Fine-Tuning Embedding Models: Achieving More with Less
Author(s): Nilesh Raghuvanshi Originally published on Towards AI. Improving Retrieval Augmented Generation (RAG) Systematically Fine-tuning for alignmentβ AI generated image Introduction In my last article, we saw that, while evaluating multiple embedding models on our domain-specific data, the huggingface/BAAI/bge-large-en-v1.5 model (1024 dimensions) …
Evaluating Retrieval & Generation Pipelines
Author(s): Nilesh Raghuvanshi Originally published on Towards AI. Improving Retrieval Augmented Generation (RAG) Systematically Evaluating the pipeline β AI generated image Introduction This is the third and final article in a short series on systematically improving retrieval-augmented generation (RAG). In earlier articles, …
Choosing the Best Embedding Model For Your RAG Pipeline
Author(s): Nilesh Raghuvanshi Originally published on Towards AI. Improving Retrieval Augmented Generation (RAG) Systematically Choosing the right option β AI generated image Introduction Through my experience building an extractive question-answering system using Googleβs QANet and BERT back in 2018, I quickly realized …