Cobus GreylingLanguage Agent Tree Search — LATSThe LATS framework is a first of its kind general framework that synergises the capabilities of LMs in reasoning, acting, and planning. It…14h ago14h ago
Cobus GreylingTree Of Thoughts Prompting (ToT)Prompting techniques are continuously evolving & this evolution demands supporting structures to put more complex prompts to work. This…1d ago1d ago
Cobus GreylingUsing Fine-Tuning To Imbed Hidden Messages In Language ModelsThis text is revealed only when triggered by a specific query to the Language Model.2d ago22d ago2
Cobus GreylingImplementing Chain-of-Thought Principles in Fine-Tuning Data for RAG SystemsKnowledge-oriented question answering is now a crucial aspect of enterprise knowledge management, aiming to provide accurate responses to…5d ago5d ago
Cobus GreylingAssertions Are Like Guardrails for LLM AppsDSPy Assertions are a different approach to guardrails, which asserts computational constraints on foundation models.Jun 3Jun 3
Cobus GreylingRAGTruthIn essence, RAGTruth is a large-scale corpus of naturally generated hallucinations, featuring detailed word-level annotations specifically…May 31May 31
Cobus GreylingDSPy & The Principle Of AssertionsIn February 2024, a study introduced Assertions to the DSPy framework. These Assertions serve as both constraints and guides for Language…May 30May 30
Cobus GreylingUsing DSPy For A RAG ImplementationRAG enables LLMs to adaptively access real-time knowledge, providing insightful responses beyond their original training. Yet, implementing…May 291May 291
Cobus GreylingAn Introduction To DSPyDeclarative Self-Improving Language Programs (DSPy) aims to separate the program flow from the prompts. While also optimising prompts based…May 281May 281
Cobus GreylingControllable Agents For RAG With Human In The Loop ChatThis demo from LlamaIndex is a good example of how the capabilities of agents and RAG are merging & how HITL can be used to solve for long…May 27May 27