Generative AI

Explore the world of Generative AI, focusing on building AI systems that create new content. Learn about the latest trends in Generative AI, including language models, image generation, and music composition. Find practical guides, case studies, and best practices for building Generative AI systems that can generate new content. Ideal for developers, data scientists, and teams working on AI applications that require creative content generation

More Articles

Document Extraction with GPT-4o: Parse PDF, Word and Excel Files

Document Extraction with GPT-4o: Parse PDF, Word and Excel Files

Parse PDF, Word and Excel files with GPT-4o vision: render each page as an image, extract the text in Python, for about 0.32 to 0.62 cents per page.

2024-08-15
9 min read
Read Post
Fine-tune OpenAI's GPT-4o mini LLM AI model

Fine-tune OpenAI's GPT-4o mini LLM AI model

Fine-tune GPT-4o mini in the OpenAI dashboard: the JSONL training format, how many examples you need, job settings, costs and calling the model from Python.

2024-07-25
8 min read
Read Post
Neo4j LLM Knowledge Graph Builder: How to Create Knowledge Graphs for RAG

Neo4j LLM Knowledge Graph Builder: How to Create Knowledge Graphs for RAG

Set up the Neo4j LLM Knowledge Graph Builder on AuraDB or Docker, turn a web page into a knowledge graph and query it with GraphRAG in the built-in chat.

2024-07-19
10 min read
Read Post
KAN: Is this the end of feedforward networks?

KAN: Is this the end of feedforward networks?

How Kolmogorov-Arnold Networks (KANs) replace MLP weights with learnable splines, what the paper shows on accuracy, and why MLPs aren't done yet.

2024-05-28
9 min read
Read Post
How to use AI to create a PowerPoint presentation?

How to use AI to create a PowerPoint presentation?

Let GPT-4 write python-pptx code that builds a PowerPoint deck from your company documents via RAG, using your own corporate template.

2024-05-15
7 min read
Read Post
BitNet: LLM Quantization at its Extreme

BitNet: LLM Quantization at its Extreme

How Microsoft's BitNet trains LLMs with 1-bit and ternary weights, why it beats post-training quantization, and what it saves in memory and energy.

2024-05-01
10 min read
Read Post
GenAI: Technological Masterpiece or Ecological Disaster?

GenAI: Technological Masterpiece or Ecological Disaster?

GenAI's energy use is growing fast. The IEA and de Vries numbers, plus the techniques that cut it: TPUs, MoE, distillation, MoD, layer pruning and BitNet.

2024-04-19
16 min read
Read Post