Sascha GstirinPondhouse DataExtract data from documents using Large Language ModelsThe more we work with AI, the more we need to extract data from documents. In a scalable manner. While conventional and machine learning…Jul 2Jul 2
Sascha GstirinPondhouse DataHow to finetune Llama 3 on consumer GPUsLarge Language Models (LLMs) have proven themselves as powerful tools capable of understanding and generating human-like text across a wide…Jul 2Jul 2
Sascha GstirinPondhouse DataUsing AI directly from your database — with PostgreSQL and pgaiAI is transforming the way we create applications and interact with data. Almost every application needs some form of AI nowadays. Every…Jun 17Jun 17
Sascha GstirinPondhouse DataKAN: Is this the end of feedforward networks?MLPs are the backbone of the the most powerful AI models we know, but are KAN the next revolutionary step which will replace them?May 27May 27
Sascha GstirinPondhouse DataLLM Safety with Llama Guard 2LLMs have transformed the way we interact with information. They transformed the way we think and design automations. In short, they have…May 27May 27
Sascha GstirinPondhouse DataHow to use AI to create a PowerPoint presentation?LLMs have been tremendously successful in generating text. In this post, we will show you how to use AI to create a PowerPoint presentationMay 16May 16
Sascha GstirinPondhouse DataWhat is the Google Vertex AI Agent Builder?A practical example: Google Search with Slack.May 13May 13
Sascha GstirinPondhouse DataAdvanced RAG: Increase RAG Quality with ColBERT Reranker and llamaindexFinding the right documents during retrieval is probably the most important aspect of your RAG pipeline. This guide demonstrates how to use…May 13May 13
Sascha GstirinPondhouse DataAdvanced RAG: Improving Retrieval-Augmented Generation with Hypothetical Document Embeddings (HyDE)HyDE is a technique used to improve the performance of RAG models by generating hypothetical document embeddings based on the query and…May 13May 13
Sascha GstirinPondhouse DataAdvanced RAG: Recursive Retrieval with llamaindexWith recursive retrieval, RAG can generate more coherent and contextually relevant responses. This guide introduces you to the concept of…May 13May 13