Cobus Greyling (9)

A Benchmark for Verifying Chain-Of-Thought

A Chain-of-Thought is only as strong as its weakest link; a recent study from Google Research created a benchmark...

Seven RAG Engineering Failure Points

Retrieval-Augmented Generation (RAG) systems remains a compelling solution to the challenge of relevant up-to-date...

Adding Noise Improves RAG Performance

This study’s findings suggest that including irrelevant documents can enhance performance by over 30% in...

Corrective RAG (CRAG)

By now, RAG is an accepted and well established standard for addressing data relevance for in-context learning. But...

MultiHop-RAG

A recent direction in RAG architecture is establishing wider context via a process of orchestration and chains...

No-Code Deployment & Orchestration Of Open-Sourced Foundation Models

No-Code Deployment Of Open-Sourced Foundation Models Open-Sourced models from Argilla, EleutherAl, Facebook, Google,...

UniMS-RAG: Unified Multi-Source RAG for Personalised Dialogue

Considerable development has taken place in the area of RAG, especially in adding structure and multi-document...

Prompt-RAG: Vector Embedding Free Retrieval-Augmented Generation

Prompt-RAG certainly has limitations, but in selected instances, Prompt-RAG will serve well as an alternative to the...

Understanding LLM User Experience & Expectation

This study surfaces valuable insights into the frequency of LLM use together with user intents, expectations and...

Bulk Data Discovery

Human supervision & annotation of data will increase in importance, and numerous tools are being developed to...