53 karma · joined October 30, 2024
Wasm size from 30Mb to 300kb and 1.5x speedup. It's definitely worth it for performance or distribution size.
Why bring server software to edge devices? Because its fucking awesome!
How do you extract and relate to each other the facts from the documents that require comprehension and not simple similarity matching using common embeddings models?
Recently started some agentic features for paid version, and this lead to a side project https://eatmydata.ai - a question-to-sql-to-dashboard builder, where data doesn't get exposed to AI (with bundled in-browser SQLite vector search, NER and many other features).
The latter is open-sourced under MIT: https://github.com/eatmydata-org/eatmydata
We have low-cardinality data and yes this is safe to share and required to build an actual query.
Then we have high-cardinality and possibly PII - there’s absolutely no reason to share that data, there’s nothing for LLM to analyse there. Also semantic index (vector search) will find relevant records much faster and more accurately that any chain-of-thoughts just with an LLM-authored search fn call.
Further there are continuous numerical values and there’s not much LLM needs to see in there either. We can say, for example, if you look at data distributions when building your analysis, it can drive your analysis logic, but another point of view here is taht it creates unnecessary bias instead.
For example, there is no way neither in Claude nor in ChatGPT to run your own WASM or JS or whatever AI produces directly in user's browser context as a tool/skill - there is no call site for that. The only option is remote server-side.
My whole idea was that AI can perfectly write SQL and dashboard code knowing only the shape of your data and not it's contents. With direct upload to vendor now we're forced to share the contents.
For example, MIT-licensed sqlite vector search extension.
Overall, I have a orchestrator - sql coder - js coder - dashboards, all without backend, running locally in the browser. It's mostly tested on small analysis and question answering with Gemini Flash Lite, and the overall target was speed from question to answer, including data sharing and waiting.
For the "show me how many people are from Dallas" in AdventureWorks, it really depends on the model.
With `gemini-3.1-flash-lite` for all agents it produces this sql from the first try for $0.0033: ``` SELECT COUNT(DISTINCT ca.CustomerID) as customer_count FROM CustomerAddress ca JOIN ( SELECT a.AddressID FROM vector_search('Address', 'City', 'Dallas', 20) vs JOIN Address a ON a.rowid = vs.rowid WHERE a.City = 'Dallas' ) addr ON ca.AddressID = addr.AddressID ```
and then formats output in Markdown.
I'll bake some default model in later, and more examples. And I guess it needs some default token quota.
Multi-threaded WebAssembly in action for route optimization, all bundled with geocoding, OSM maps and routing, and provided world-wide.
We're adding driver's PWA, saving and sharing of route optimization projects, editing of optimized routes, sharing it with others either for execution or for approval, integrations and AI-assisted data imports, auth flows, support prompts, sales automation and all that boring stuff.
It's been approx. an year since we are up and running, and we helped 100+ businesses in the US and world-wide to understand the value and savings of automated route planning, and prepared tens thousands of optimized routes for companies operating from 1 to 50 vehicles. All this keeping our operational expenses low and flat, thanks to our local-first route optimization engine working in the browser, and reliance on OpenStreetMap.
Let's start it with index of whole Spain, 2.4gb download, 4gb on disk: https://gist.github.com/dkourilov/e243270684b5973f1fac005c78...
I'd say it's pretty usable to run a EU-sized country or several US states on any commodity PC. For embedded devices, it really depends what is the device. On Raspberry PI it should be fine for batch geocoding, realtime (typeahead) will definitely be lagging.
You can balance traffic to external networks or clouds with it too.
DJ_Dave live events are the best illustration for all of it. If you love electronic music, ever touched any generative art, and know basic coding this is for you.
Routing24 builds and provides professional route optimization tools to SMBs for free.
We are seeking a part-time consultant and advisor with extensive experience deploying commercial route optimization and TMS/DMS products in real-world business environments.
We offer hourly or per-project rates. To apply, please email: denis@routing24.com
It's been 6 month since our first appearance on Show HN [1], and I'm working with first free users on bugs, improved workflows and UX, geocoding, solver features, future mobile app etc. etc.
We officially crossed the limits of 1500 stops per optimization with some waste collection guys, all still running fully client-side in the browser.
You're right, I must've been living in Germany long enough to have it imprinted in my subconscious :)