- db/Dockerfile: postgis:16-3.4 + postgresql-16-pgvector (works around the
EOL bullseye release files: disable Check-Valid-Until, add pgdg repo)
- 20-vector.sql: CREATE EXTENSION vector on first boot
- embed/main.go (embedpoi): build poi_vec from poi — zembed embeddings of
'name — kind' (2560-d), resumable, HNSW cosine index at the end
- main.go: /semantic endpoint (embeds q with the local model, cosine <=>
over poi_vec, returns lat/lng/score); add lat/lng to /near /nearest
/corridor so the UI can pin results; bind the vector as a text literal
+ ::vector cast (lib/pq has no []float32 codec)
- mock/app.js: poi_semantic tool + poi_near now returns coords; agent loop
drops poi_near/poi_semantic results as map pins (showSpatialPins)
- mock/styles.css: .sp-dot / .sp-card pin + popup styles
- README: document the pgvector stack + embedpoi
Ran the full stack (docker now available via sg docker):
- postgis/postgis:16-3.4 up, both extracts imported:
northeast 291,000 POIs (from ~/osm-build/data/northeast.osm.pbf),
colombia 228,446 POIs
- spatiald live on :5005, proxied by the mock server (/spatial/*,
/spatial-status); UI badge + poi_near tool activate automatically
Fixes discovered by running against real data:
- osm2pgsql image: osm2pgsql/osm2pgsql does not exist on Docker Hub —
use iboates/osm2pgsql, bypass its DB-probing entrypoint (--entrypoint
osm2pgsql), password via PGPASSWORD (this build's --password flag
forces an interactive prompt)
- osm2pgsql 2.x schema: planet_osm_point/_polygon (not _node/_way),
geometry in EPSG:3857 'way' column, -k hstore for opening_hours/
fee/website/addr:*, refresh_poi() dedupes relation polygons and
uses hstore -> (not ->>)
- compose file downgraded to v1-compatible 3.8 (host has docker-compose
1.29, no v2 plugin); OSM_DIR exported by import.sh
- spatiald: proper SQL parameterization (@@i@@ tokens, body ..
shifted past the filter args — the first renumber attempt was
unsound), ST_Distance(geography) instead of the geometry-only
ST_Distance_Sphere, 4-arg ST_DWithin for the corridor band, WKT in
lng lat order, kind= accepts exact (amenity=restaurant), bare tag
value (restaurant) or family (tourism)
- mock server /spatial proxy: forward u.search (was dropping it)
- app.js poi_near: 'points' param, semicolons must be %3B-encoded
(Go url.Parse drops the tail of a value containing a raw ';')
- README: osm2pgsql 2.x data notes + kind semantics
The dev directory now holds source code + compiled binaries only:
~/trips/osm/ OSM PBF extracts (was osm/, 1.4 GB)
~/trips/tilecache/ mock tile cache (was mock/.tilecache)
~/trips/store/mock/ per-trip uploads + chat logs (was mock/store, PII)
~/trips/logs/ server.log
~/trips/stale-osm-build/ stale source/tarball dup of ~/osm-build
(repo osm/build had no binaries; the live OSRM
toolchain + graphs already lived in ~/osm-build)
Code now points at the new locations, all overridable via env:
- mock/server.js: TRIPS_HOME (default ~/trips) for tile cache + store
- setup-osrm.sh / setup-osrm-colombia.sh: OSM_DIR (default ~/trips/osm)
- spatial/compose+import.sh: OSM_DIR (default ~/trips/osm)
- .gitignore: rewritten — no artifact paths remain in-tree
Milestone 1 — live web search:
- mock/server.js: /search + /search-status proxy to the self-hosted
SearXNG (third leg of the 3-source blend; engine endpoint stays
server-side), /spatial + /spatial-status proxy to the spatial service
- mock/app.js: background enrichment of suggestion cards — each
candidate gets a web element (discovery cards + "you might like"
rows) that is checked via SearXNG in the background (one in-flight
query per place, 1 h TTL, failures retry in ~5 min) and APPENDS
sourced facts with provenance URLs; never reorders/rewrites the plan.
New LLM tools: web_search (cite URLs) and poi_near (PostGIS). Status
badge gains 'web' / 'spatial'.
- styles.css: .cc-web live-facts blocks, t-web verified chip
Milestone 2 — PostGIS spatial DB (code complete; needs docker access
to run — see spatial/README.md):
- spatial/: docker-compose (postgis/postgis:16-3.4 + osm2pgsql:16
one-shot importer + spatiald), schema.sql (poi table w/ GIST index,
spatial_extract bookkeeping, refresh_poi()), import.sh for the PBF
extracts in ../osm, spatiald (Go, lib/pq): /health, /near
(ST_DWithin), /nearest (KNN), /corridor (ST_Buffer along a route),
with kind/name/extract/limit filters
