How we implemented a robust document processing and retrieval system that handles file uploads, chunking, embedding generation, and semantic search at scale. The Challenge Building a Retrieval-Augmented Generation (RAG) system that can handle dive...
Voice AI is rapidly becoming immersive, with real-time transcription, reasoning, and speech synthesis all working together. In my latest experiment, we tested KittenML TTS (preview) as the speech output layer in a LiveKit voice agent pipeline using O...
Building accurate company name search query and index
Introduction Internal teams of an organization need a mechanism to quickly and accurately obtain the information they need from the vast amount of internal documentation. Large Language Models like GPT and PALM are good at answering generic questions...
At Peakflo, we send thousands of PDFs per day to our customers. These include invoices, statements of accounts, or on-demand reports attached to emails or directly downloaded on-demand through the UI. To achieve this, we had to build a fast, reliable...
Hello, builders, innovators, tech enthusiasts, and curious minds 🧑🚀 The Peakflo Engineering team is extremely thrilled to announce the launch of our new Blog! It will be a platform to share the ins and outs, triumphs and challenges, and journey an...
Problem As an engineer at Peakflo, I had the opportunity to work on improving the overall performance and SEO scores of the website that was previously built on WordPress. One of the main challenges with the previous website was that it took a long t...
