Akash MathurinAWS in Plain EnglishDeploy a Serverless ML Inference using FastAPI, AWS Lambda, and API GatewayHarnessing the Power of Scalable Infrastructure for Seamless ML Deployment18 min read·Feb 17, 2024--3--3
Akash MathurData Management in LlamaIndex🦙: Smart Tracking and Debugging of Document ChangesEfficient Document Tracing and Debugging of Document Changes14 min read·Feb 2, 2024--1--1
Akash MathurAdvanced RAG: Query Augmentation for Next-Level Search using LlamaIndex🦙Using Open Source LLM Zephyr-7b-alpha and BGE Embeddings bge-large-en-v1.513 min read·Jan 18, 2024--3--3
Akash MathurAdvanced RAG: Enhancing Retrieval Efficiency through Evaluating Reranker Models using LlamaIndex🦙Refining Retrieval: Evaluating Reranker Models for Enhanced Efficiency12 min read·Dec 28, 2023--2--2
Akash MathurAdvanced RAG: Optimizing Retrieval with Additional Context & MetaData using LlamaIndex🦙Parent-child document retrieval with metadata extraction using Zephyr12 min read·Dec 23, 2023--3--3
Akash MathurElevating Mistral-7B’s Performance through QLoRARefining Mistral-7B via QLoRA for Diverse Applications13 min read·Dec 15, 2023----
Akash MathurVector Database vs. Indexing- Path to Efficient Data HandlingA Comparative Dive into Database vs. Indexing for Seamless Data Mastery9 min read·Dec 10, 2023--1--1
Akash MathurComprehensive Guide to Customize your Llama2 ChatBot with LlamaIndex and StreamlitEmpower Your Conversations: Customizing Your Llama2 Chatbot with LlamaIndex and Streamlit12 min read·Nov 28, 2023--1--1
Akash MathurinAWS in Plain EnglishBig Data Processing Using Distributed Maps and AWS Step FunctionsHarnessing Distributed Maps and AWS Step Functions9 min read·Nov 11, 2023----
Akash MathurinAWS in Plain EnglishUnlocking FAISS for Efficient Search: Vector Indexing and ANN with Serverless ArchitectureDeciphering FAISS, Vector Indexing and ANN for Efficient Search10 min read·Nov 5, 2023----