Vivek Nayyar vivek12345

Bucket	Outcome	Steps
Learning/Performance	Single ownership of a project	- Be a PIC for a large project - Setup alerts and monitors on datadog - Setup zenduty for oncall and support team on oncall
Initiative Goals	Knowledge Sharing and Visibility	- Share a project or work in tech sharing session - Write a blog for our engineering blog
Personal Goals	Know team members from different teams	- Have a coffee with one member of non tech team

Bucket	Outcome	Steps
Learning/Performance	Having better understand of codebase	- Complete at least one medium-sized task. - Be comfortable navigating all parts of the codebase - Be release manager for one sprint
Initiative Goals	Improve code quality and process	- Build a useful utility for the team - Improve test coverage - Ask questions in product and tech grooming
Personal Goals	Know cross team members	- Have a coffee with one member of another tech team

Bucket	Outcome	Steps
Learning/Performance	Understand how the team works and responsibilities of different stakeholders.	- Understand the team’s processes (meetings, git workflow, code review, testing, deployment, etc.) - Understand who to talk to for different question domains (tech, process, HR, culture, etc.) - Understand the organization hierarchy and all departments in the company - Setup dev environment locally - Understand your manager’s/lead’s expectations of you in this role. - Buy one policy on Qoala App to understand the end to end flow - Pick up one small task every week starting week 2.
Initiative Goals	Being involved in discussions	- Make a documentation contribution. - Ask atleast one question in team meetings
Personal Goals	Knowing your team better	- Come to office every day for the initial week to know the team. - Have a coffee with one team member - Schedule 1:1 with yo

	// Get the pdf loader from langchain
	import { PDFLoader } from "langchain/document_loaders/fs/pdf";
	// import the RecursiveCharacterTextSplitter from langchain
	import { RecursiveCharacterTextSplitter } from "langchain/text_splitter";
	// We will use open ai embeddings from langchain and import it
	import { OpenAIEmbeddings } from "langchain/embeddings/openai";
	// Use HNSWLib as our vector db
	import { HNSWLib } from "langchain/vectorstores/hnswlib";
	// import the chain for connecting llm with vectore store
	import { RetrievalQAChain } from "langchain/chains";

	// import the chain for connecting llm with vectore store
	import { RetrievalQAChain } from "langchain/chains";

	// import the open ai function to load our LLM model
	import { OpenAI } from "langchain/llms/openai";

	// Create vector store retriever
	const vectorStoreRetriever = vectorStore.asRetriever();

	// init the LLM model

	// We will use open ai embeddings from langchain and import it
	import { OpenAIEmbeddings } from "langchain/embeddings/openai";

	// Use HNSWLib as our vector db
	import { HNSWLib } from "langchain/vectorstores/hnswlib";

	// Init open ai embeddings
	const embeddings = new OpenAIEmbeddings();

	// Finally store our splitted chunks with open ai embeddings

	// import the RecursiveCharacterTextSplitter from langchain
	import { RecursiveCharacterTextSplitter } from "langchain/text_splitter";

	// Initialize it with chunksize and chunkOverlap
	const splitter = new RecursiveCharacterTextSplitter({
	chunkSize: 1000,
	chunkOverlap: 20,
	});

	// created chunks from pdf

	// Get the pdf loader from langchain
	import { PDFLoader } from "langchain/document_loaders/fs/pdf";

	// Initialize it with the path to the pdf file
	const loader = new PDFLoader("src/documents/budget_speech.pdf");

	// Load into docs variable
	const docs = await loader.load();

	on("before:browser:launch", (browser = {}, launchOptions) => {
	const downloadDirectory = path.join(__dirname, "..", "excelDownloads");
	if (browser.family === "chromium") {
	launchOptions.preferences.default["download"] = {
	default_directory: downloadDirectory
	};
	}
	return launchOptions;
	});