My Courses
-
Nomic Embeddings and Their Integration with LlamaIndex
Enhance AI with Nomic Embeddings and LlamaIndex for efficient, semantic data handling and retrieval.
-
Hands-On Guide to Running LLMs Locally using Ollama
Explore how Ollama enables local execution of large language models for enhanced privacy and cost savings.
-
Thought-Augmented Reasoning through Buffer of Thoughts (BoT)
Enhance the robustness and accuracy of LLM through thought-augmented reasoning based on the Buffer of Thought approach.
-
How Does RAG Enhance the Contextual Understanding of LLMs?
RAG elevates understanding: integrating external knowledge sources into language model generation process
-
Observing and Examining AI Agents through AgentOps
Explore how AgentOps monitors, debugs, and tracks costs for LLM-based AI agents in various contexts.
-
Self-Organising File Management Through LlamaFS
Implement LlamaFS, an AI-driven file management system, based on Llama3 and Groq.
-
GNN-RAG: Enhancing the Reasoning Capabilities of LLMs using GNNs
GNN-RAG, a recent development, synergises GNNs and LLMs to excel in KGQA.
-
Implementing RAG-as-a-Service using Vectara
Discover Vectara and simplify RAG-as-a-Service for seamless generative AI application building.
-
RAG Reproducibility and Research using FlashRAG
FlashRAG: An open-source toolkit for standardised comparison and reproduction of RAG methods.
-
No-Code Approach for Building Agentic RAG using RAGapp
Implement Agentic RAG with RAGapp: no-code, an agent-based framework for multi-step reasoning using Docker.
