Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
39 commits
Select commit Hold shift + click to select a range
cfd4a2c
water rights migration from elm
spodgorny9 Jan 16, 2026
0d6946c
Merge remote-tracking branch 'origin/main' into sp/tx_groundwater
ppinchuk Jan 28, 2026
8b7f29d
Bump elm version
ppinchuk Jan 29, 2026
f24ccda
Update node labels on validation graph
ppinchuk Jan 31, 2026
ab30952
Clarify docstring
ppinchuk Jan 31, 2026
7ccb77f
Add interface class
ppinchuk Jan 31, 2026
b277c6b
Use `text_kind_validator` parameter
ppinchuk Jan 31, 2026
358c2ca
Use `check_if_legal_doc` as flag
ppinchuk Jan 31, 2026
89e09c8
`_move_files` now purely moves files
ppinchuk Jan 31, 2026
db8928c
Move tech specs up a class
ppinchuk Jan 31, 2026
0684e5f
`filter_docs` now own method
ppinchuk Jan 31, 2026
5fa2b9b
Generalized `_parse_docs_for_ordinances`
ppinchuk Jan 31, 2026
6cdae48
pass in tech specs
ppinchuk Jan 31, 2026
04ac67f
permitted use extraction now optional
ppinchuk Jan 31, 2026
11c71e1
Add water rights tech specs
ppinchuk Jan 31, 2026
0d6d947
Allow custom callback for writing out data
ppinchuk Jan 31, 2026
5950eab
Allow custom callback for extracting ordinances
ppinchuk Jan 31, 2026
f16d0a1
Throw error if user does not specify model for default tasks
ppinchuk Jan 31, 2026
85d82f4
Add missing function
ppinchuk Jan 31, 2026
9cc67c0
Add missing import
ppinchuk Jan 31, 2026
51d98cd
Fix call
ppinchuk Jan 31, 2026
fc45377
Add extra fields to tech spec
ppinchuk Jan 31, 2026
ac024df
Param now optional
ppinchuk Jan 31, 2026
7b5e860
Add logger statement and remove unused function
ppinchuk Jan 31, 2026
306fcc9
Add logger statement
ppinchuk Jan 31, 2026
4b01488
Fix date bug
ppinchuk Jan 31, 2026
ecb5662
Use registry for jurisdiction data
ppinchuk Jan 31, 2026
1a301a5
Add texas GWCD
ppinchuk Jan 31, 2026
fdd1c53
Add embedding task
ppinchuk Jan 31, 2026
8dc0fa0
Add prices
ppinchuk Jan 31, 2026
85c8880
Formatting
ppinchuk Jan 31, 2026
62fa5f7
Add missing classes for water extraction
ppinchuk Jan 31, 2026
d9518c3
Minor formatting
ppinchuk Jan 31, 2026
8d4a684
Build water rights namespace
ppinchuk Jan 31, 2026
2213724
Add processing functions
ppinchuk Feb 1, 2026
feae742
Remove unused modules
ppinchuk Feb 1, 2026
1efc31b
Fix docstrings
ppinchuk Feb 1, 2026
cf149a4
Add water rights example folder
ppinchuk Feb 1, 2026
8ef4019
Lower threshold for now
ppinchuk Feb 1, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
99 changes: 99 additions & 0 deletions compass/data/tx_water_districts.csv
Original file line number Diff line number Diff line change
@@ -0,0 +1,99 @@
State,County,Subdivision,Jurisdiction Type,FIPS,Website
Texas,,Bandera County River,Authority & Groundwater District,1,
Texas,,Barton Springs/Edwards,Aquifer Conservation District,2,
Texas,,Bee,Groundwater Conservation District,3,
Texas,,Blanco Pedernales,Groundwater Conservation District,4,
Texas,,Bluebonnet,Groundwater Conservation District,5,
Texas,,Brazoria County,Groundwater Conservation District,6,
Texas,,Brazos Valley,Groundwater Conservation District,7,
Texas,,Brewster County,Groundwater Conservation District,8,
Texas,,Brush Country,Groundwater Conservation District,9,
Texas,,Calhoun County,Groundwater Conservation District,10,
Texas,,Central Texas,Groundwater Conservation District,11,
Texas,,Clear Fork,Groundwater Conservation District,12,
Texas,,Clearwater,Underground Water Conservation District,13,
Texas,,Coastal Bend,Groundwater Conservation District,14,
Texas,,Coastal Plains,Groundwater Conservation District,15,
Texas,,Coke County,Underground Water Conservation District,16,
Texas,,Colorado County,Groundwater Conservation District,17,
Texas,,Comal Trinity,Groundwater Conservation District,18,
Texas,,Corpus Christi,ASRConservation District,19,
Texas,,Cow Creek,Groundwater Conservation District,20,
Texas,,Crockett County,Groundwater Conservation District,21,
Texas,,Culberson County,Groundwater Conservation District,22,
Texas,,Duval County,Groundwater Conservation District,23,
Texas,,Evergreen,Underground Water Conservation District,24,
Texas,,Fayette County,Groundwater Conservation District,25,
Texas,,Garza County,Underground Water Conservation District,26,
Texas,,Gateway,Groundwater Conservation District,27,
Texas,,Glasscock,Groundwater Conservation District,28,
Texas,,Goliad County,Groundwater Conservation District,29,
Texas,,Gonzales County,Underground Water Conservation District,30,
Texas,,Guadalupe County,Groundwater Conservation District,31,
Texas,,Hays Trinity,Groundwater Conservation District,32,
Texas,,Headwaters,Groundwater Conservation District,33,
Texas,,Hemphill County,Underground Water Conservation District,34,
Texas,,Hickory,Underground Water Conservation District,35,
Texas,,High Plains,Underground Water Conservation District,36,
Texas,,Hill Country,Underground Water Conservation District,37,
Texas,,Hudspeth County,Underground Water Conservation District,38,
Texas,,Irion County,WConservation District,39,
Texas,,Jeff Davis,County Underground Water Conservation District,40,
Texas,,Kenedy County,Groundwater Conservation District,41,
Texas,,Kimble County,Groundwater Conservation District,42,
Texas,,Kinney County,Groundwater Conservation District,43,
Texas,,Lipan Kickapoo,WConservation District,44,
Texas,,Live Oak,Underground Water Conservation District,45,
Texas,,Llano Estacado,Underground Water Conservation District,46,
Texas,,Lone Star,Groundwater Conservation District,47,
Texas,,Lone Wolf,Groundwater Conservation District,48,
Texas,,Lost Pines,Groundwater Conservation District,49,
Texas,,Lower Trinity,Groundwater Conservation District,50,
Texas,,McMullen,Groundwater Conservation District,51,
Texas,,Medina County,Groundwater Conservation District,52,
Texas,,Menard County,UWD,53,
Texas,,Mesa,Underground Water Conservation District,54,
Texas,,Mesquite,Groundwater Conservation District,55,
Texas,,Mid East Texas,Groundwater Conservation District,56,
Texas,,Middle Pecos,Groundwater Conservation District,57,
Texas,,Middle Trinity,Groundwater Conservation District,58,
Texas,,Neches & Trinity Valleys,Groundwater Conservation District,59,
Texas,,North Plains,Groundwater Conservation District,60,
Texas,,North Texas,Groundwater Conservation District,61,
Texas,,Northern,Trinity Groundwater Conservation District,62,
Texas,,Panhandle,Groundwater Conservation District,63,
Texas,,Panola County,Groundwater Conservation District,64,
Texas,,Pecan Valley,Groundwater Conservation District,65,
Texas,,Permian Basin,Underground Water Conservation District,66,
Texas,,Pineywoods,Groundwater Conservation District,67,
Texas,,Plateau,UWC and Supply District,68,
Texas,,Plum Creek,Conservation District,69,
Texas,,Post Oak Savannah,Groundwater Conservation District,70,
Texas,,Prairielands,Groundwater Conservation District,71,
Texas,,Presidio County,Underground Water Conservation District,72,
Texas,,Real Edwards,C and R District,73,
Texas,,Red River,Groundwater Conservation District,74,
Texas,,Red Sands,Groundwater Conservation District,75,
Texas,,Reeves County,Groundwater Conservation District,76,
Texas,,Refugio,Groundwater Conservation District,77,
Texas,,Rolling Plains,Groundwater Conservation District,78,
Texas,,Rusk County,Groundwater Conservation District,79,
Texas,,San Patricio County,Groundwater Conservation District,80,
Texas,,Sandy Land,Underground Water Conservation District,81,
Texas,,Santa Rita,Underground Water Conservation District,82,
Texas,,Saratoga,Underground Water Conservation District,83,
Texas,,South Plains,Underground Water Conservation District,84,
Texas,,Southeast Texas,Groundwater Conservation District,85,
Texas,,Southern Trinity,Groundwater Conservation District,86,
Texas,,Southwestern Travis County,Groundwater Conservation District,87,
Texas,,Starr County,Groundwater Conservation District,88,
Texas,,Sterling County,Underground Water Conservation District,89,
Texas,,Sutton County,Underground Water Conservation District,90,
Texas,,Terrell County,Groundwater Conservation District,91,
Texas,,Texana,Groundwater Conservation District,92,
Texas,,Trinity Glen Rose,Groundwater Conservation District,93,
Texas,,Upper Trinity,Groundwater Conservation District,94,
Texas,,Uvalde County,Underground Water Conservation District,95,
Texas,,Victoria County,Groundwater Conservation District,96,
Texas,,Wes Tex,Groundwater Conservation District,97,
Texas,,Wintergarden,Groundwater Conservation District,98,
6 changes: 3 additions & 3 deletions compass/extraction/apply.py
Original file line number Diff line number Diff line change
Expand Up @@ -82,15 +82,15 @@ async def check_for_ordinance_info(
chunks = model_config.text_splitter.split_text(doc.text)
chunk_parser = ParseChunksWithMemory(chunks, num_to_recall=2)
legal_text_validator = (
None
if doc.attrs.get("is_legal_doc", False)
else LegalTextValidator(
LegalTextValidator(
tech=tech,
llm_service=model_config.llm_service,
usage_tracker=usage_tracker,
doc_is_from_ocr=doc.attrs.get("from_ocr", False),
**model_config.llm_call_kwargs,
)
if doc.attrs.get("check_if_legal_doc", True)
else None
)

ordinance_text_collector = ordinance_text_collector_class(
Expand Down
48 changes: 48 additions & 0 deletions compass/extraction/water/__init__.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
"""Water ordinance extraction utilities"""

from .parse import StructuredWaterParser
from .ordinance import (
WaterRightsHeuristic,
WaterRightsTextCollector,
WaterRightsTextExtractor,
)
from .processing import (
build_corpus,
extract_water_rights_ordinance_values,
label_docs_no_legal_check,
write_water_rights_data_to_disk,
)


WATER_RIGHTS_QUESTION_TEMPLATES = [
"{jurisdiction} rules",
"{jurisdiction} management plan",
"{jurisdiction} well permits",
"{jurisdiction} well permit requirements",
"requirements to drill a water well in {jurisdiction}",
]

BEST_WATER_RIGHTS_ORDINANCE_WEBSITE_URL_KEYWORDS = {
"pdf": 92160,
"water": 46080,
"rights": 23040,
"zoning": 11520,
"ordinance": 5760,
r"renewable%20energy": 1440,
r"renewable+energy": 1440,
"renewable energy": 1440,
"planning": 720,
"plan": 360,
"government": 180,
"code": 60,
"area": 60,
r"land%20development": 15,
r"land+development": 15,
"land development": 15,
"land": 3,
"environment": 3,
"energy": 3,
"renewable": 3,
"municipal": 1,
"department": 1,
}
Loading