Writing
On RAG, LLMs and building with AI. These were published on the Nanonets blog; new essays on deploying AI agents will live here.
- Best LLM APIs for Document Data ExtractionNanonets, Aug 2024A hands-on comparison of OpenAI, Gemini, Claude and Nanonets for pulling structured data out of invoices, medical records, multipage PDFs and handwriting — accuracy, pricing and fit.
- Building a Retrieval-Augmented Generation (RAG) AppNanonets, Aug 2024Building a RAG pipeline for financial document analysis, through both the indexing and the querying stages.
- RAG for Smarter AI WorkflowsNanonets, Aug 2024Where RAG fits inside an automated business workflow, rather than as a standalone question-answering feature.
- What is Retrieval Augmented Generation (RAG)?Nanonets, Aug 2024How RAG lets a language model pull in outside information before answering, explained without the jargon.
- What are Large Language Models (LLMs)?Nanonets, Aug 2024A grounded introduction to what LLMs are and how they generate language — and whether one belongs in your product.
- Prompt Engineering: 8 Advanced Techniques for Better AI ResultsNanonets, Jan 2024Eight concrete techniques for more reliable LLM output, from few-shot examples to structured prompting.
- What Is LlamaIndex and How Does It Work?Nanonets, Oct 2023How LlamaIndex connects your own data to an LLM through indexing and querying.