The goal of this exercise is to extract information about the Berlin metro system from Wikidata and to analyze its relationships with Neo4j.
| @interface Base58Encoder : NSObject { | |
| } | |
| + (NSString *)base58EncodedValue:(long long)num; | |
| @end |
| var z="http://gist.github.com/",y=document.write,x=$("body"),w=$("p.gist").map(function(b,a){a=$(a);var c=$("a",a),u=c.attr("href");if(c.length&&u.indexOf(z)==0)return{p:a,id:u.substring(z.length)}}).get(),v=function(){if(w.length==0)document.write=y;else{var b=w.shift();document.write=function(){document.write=function(a){b.p.replaceWith(a);v()}};x.append('<scr'+'ipt src="'+z+b.id+'.js"></scr'+'ipt>')}};v(); |
| #------------ bootstrap the cluster nodes -------------------- | |
| redis_image='redis:5' | |
| network_name='host' # must be in host mode | |
| #---------- create the cluster ------------------------ | |
| for port in `seq 6379 6384`; do \ | |
| start_cmd="redis-server --port $port --cluster-enabled yes --cluster-config-file nodes.conf --cluster-node-timeout 5000 --appendonly yes" | |
| docker run -d --name "redis-"$port -p $port:6379 --net $network_name $redis_image $start_cmd; |
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.