In the previous posts (Part 1, Part 2, Part 3) I showed how we built the context-aware retriever. This post covers how to use kb-bridge, the Python...
Read More
In Part 1 and Part 2, I walked through the design and implementation. Now let’s evaluate how well it performs on the ContractNLI dataset and see if...
Read More
In Part 1, I walked through the design. Now let’s see it in action with a hands-on example using the ContractNLI dataset. I’ll assume chunking is a...
Read More
In this post, I’ll share how I built a context-aware retriever for knowledge base question answering. It runs on top of an MCP server and can easil...
Read More
TL;DR. We train a small bidirectional Transformer + Double DQN to play Hangman, restricted to words ≤5 characters (training and inference) to keep ...
Read More