Linked below are our posts about local knowledge bases and RAG (Retrieval Augmented Generation) processing published on this site during 2024 and 2025. The most recent post is at the top of the list.

The posts are all in PDF format. Links have not been preserved.

Posts published in 2025

29-Using AI assistants to summarize and generate content
28-Using AI assistants to generate an astronomy website
27-Human/AI collaborative projects
26-Updating community information using an AI-powered workflow
25-Resizing images using the Python Pillow library
24-DITA-based structured information collections
23-Captioning images with a small language model
22-Revisiting AI art
21-Summarizing text
20-Generating AI art with Canva and Perplexity
19-Transitioning from Python pipelines to AI assistants (part 2)
18-Transitioning from Python pipelines to AI assistants (part 1)
17-Generating content derived from multiple sources
16-Using LLaVA for multimodal processing
15-Setting up knowledge bases for prototyping
14-Computer history content
13-Returning to large language models and Colab notebooks
12-Setting up RAG processing projects

Posts published in 2024

11-Using a small language model with chat and a system prompt
10-Using a small language model with chat
9-Using a small language model with a single query
8-Establishing groundrules for content generation
7-Establishing a RAG prototyping environment
6-Getting to “ground-truth” with RAG processing
5-Updating down-level content
4-Comparing the effectiveness of DITA output types
3-Generating new content with oXygen’s Positron
2-Building bot-ready knowledge bases
1-The role of local knowledge bases in RAG processing