feat: add 'urban_centres' dataset for better city coverage and add population ranking

Find cities Overture has only as a point, and rank the largest first

Merge pull request #13 from developmentseed/feature/fuzzy-localities-and-alternate-names

Break ranking ties by id, so results come back in the same order

Match every name a place has, without case or accents

Read Overture's own bbox rather than computing it from the geometry

Let fuzzy search find cities, and keep them from the model

Merge pull request #11 from developmentseed/fix/match-english-names

Tell the API it is mounted under /api

Serve the installed version, and bump it to 0.2.0

Build the fixture rows with format specifiers, not percent format

Match places on their English name as well as their own

Merge pull request #9 from developmentseed/feature/expose-api-hf-deployment

Expose the API alongside the Streamlit demo in the HF Space via nginx

Merge pull request #8 from developmentseed/feature/unify-search-api

Unify /search and /search/fuzzy under a mode param; add OpenAPI response models

Merge pull request #7 from developmentseed/feature/fuzzy-search-endpoint

fix: point NATURAL_EARTH_PATH to test_ne_geography.parquet tracked in git

fix: use module-scoped con fixture to avoid repeated LOAD spatial overhead

Add minimal parquet fixture data for CI tests

Add ruff.toml and fix lint errors (imports, type hints, formatting)

Fix ruff formatting across all source and test files

Drop 3.14 from CI test matrix

Add mypy type checking to CI and fix type errors

add unit tests and CI workflow

Fix lint: remove unused math import, move imports before constants in sql.py

Add GET /sources endpoint

Optimize to_feature_collection to use to_dict(orient=records)

Unify /search/fuzzy response shape for ids_only mode

Fix _per_source_limit to floor at 3 candidates for complex queries

Add optional country and subtype to Place schema

Add request ID middleware and request logging

Add GET /health endpoint

Consolidate schema definition into config.SCHEMA_INFO

Unify geometry normalization and kill per-row DuckDB connections in export.py

Replace print() with logging in sql.py and search.py

Remove dead COUNTRIES and SUBTYPES literals from schemas.py

Add subtype to /search/fuzzy ids_only responses

Fix fuzzy-match ranking and broaden divisions_area coverage

Include name and bbox in /search/fuzzy ids_only responses

Add pure fuzzy-search and by-ID geometry endpoints, decoupled from the LLM path

Update README.md

Add update plausible link

Add gazet.ds.io to streamlit ui

streamlit: add powered by Modal

Merge pull request #6 from developmentseed/improve-data-quality

hf: update deploy docs

hf: update Dockerfile & supervisord to point to q8_0.gguf model

docs: update modal docs to serve q8 instead of q4

finetune: update the params to run experiment on H200