear" } } }, "image/png": "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", "text/html": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# We humans find it easier to visalize things in 2D!\n", "# Reduce the dimensionality of the vectors to 2D using t-SNE\n", "# (t-distributed stochastic neighbor embedding)\n", "\n", "tsne = TSNE(n_components=2, random_state=42)\n", "reduced_vectors = tsne.fit_transform(vectors)\n", "\n", "# Create the 2D scatter plot\n", "fig = go.Figure(data=[go.Scatter(\n", " x=reduced_vectors[:, 0],\n", " y=reduced_vectors[:, 1],\n", " mode='markers',\n", " marker=dict(size=5, color=colors, opacity=0.8),\n", " text=[f\"Type: {t}
Text: {d[:100]}...\" for t, d in zip(doc_types, documents)],\n", " hoverinfo='text'\n", ")])\n", "\n", "fig.update_layout(\n", " title='2D FAISS Vector Store Visualization',\n", " scene=dict(xaxis_title='x',yaxis_title='y'),\n", " width=800,\n", " height=600,\n", " margin=dict(r=20, b=10, l=10, t=40)\n", ")\n", "\n", "fig.show()" ] }, { "cell_type": "code", "execution_count": 12, "id": "e1418e88-acd5-460a-bf2b-4e6efc88e3dd", "metadata": {}, "outputs": [ { "data": { "application/vnd.plotly.v1+json": { "config": { "plotlyServerURL": "https://plot.ly" }, "data": [ { "hoverinfo": "text", "marker": { "color": [ "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "blue", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "red", "orange", "orange", "orange", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green", "green" ], "opacity": 0.8, "size": 5 }, "mode": "markers", "text": [ "Type: products
Text: # Product Summary\n\n# Rellm: AI-Powered Enterprise Reinsurance Solution\n\n## Summary\n\nRellm is an inno...", "Type: products
Text: ### Seamless Integrations\nRellm's architecture is designed for effortless integration with existing ...", "Type: products
Text: ### Regulatory Compliance Tools\nRellm includes built-in compliance tracking features to help organiz...", "Type: products
Text: Join the growing number of organizations leveraging Rellm to enhance their reinsurance processes whi...", "Type: products
Text: Experience the future of reinsurance with Rellm, where innovation meets reliability. Let Insurellm h...", "Type: products
Text: # Product Summary\n\n# Markellm\n\n## Summary\n\nMarkellm is an innovative two-sided marketplace designed ...", "Type: products
Text: - **User-Friendly Interface**: Designed with user experience in mind, Markellm features an intuitive...", "Type: products
Text: - **Customer Support**: Our dedicated support team is always available to assist both consumers and ...", "Type: products
Text: ### For Insurance Companies:\n- **Basic Listing Fee**: $199/month for a featured listing on the platf...", "Type: products
Text: ### Q3 2025\n- Initiate a comprehensive marketing campaign targeting both consumers and insurers to i...", "Type: products
Text: # Product Summary\n\n# Homellm\n\n## Summary\nHomellm is an innovative home insurance product developed b...", "Type: products
Text: ### 2. Dynamic Pricing Model\nWith Homellm's innovative dynamic pricing model, insurance providers ca...", "Type: products
Text: ### 5. Multi-Channel Integration\nHomellm seamlessly integrates into existing insurance platforms, pr...", "Type: products
Text: - **Basic Tier:** Starting at $5,000/month for small insurers with basic integration features.\n- **S...", "Type: products
Text: All tiers include a comprehensive training program and ongoing updates to ensure optimal performance...", "Type: products
Text: With Homellm, Insurellm is committed to transforming the landscape of home insurance, ensuring both ...", "Type: products
Text: # Product Summary\n\n# Carllm\n\n## Summary\n\nCarllm is an innovative auto insurance product developed by...", "Type: products
Text: - **Instant Quoting**: With Carllm, insurance companies can offer near-instant quotes to customers, ...", "Type: products
Text: - **Mobile Integration**: Carllm is designed to work seamlessly with mobile applications, providing ...", "Type: products
Text: - **Professional Tier**: $2,500/month\n - For medium-sized companies.\n - All Basic Tier features pl...", "Type: products
Text: ### Q2 2025: Customer Experience Improvements\n- Launch of a new **mobile app** for end-users.\n- Intr...", "Type: contracts
Text: # Contract with GreenField Holdings for Markellm\n\n**Effective Date:** November 15, 2023 \n**Contract...", "Type: contracts
Text: ## Renewal\n1. **Automatic Renewal**: This contract will automatically renew for sequential one-year ...", "Type: contracts
Text: ## Features\n1. **AI-Powered Matching**: Access to advanced algorithms that connect GreenField Holdin...", "Type: contracts
Text: ## Support\n1. **Customer Support Access**: The Client will have access to dedicated support through ...", "Type: contracts
Text: **Signatures:** \n_________________________ _________________________ \n**...", "Type: contracts
Text: # Contract with Greenstone Insurance for Homellm\n\n---\n\n## Terms\n\n1. **Parties**: This Contract (\"Agr...", "Type: contracts
Text: 4. **Payment Terms**: \n - The Customer shall pay an amount of $10,000 per month for the Standard T...", "Type: contracts
Text: ---\n\n## Features\n\n- **AI-Powered Risk Assessment**: Customer will have access to enhanced risk evalu...", "Type: contracts
Text: - **Customer Portal**: A dedicated portal will be provided, allowing the Customer's clients to manag...", "Type: contracts
Text: ______________________________ \n[Name], [Title] \nDate: ______________________\n\n**For Greenstone In...", "Type: contracts
Text: # Contract with Roadway Insurance Inc. for Carllm\n\n---\n\n## Terms\n\n1. **Agreement Effective Date**: T...", "Type: contracts
Text: ---\n\n## Renewal\n\n1. **Automatic Renewal**: This agreement will automatically renew for an additional...", "Type: contracts
Text: ---\n\n## Features\n\n1. **Access to Core Features**: Roadway Insurance Inc. will have access to all Pro...", "Type: contracts
Text: ---\n\n## Support\n\n1. **Technical Support**: Roadway Insurance Inc. will receive priority technical su...", "Type: contracts
Text: # Contract with Stellar Insurance Co. for Rellm\n\n## Terms\nThis contract is made between **Insurellm*...", "Type: contracts
Text: ### Termination\nEither party may terminate this agreement with a **30-day written notice**. In the e...", "Type: contracts
Text: ## Features\nStellar Insurance Co. will receive access to the following features of the Rellm product...", "Type: contracts
Text: ## Support\nInsurellm provides Stellar Insurance Co. with the following support services:\n\n- **24/7 T...", "Type: contracts
Text: # Contract with TechDrive Insurance for Carllm\n\n**Contract Date:** October 1, 2024 \n**Contract Dura...", "Type: contracts
Text: ## Renewal\n\n1. **Automatic Renewal**: This contract shall automatically renew for additional one-yea...", "Type: contracts
Text: ## Support\n\n1. **Customer Support**: Insurellm will provide 24/7 customer support to TechDrive Insur...", "Type: contracts
Text: **TechDrive Insurance Representative:** \nName: Sarah Johnson \nTitle: Operations Director \nDate: _...", "Type: contracts
Text: # Contract with EverGuard Insurance for Rellm: AI-Powered Enterprise Reinsurance Solution\n\n**Contrac...", "Type: contracts
Text: 4. **Usage Rights**: EverGuard Insurance is granted a non-exclusive, non-transferable license to acc...", "Type: contracts
Text: 1. **Core Functionality**: Rellm provides EverGuard Insurance with advanced AI-driven analytics, sea...", "Type: contracts
Text: 1. **Customer Support**: Insurellm will provide EverGuard Insurance with 24/7 customer support, incl...", "Type: contracts
Text: ---\n\n**Signatures** \n**For Insurellm**: __________________________ \n**Name**: John Smith \n**Title...", "Type: contracts
Text: # Contract with Belvedere Insurance for Markellm\n\n## Terms\nThis Contract (\"Agreement\") is made and e...", "Type: contracts
Text: ## Renewal\n1. **Renewal Terms**: This Agreement may be renewed for additional one-year terms upon mu...", "Type: contracts
Text: ## Features\n1. **AI-Powered Matching**: Belvedere Insurance will benefit from Markellm's AI-powered ...", "Type: contracts
Text: ## Support\n1. **Technical Support**: Technical support will be available from 9 AM to 7 PM EST, Mond...", "Type: contracts
Text: **Belvedere Insurance** \nSignature: ______________________ \nName: [Authorized Signatory] \nTitle: ...", "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 Agreement will automatically renew for successive one-yea...", "Type: contracts
Text: 2. **Seamless Integrations**: The architecture of Rellm allows for easy integration with existing sy...", "Type: contracts
Text: 1. **Technical Support**: Provider shall offer dedicated technical support to the Client via phone, ...", "Type: contracts
Text: **Insurellm, Inc.** \n_____________________________ \nAuthorized Signature \nDate: ________________...", "Type: contracts
Text: # Contract with Velocity Auto Solutions for Carllm\n\n**Contract Date:** October 1, 2023 \n**Contract ...", "Type: contracts
Text: ## Renewal\n\n1. **Automatic Renewal**: This contract will automatically renew for successive 12-month...", "Type: contracts
Text: ## Support\n\n1. **Customer Support**: Velocity Auto Solutions will have access to Insurellm’s custome...", "Type: contracts
Text: # Contract with GreenValley Insurance for Homellm\n\n**Contract Date:** October 6, 2023 \n**Contract N...", "Type: contracts
Text: 4. **Confidentiality:** Both parties agree to maintain the confidentiality of proprietary informatio...", "Type: contracts
Text: 1. **AI-Powered Risk Assessment:** Access to advanced AI algorithms for real-time risk evaluations.\n...", "Type: contracts
Text: 3. **Regular Updates:** Insurellm will offer ongoing updates and enhancements to the Homellm platfor...", "Type: contracts
Text: # Contract with BrightWay Solutions for Markellm\n\n**Contract Date:** October 5, 2023 \n**Contract ID...", "Type: contracts
Text: 3. **Service Level Agreement (SLA):** \n Insurellm commits to a 99.9% uptime for the platform with...", "Type: contracts
Text: 2. **Real-Time Quote Availability:** \n Consumers sourced via BrightWay Solutions will receive rea...", "Type: contracts
Text: 3. **Training and Onboarding:** \n Insurellm agrees to provide one free training session on how to...", "Type: contracts
Text: # Contract with Pinnacle Insurance Co. for Homellm\n\n## Terms\nThis contract (\"Contract\") is entered i...", "Type: contracts
Text: ## Renewal\n1. **Renewal Terms**: At the end of the initial term, this Contract shall automatically r...", "Type: contracts
Text: ## Features\n1. **AI-Powered Risk Assessment**: Utilized for tailored underwriting decisions specific...", "Type: contracts
Text: ## Support\n1. **Technical Support**: Insurellm shall provide 24/7 technical support via an email and...", "Type: company
Text: # Overview of Insurellm\n\nInsurellm is an innovative insurance tech firm with 200 employees across th...", "Type: company
Text: # Careers at Insurellm\n\nInsurellm is hiring! We are looking for talented software engineers, data sc...", "Type: company
Text: # About Insurellm\n\nInsurellm was founded by Avery Lancaster in 2015 as an insurance tech startup des...", "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: ## Annual Performance History\n- **2020:** \n - Completed onboarding successfully. \n - Met expecta...", "Type: employees
Text: ## Compensation History\n- **2020:** Base Salary: $80,000 \n- **2021:** Base Salary Increase to $90,0...", "Type: employees
Text: Alex Chen continues to be a vital asset at Insurellm, contributing significantly to innovative backe...", "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: ## Annual Performance History\n- **2018**: **3/5** - Adaptable team player but still learning to take...", "Type: employees
Text: ## Compensation History\n- **March 2018**: Initial salary of $80,000.\n- **July 2019**: Salary increas...", "Type: employees
Text: # HR Record\n\n# Emily Tran\n\n## Summary\n- **Date of Birth:** March 18, 1991 \n- **Job Title:** Digital...", "Type: employees
Text: - **January 2017 - May 2018**: Marketing Intern \n - Supported the Marketing team by collaborating ...", "Type: employees
Text: - **2021**: \n - Performance Rating: Meets Expectations \n - Key Achievements: Contributed to the ...", "Type: employees
Text: - **Professional Development Goals**: \n - Emily Tran aims to become a Marketing Manager within the...", "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: ## Annual Performance History\n- **2021:** First year at Insurellm; achieved 90% of monthly targets. ...", "Type: employees
Text: ## Other HR Notes\n- Jordan has shown an interest in continuing education, actively participating in ...", "Type: employees
Text: # Avery Lancaster\n\n## Summary\n- **Date of Birth**: March 15, 1985 \n- **Job Title**: Co-Founder & Ch...", "Type: employees
Text: - **2010 - 2013**: Business Analyst at Edge Analytics \n Prior to joining Innovate, Avery worked as...", "Type: employees
Text: - **2018**: **Exceeds Expectations** \n Under Avery’s pivoted vision, Insurellm launched two new su...", "Type: employees
Text: - **2022**: **Satisfactory** \n Avery focused on rebuilding team dynamics and addressing employee c...", "Type: employees
Text: ## Compensation History\n- **2015**: $150,000 base salary + Significant equity stake \n- **2016**: $1...", "Type: employees
Text: ## Other HR Notes\n- **Professional Development**: Avery has actively participated in leadership trai...", "Type: employees
Text: # HR Record\n\n# Maxine Thompson\n\n## Summary\n- **Date of Birth:** January 15, 1991 \n- **Job Title:** ...", "Type: employees
Text: ## Insurellm Career Progression\n- **January 2017 - October 2018**: **Junior Data Engineer** \n * Ma...", "Type: employees
Text: ## Annual Performance History\n- **2017**: *Meets Expectations* \n Maxine showed potential in her ro...", "Type: employees
Text: - **2021**: *Exceeds Expectations* \n Maxine spearheaded the transition to a new data warehousing s...", "Type: employees
Text: ## Compensation History\n- **2017**: $70,000 (Junior Data Engineer) \n- **2018**: $75,000 (Junior Dat...", "Type: employees
Text: # Samantha Greene\n\n## Summary\n- **Date of Birth:** October 14, 1990\n- **Job Title:** HR Generalist\n-...", "Type: employees
Text: ## Annual Performance History\n- **2020:** Exceeds Expectations \n Samantha Greene demonstrated exce...", "Type: employees
Text: ## Compensation History\n- **2020:** Base Salary - $55,000 \n The entry-level salary matched industr...", "Type: employees
Text: - **2023:** Base Salary - $70,000 \n Recognized for substantial improvement in employee relations m...", "Type: employees
Text: # HR Record\n\n# Alex Thomson\n\n## Summary\n- **Date of Birth:** March 15, 1995 \n- **Job Title:** Sales...", "Type: employees
Text: ## Annual Performance History \n- **2022** - Rated as \"Exceeds Expectations.\" Alex Thomson achieved ...", "Type: employees
Text: ## Other HR Notes\n- Alex Thomson is an active member of the Diversity and Inclusion committee at Ins...", "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- **2023:** Rating: 4.5/5 \n *Samuel exceeded expectations, successfu...", "Type: employees
Text: ## Compensation History\n- **2023:** Base Salary: $115,000 + Bonus: $15,000 \n *Annual bonus based o...", "Type: employees
Text: - **Engagement in Company Culture:** Regularly participates in team-building events and contributes ...", "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: ## Annual Performance History \n- **2021**: \n - **Performance Rating**: 4.5/5 \n - **Key Achievem...", "Type: employees
Text: - **2022**: \n - **Base Salary**: $65,000 (Promotion to Senior SDR) \n - **Bonus**: $13,000 (20% o...", "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: employees
Text: ## Annual Performance History\n- **2019:** Exceeds Expectations - Continuously delivered high-quality...", "Type: employees
Text: ## Compensation History\n- **June 2018:** Starting Salary - $85,000\n- **June 2019:** Salary Increase ...", "Type: employees
Text: ## Other HR Notes\n- Jordan K. Bishop has been an integral part of club initiatives, including the In...", "Type: employees
Text: # HR Record\n\n# Emily Carter\n\n## Summary\n- **Date of Birth:** August 12, 1990 \n- **Job Title:** Acco...", "Type: employees
Text: - **2017-2019:** Marketing Intern \n - Assisted with market research and campaign development for s...", "Type: employees
Text: ## Compensation History\n| Year | Base Salary | Bonus | Total Compensation |\n|------|--------...", "Type: employees
Text: Emily Carter exemplifies the kind of talent that drives Insurellm's success and is an invaluable ass..." ], "type": "scatter3d", "x": [ 10.574532, 17.168737, -17.779839, 42.432514, 31.939625, 81.58427, 73.11807, 72.017296, 82.13942, 67.43707, 27.02473, 39.152187, 14.694442, 60.02976, 57.065754, 3.3731627, 14.87718, 28.963793, 36.10357, 49.960213, 42.218616, -21.139791, 14.940806, 62.210804, 79.14163, -7.2309794, -16.541533, -3.233923, 53.234257, -22.39822, 9.041602, -23.646568, 8.435684, 77.49919, -21.151524, 10.669304, 4.810214, 2.313524, 10.940845, -38.493004, -10.3407755, 29.634792, -65.51476, 34.495274, 17.24997, 2.6952226, -59.793846, -27.598888, 57.347626, 28.837118, 92.74769, 31.056536, 30.230637, 39.334774, 51.65443, -5.4677944, 31.069746, 4.988879, -33.65265, 57.954292, -54.09445, -24.684357, -3.475585, 36.001396, -26.2112, 70.2531, 78.39517, 84.40315, 57.02638, 16.354214, 6.601737, 48.272915, -45.65737, 1.4264491, -24.12308, 20.765697, 8.103356, -64.68929, -60.041668, -42.694756, 14.657618, -64.18794, -69.75638, -62.263195, -58.80821, -80.817856, -78.57243, -22.407711, -49.401333, -20.848778, -16.395742, -15.641011, 7.2111783, 0.18549652, -90.00813, -10.424618, -5.344003, -29.427475, -41.974533, -19.53244, -51.275753, -22.551493, -28.349007, -53.854477, -38.12469, -13.612175, -38.895386, -17.720013, -3.0384831, -61.168724, -75.870926, 9.286311, 5.669115, -62.22309, -36.345222, -6.303077, -44.777668, -73.735245, -14.205331, 24.661335, -66.57858, 20.109545, -58.2281 ], "y": [ -12.7359495, -30.876972, -22.067339, -5.5269856, -20.414396, -4.6363235, 7.2993784, -3.385071, 12.822765, 6.43254, -44.466362, -56.17959, -57.278294, -34.92456, -43.909443, -33.119408, 7.816011, 16.892565, -5.8429976, -19.242083, 14.153994, -19.067257, -79.74044, -78.9052, 24.38317, -29.560297, 12.58942, -81.16138, -63.89177, -37.02063, -23.436914, -97.32981, -92.38052, -52.35171, -85.87925, -28.643091, -48.916958, -9.1980715, -4.423408, -73.46124, -67.36527, 43.2403, -66.21299, -25.763964, -32.588226, -41.912003, 88.85663, -20.289455, -0.50626284, -100.46157, -15.646977, -5.2484374, -19.818632, -46.65949, 35.306133, -35.10067, 17.055412, -13.854688, -78.60895, 35.100025, -41.988274, -57.32439, -66.95911, -75.98633, -47.901028, -19.618052, -44.72537, -23.100975, -26.319355, -51.08191, -100.798935, -87.28581, -34.44673, -6.7311134, -1.7348578, 11.527053, 56.204773, 21.256529, 59.36381, 8.717058, 75.96616, 43.17332, 43.613567, 9.2787285, 4.770594, 31.448248, -4.0775123, 58.659966, 38.37099, 32.443676, 13.48673, 37.62229, 39.408714, 23.403852, 60.901432, 48.396935, 80.55659, 85.638626, 59.43376, 65.85908, 84.21796, 102.04246, 107.20257, 101.58528, 86.03432, 47.815907, 36.878307, 26.85156, 80.02965, 73.75553, 78.565475, 108.51336, 47.97063, 51.313667, 62.620865, 63.923195, 31.12987, 80.27194, 42.60242, 71.0257, 11.617887, 67.05301, -9.053225 ], "z": [ -70.408066, -91.266685, -69.883514, -83.33502, -59.37371, -45.855957, -29.427502, -8.724047, 5.4299064, -65.11009, -43.63478, -24.021072, -24.953876, -38.53293, -61.720154, -37.27078, -50.18197, -35.707664, -30.967945, -22.050114, -65.497375, 18.329159, 25.69994, -44.919304, 26.445461, 78.90974, -78.523705, 54.482758, -7.2413745, -11.716538, 93.45988, -1.158737, -1.4209359, -16.63941, -27.178946, 30.235897, 18.336214, -0.4756524, 21.996094, -5.251641, -2.86962, -52.424652, -0.314814, 10.413203, -5.951366, -70.69064, -74.841034, 58.223354, 24.2808, 25.339191, -20.976206, 47.267094, 73.80028, 21.609999, -5.049262, -97.45211, 34.879322, 66.029755, 18.782377, -33.59886, 20.82808, -47.966576, -48.63757, -40.930275, 35.5203, 34.117455, 24.028719, 9.700905, 50.414143, 52.110744, 27.217413, -15.736553, -7.8196363, -29.157057, -22.764433, -4.6217175, -22.790184, 61.15323, -9.406136, -48.40084, -34.03866, 52.536488, -24.133337, -11.884066, 10.305743, 8.181893, -0.21625689, -22.071638, -4.1506543, -31.37159, 39.81665, 53.46707, 57.859932, 69.61297, 0.15355189, 80.32389, 18.199785, 42.60248, 60.72887, 52.969788, 29.168976, -22.34308, 7.7036004, -6.6861544, -14.169032, -2.5249429, 25.025623, 2.0362377, -13.213163, -33.986835, -14.487987, -2.0317492, 6.2367206, 17.983465, 11.510135, -44.819134, 68.60727, 12.572406, -51.457294, 1.640381, 32.901413, 34.649315, -40.395123 ] } ], "layout": { "height": 700, "margin": { "b": 10, "l": 10, "r": 20, "t": 40 }, "scene": { "aspectmode": "auto", "aspectratio": { "x": 0.9419723669496408, "y": 1.0788515405572938, "z": 0.9840114481681961 }, "camera": { "center": { "x": 0, "y": 0, "z": 0 }, "eye": { "x": -0.3240312930920217, "y": 2.104121309336703, "z": -0.39392542021594795 }, "projection": { "type": "perspective" }, "up": { "x": 0, "y": 0, "z": 1 } }, "xaxis": { "title": { "text": "x" }, "type": "linear" }, "yaxis": { "title": { "text": "y" }, "type": "linear" }, "zaxis": { "title": { "text": "z" }, "type": "linear" } }, "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": "3D FAISS Vector Store Visualization" }, "width": 900 } }, "image/png": "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", "text/html": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Let's try 3D!\n", "\n", "tsne = TSNE(n_components=3, random_state=42)\n", "reduced_vectors = tsne.fit_transform(vectors)\n", "\n", "# Create the 3D scatter plot\n", "fig = go.Figure(data=[go.Scatter3d(\n", " x=reduced_vectors[:, 0],\n", " y=reduced_vectors[:, 1],\n", " z=reduced_vectors[:, 2],\n", " mode='markers',\n", " marker=dict(size=5, color=colors, opacity=0.8),\n", " text=[f\"Type: {t}
Text: {d[:100]}...\" for t, d in zip(doc_types, documents)],\n", " hoverinfo='text'\n", ")])\n", "\n", "fig.update_layout(\n", " title='3D FAISS Vector Store Visualization',\n", " scene=dict(xaxis_title='x', yaxis_title='y', zaxis_title='z'),\n", " width=900,\n", " height=700,\n", " margin=dict(r=20, b=10, l=10, t=40)\n", ")\n", "\n", "fig.show()" ] }, { "cell_type": "markdown", "id": "9468860b-86a2-41df-af01-b2400cc985be", "metadata": {}, "source": [ "## Time to use LangChain to bring it all together" ] }, { "cell_type": "code", "execution_count": 13, "id": "129c7d1e-0094-4479-9459-f9360b95f244", "metadata": {}, "outputs": [], "source": [ "# create a new Chat with OpenAI\n", "llm = ChatOpenAI(temperature=0.7, model_name=MODEL)\n", "\n", "# set up the conversation memory for the chat\n", "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n", "\n", "# the retriever is an abstraction over the VectorStore that will be used during RAG\n", "retriever = vectorstore.as_retriever()\n", "\n", "# putting it together: set up the conversation chain with the GPT 3.5 LLM, the vector store and memory\n", "conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)" ] }, { "cell_type": "code", "execution_count": null, "id": "968e7bf2-e862-4679-a11f-6c1efb6ec8ca", "metadata": {}, "outputs": [], "source": [ "query = \"Can you describe Insurellm in a few sentences\"\n", "result = conversation_chain.invoke({\"question\":query})\n", "print(result[\"answer\"])" ] }, { "cell_type": "markdown", "id": "bbbcb659-13ce-47ab-8a5e-01b930494964", "metadata": {}, "source": [ "## Now we will bring this up in Gradio using the Chat interface -\n", "\n", "A quick and easy way to prototype a chat with an LLM" ] }, { "cell_type": "code", "execution_count": 14, "id": "c3536590-85c7-4155-bd87-ae78a1467670", "metadata": {}, "outputs": [], "source": [ "# Wrapping that in a function\n", "\n", "def chat(message, history):\n", " result = conversation_chain.invoke({\"question\": message})\n", " return result[\"answer\"]" ] }, { "cell_type": "code", "execution_count": 15, "id": "b252d8c1-61a8-406d-b57a-8f708a62b014", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Running on local URL: http://127.0.0.1:7861\n", "\n", "To create a public link, set `share=True` in `launch()`.\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# And in Gradio:\n", "\n", "view = gr.ChatInterface(chat).launch()" ] }, { "cell_type": "code", "execution_count": null, "id": "5435b2b9-935c-48cd-aaf3-73a837ecde49", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.10" } }, "nbformat": 4, "nbformat_minor": 5 }