Not that good IMHO.
I asked it:
"Show me all the train yards in New York."
It only identified seven of them when there are many more:
https://en.wikipedia.org/wiki/List_of_New_York_City_Subway_y...
Then when I tried to copy and past my prompt from the history it did not display the full prompt and had no option to copy it to the clipboard.
I think it is the novelty of the idea of what an LLM can do that is important. I suppose accuracy can be improved over time. Compared to using gmaps to search places, it seems to be a bit better.
Sounds like the current zeitgeist.
Seems like it should be useful beyond demos but we aren't sure what those use cases would be. Just need to wait for AGI and then..
I have actually spent about 20 minutes now and I can't think anything worth asking the model in this context.
Awesome, I really like it, but you must add the "© OpenStreetMap Contributors" Trademark somewhere on the map. It's usually on the bottom right.
Absolutely! It's actually shown by default, OP shouldn't be turning it off.
Also, if you run out of free Mapbox credits, feel free to change the basemap to openfreemap.org (I'm the creator).
Totally, it was old internal code so I think I had it removed then. I have updated it. Changing to openfreemap.org this weekend, I love your work.
Really nice idea!
Sadly in my prompt it replies with absolutely invented data. Same prompt, three times gives 3-4 different results, that era simply not true.
Prompt: show me the best glass factories in valsassina, italy. (there are no glass factories, so it suggest glass worker that contains wrong coordinates and invented names)
What are your api costs from publicly serving this if you don’t mind sharing (especially from HN traffic)?
I have some ideas I’d like to release, but LLM api pricing and sudden traffic from sites like this one seem scary.
Prerecord video demos of it, and have your site swap out the live demo with the pre-recorded videos after $x amount of money has been spent by visitors.
Not too bad, I had some gas in the tank from an old project sitting on my API account so it used up all of it. Expect in the few hundred dollars.
I'm considering switching to DeepSeek since it's way cheaper. I'll swap once I'm done testing out the API. You can use your own hosted LLM but it's not worth it at this moment.
Woah, a few hundred just to demo the thing. How could you keep this afloat?
That’s the tricky part about building LLM apps. I’d love to hear more from Indie devs because money is absolutely a bottle neck here.
For fun:
You don’t need an LLM for some of your calls I think. “Where is the Eiffel Tower”, Eiffel Tower is a NER that small NLP libraries can extract. Then it’s a simple long/lat lookup. You might be able to re-route 20% of your calls to a no-cost backend call.
never had any thought on monetizing this at all so maybe offer pro features down the line? idk I'm used to just putting stuff out there for people to try out. Could be spent on worse things all things considered haha
You could use CPU inference on a smaller local model (either always or after a demo budget is spent).
Don't forget to put up a "donate" button.
That sounds like a bad idea to me.
CPU inference for LLMs takes forever (you'll get like 1tk/s on CPU) and limits you significantly in terms of model size/quality. You'll lock up all of your cores to provide service for a single user at a snail's pace.
I don't think it should even be considered as an option
llama 3.2 3b, qwen2.5 3B quantized to 4bit runs CPU inference quite fast. You can get a beefier VM and still save a ton of money. Depending on the context token length of this soluion, it's either fast or slow. If it's below 1024 tokens per request, you get around 10 sec delay, if you are at around 128 tokens I guess you would be somewhere at 1 sec for time to first token...
LLMs are notoriously terrible at spatial thinking — if you can solve that with RAG and a database of actual locations, that’s promising. Or was there another approach?
Easiest might be to cross check with some location APIs but it might get expensive. RAG can be a better long term solution though.
I asked it "show me cityname" and it did not find it. First asking for country did not help at all either.
I tried "show me Portugal" and it showed me Madeira, which is an island that is indeed part of Portugal, but I was expecting it to go for the mainland.
Repeating the prompt alternates between Madeira and Açores which is again, technically correct, but in this case not the best kind of correct.
I asked it to find me soccer fields in <insert my suburb> and it showed me results but all 5 of them were misplaced. One of the fields was shown where a train station is, there are no parks nearby.
Same for my question of bars in Thessaloniki, it found 5 in the whole city and the locations were off by km. I fear that we're missing the point, though, because the good bit here isn't "it can do what Google Maps can do", but we aren't asking the right questions to show that off.
Really cool idea and fast response times, nice job! I noticed after a few searches the results seem to get less accurate, however. Pins dropping in the ocean, etc.
Thanks! I might have to hard reset the context on each request. Noticed it too.
It seems you can make it hang if you input something that triggers the LLM's guardrails. For example, I entered 'where they sell drugs,' and the API endpoint hung every time I submitted it. However, on a few occasions, it returned a response immediately (with an error in the API response). I suspect there are too many retries if the structured JSON output is not formatted correctly when the guardrails are activated
Nice job. . . I looked for kite boarding spots in Puerto Rico and everything showed up. I really like the clean UI too.
This is kinda neat and far more intuitive than using google maps search. Although I wonder how accurate it is with the data points.
aaaand I broke it. It is now hallucinating phantom locations.
After two queries it became completely dysfunctional.
This has some meme potential, it succeeded at "show me the OpenAI data centers"
No way haha I was actually slightly concerned when I published it might have some OPSEC issues for some categories.
This is really cool! Though for some reason the lat/long coordinates of places are completely off, despite the addresses being correct.
I searched "show me 5 parks in SF", and all 5 were in the wrong spot. For example:
Lafayette Park Lafayette & Gough St, San Francisco, CA 94109 Latitude: 37.7955 Longitutde: -122.4668
This is a really great interface! Tried "wooded hiking trails near [my address]" and got exactly what I was looking for.
Then threw in some common google maps searches and got fun results.
"airport" => LAX
"restaurant" => The Clove Club in London
"coffee shop" => Philz in SF
It doesn't seem to take into account the current map location, so I wonder how the randomness works.
That's awesome! I didn't even think about current location, I'll add it to the roadmap.
I did notice randomness too, going on a limb to say it's standard LLM randomness.
This is cool. Few suggestions:
Use local storage to save the search history.
The i icon does nothing.
Have a open external window icon next to location/landmark title that searches Google for that location
nice idea, but it fails completely for me.
e.g. "show me all IT companies in <suburb where I live>" should show my company (and only my company) - but it shows two other companies that aren't actually in the same city and draws the POI on a sugar beet field near <suburb>
Is the LLM perhaps only trained on english language geo data?
Not sure why this got nuked from the front-page all of a sudden but thanks everyone for checking it out. I'll be sure to incorporate the features mentioned here.
Don't forget the mandatory '© OpenStreetMap contributors'.
https://osmfoundation.org/wiki/Licence/Attribution_Guideline...
Does it have internet access? Looks like a very convenient interface for looking for hotels, planning travels
It does, I can certainly add it. I made it because I'm looking to open a new location for a brick and mortar business so I needed a way to look at the competitive landscape, high-level demographics etc...
It would be cool for planning travels! I'll look into it.
awesome. i can see future iterations of this becoming really useful.
e.g. "i'm traveling to Tokyo this summer, show me good areas to live in if i want to run 10k every day through nature, as well as work out of highly rated cafes.".
i want to see good areas highlighted on the map. and even better would be integrating with Airbnb / Yelp / Google business ratings, etc. to show places i can rent in those areas.
another e.g. "best times to land in XYZ city if i want to avoid traffic getting to ABC". - to check this now i have to toggle some dropdowns in Google maps. natural language is a much better "interface" for most of what i want to do with maps.
also, "Godview" reminds me of that internal map that Uber had with realtime activity. inspiration?
Just re-used a domain name, fyi "godview" is not exclusive to Uber, it's used mostly for internal tools with super-admin privileges. I'm not 100% certain if it comes from Uber originally because I remember using it internally in early 2010s before the Uber incident.
gotcha. regardless, awesome project. all the best!
doesn't work, as in, no response at all and full of console errors
This is so well done. Very interested in new UIs with LLMs. Great work.
How's it work under the hood?
thanks! very simple map + llm structured output
Any grounding with google maps or mapbox, etc?
How does it work? Translating free text to overpass? Looks very promising!
Thats a good project idea(automatic overpass query generation), I might make it over the weekend
JSON structured output lat/long pretty much. Then just plot the coordinates.
Are you on X? Would love to give a follow. I love OSM projects.
Really cool project!
It seems you are using OSM data, could you please add the proper attribution to it?
Here is a guide: https://osmfoundation.org/wiki/Licence/Attribution_Guideline...
"home of the pope" and "home of mozart" returned good results, but not "home of kant" or "home of newton".