Blog·Author
Naman Bansal.
Writer and editor at Supermemory. Covering AI memory, context engineering, and the future of intelligent systems for developers and builders.
- Matryoshka Representation Learning: The Ultimate Guide & How We Use ItEmbeddings are the cornerstone of any retrieval system. And the larger the embeddings, the more information they can store. But large embeddings require a lot of memory, which leads to high computational costs and latency.
- Build Your Own Perplexity in 15 Minutes With SupermemorySupermemory has a fascinating open-source tool called OpenSearchAI. It's essentially a search assistant similar to Perplexity, but it remembers everything you've searched for and enriches future responses with that memory. I thought to myself, “This seems cool.
- Building an AI Compliance Chatbot With Supermemory and Google DriveContract compliance reviews are a serious drain on time and focus. It’s a repetitive process that takes away from actual legal thinking, and the workflow is absolutely broken. Files live in different places. You’re never sure if you’re reading the latest version.
- Knowledge Graph For RAG: Step-by-Step TutorialIf you’ve ever built a retrieval-augmented generation (RAG) system using embeddings and vector databases, you already know the drill: you turn your data into vectors, stuff them into a store like FAISS, and let your model retrieve similar chunks during inference. And it works, until it doesn’t.
- 2 Approaches For Extending Context Windows in LLMsTransformer-based large language models have become the poster boys of modern AI, yet they still share one stark limitation: a finite context window. Once that window overflows, performance drops like a rock or the model forgets key details.
- LLM Costs Skyrocketing? Real Experts Weigh InIn this blog, we're gonna walk through a fictional story, while learning how to optimize LLMs for cost, and the associated tradeoffs. Tuesday, 10 June, 2:14 PM PST The billing alert hit.
- Best Open-Source Embedding Models Benchmarked and RankedIf your AI agent is returning the wrong context, it’s probably not your LLM, but your embedding model. Embeddings are the hidden engine behind retrieval-augmented generation (RAG) and memory systems. The better they are, the more relevant your results, and the smarter your app feels.
- 3 Ways To Build LLMs With Long-Term MemoryYou’ve already met our guide on implementing short-term conversational memory using LangChain, which is great for managing context inside a single chat window. But life, therapy, and enterprise apps sprawl across days, weeks, and years.
- How To Add Conversational Memory To LLMs Using LangChainChatbots that don’t remember conversations are very frustrating to work with. Users treat AI like a human and expect it to remember. LangChain recently migrated to LangGraph, a new stateful framework for building multi-step, memory-aware LLM apps.