A8072846/luma
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

wip chat

Browse Source
This commit is contained in:
Anibal Angulo
2025-11-07 09:41:18 -06:00
parent cafe0bf5f3
commit af9b5fed01
21 changed files with 3065 additions and 266 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
backend/app/agents/form_auditor/__init__.py Normal file
View File

@@ -0,0 +1,39 @@
from __future__ import annotations
from typing import Any
from .agent import agent, prepare_initial_findings
from .models import (
AuditReport,
ExtractedIrsForm990PfDataSchema,
ValidatorState,
)
async def build_audit_report(payload: dict[str, Any]) -> AuditReport:
extraction_payload = payload.get("extraction")
if extraction_payload is None:
raise ValueError("Payload missing 'extraction' key.")
extraction = ExtractedIrsForm990PfDataSchema.model_validate(extraction_payload)
initial_findings = prepare_initial_findings(extraction)
metadata: dict[str, Any] = {}
metadata_raw = payload.get("metadata")
if isinstance(metadata_raw, dict):
metadata = {str(k): v for k, v in metadata_raw.items()}
state = ValidatorState(
extraction=extraction,
initial_findings=initial_findings,
metadata=metadata,
)
prompt = (
"Review the Form 990 extraction and deterministic checks. Validate or adjust "
"the findings, add any additional issues or mitigations, and craft narrative "
"section summaries that highlight the most material points. Focus on concrete "
"evidence; do not fabricate figures."
)
result = await agent.run(prompt, deps=state)
return result.output

155
backend/app/agents/form_auditor/agent.py Normal file
View File

@@ -0,0 +1,155 @@
from __future__ import annotations
from collections.abc import Iterable
from pydantic_ai import Agent, RunContext
from pydantic_ai.models.openai import OpenAIChatModel
from pydantic_ai.providers.azure import AzureProvider
from app.core.config import settings
from .checks import (
aggregate_findings,
build_section_summaries,
check_balance_sheet_presence,
check_board_engagement,
check_expense_totals,
check_fundraising_alignment,
check_governance_policies,
check_missing_operational_details,
check_revenue_totals,
compose_overall_summary,
irs_ein_lookup,
)
from .models import (
AuditFinding,
AuditReport,
ExtractedIrsForm990PfDataSchema,
Severity,
ValidatorState,
)
provider = AzureProvider(
azure_endpoint=settings.AZURE_OPENAI_ENDPOINT,
api_version=settings.AZURE_OPENAI_API_VERSION,
api_key=settings.AZURE_OPENAI_API_KEY,
)
model = OpenAIChatModel(model_name="gpt-4o", provider=provider)
agent = Agent(model=model)
def prepare_initial_findings(
extraction: ExtractedIrsForm990PfDataSchema,
) -> list[AuditFinding]:
findings = [
check_revenue_totals(extraction),
check_expense_totals(extraction),
check_fundraising_alignment(extraction),
check_balance_sheet_presence(extraction),
check_board_engagement(extraction),
check_missing_operational_details(extraction),
]
findings.extend(check_governance_policies(extraction))
return findings
def _merge_findings(
findings: Iterable[AuditFinding],
added: Iterable[AuditFinding],
) -> list[AuditFinding]:
existing = {finding.check_id: finding for finding in findings}
for finding in added:
existing[finding.check_id] = finding
return list(existing.values())
agent = Agent(
model=model,
name="FormValidator",
deps_type=ValidatorState,
output_type=AuditReport,
system_prompt=(
"You are a Form 990 auditor. Review the extraction data and deterministic "
"checks provided in deps. Use tools to confirm calculations, add or adjust "
"findings, supply mitigation guidance, and craft concise section summaries. "
"The AuditReport must include severity (`Pass`, `Warning`, `Error`), "
"confidence scores, mitigation advice, section summaries, and an overall summary. "
"Ground every statement in supplied data; do not invent financial figures."
),
)
@agent.tool
def revenue_check(ctx: RunContext[ValidatorState]) -> AuditFinding:
return check_revenue_totals(ctx.deps.extraction)
@agent.tool
def expense_check(ctx: RunContext[ValidatorState]) -> AuditFinding:
return check_expense_totals(ctx.deps.extraction)
@agent.tool
def fundraising_alignment_check(ctx: RunContext[ValidatorState]) -> AuditFinding:
return check_fundraising_alignment(ctx.deps.extraction)
@agent.tool
async def verify_ein(ctx: RunContext[ValidatorState]) -> AuditFinding:
ein = ctx.deps.extraction.core_organization_metadata.ein
exists, confidence, note = await irs_ein_lookup(ein)
if exists:
return AuditFinding(
check_id="irs_ein_match",
category="Compliance",
severity=Severity.PASS,
message="EIN confirmed against IRS index.",
mitigation="Document verification in the filing workpapers.",
confidence=confidence,
)
return AuditFinding(
check_id="irs_ein_match",
category="Compliance",
severity=Severity.WARNING,
message=f"EIN {ein} could not be confirmed. {note}",
mitigation="Verify the EIN against the IRS EO BMF or IRS determination letter.",
confidence=confidence,
)
@agent.output_validator
def finalize_report(
ctx: RunContext[ValidatorState],
report: AuditReport,
) -> AuditReport:
merged_findings = _merge_findings(ctx.deps.initial_findings, report.findings)
overall = aggregate_findings(merged_findings)
sections = build_section_summaries(merged_findings)
overall_summary = compose_overall_summary(merged_findings)
metadata = ctx.deps.metadata
notes = report.notes
if notes is None and isinstance(metadata, dict) and metadata.get("source"):
notes = f"Reviewed data source: {metadata['source']}."
year: int | None = None
if isinstance(metadata, dict):
metadata_year = metadata.get("return_year")
if metadata_year is not None:
try:
year = int(metadata_year)
except (TypeError, ValueError):
pass
core = ctx.deps.extraction.core_organization_metadata
organisation_name = core.legal_name or report.organisation_name
organisation_ein = core.ein or report.organisation_ein
return report.model_copy(
update={
"organisation_ein": organisation_ein,
"organisation_name": organisation_name,
"year": year,
"findings": merged_findings,
"overall_severity": overall,
"sections": sections,
"overall_summary": overall_summary,
"notes": notes,
}
)

282
backend/app/agents/form_auditor/checks.py Normal file
View File

@@ -0,0 +1,282 @@
from __future__ import annotations
from collections import Counter, defaultdict
from .models import (
AuditFinding,
AuditSectionSummary,
ExtractedIrsForm990PfDataSchema,
Severity,
)
def aggregate_findings(findings: list[AuditFinding]) -> Severity:
order = {Severity.ERROR: 3, Severity.WARNING: 2, Severity.PASS: 1}
overall = Severity.PASS
for finding in findings:
if order[finding.severity] > order[overall]:
overall = finding.severity
return overall
def check_revenue_totals(data: ExtractedIrsForm990PfDataSchema) -> AuditFinding:
subtotal = sum(
value
for key, value in data.revenue_breakdown.model_dump().items()
if key != "total_revenue"
)
if abs(subtotal - data.revenue_breakdown.total_revenue) <= 1:
return AuditFinding(
check_id="revenue_totals",
category="Revenue",
severity=Severity.PASS,
message=f"Revenue categories sum (${subtotal:,.2f}) matches total revenue.",
mitigation="Maintain detailed support for each revenue source to preserve reconciliation trail.",
confidence=0.95,
)
return AuditFinding(
check_id="revenue_totals",
category="Revenue",
severity=Severity.ERROR,
message=(
f"Revenue categories sum (${subtotal:,.2f}) does not equal reported total "
f"(${data.revenue_breakdown.total_revenue:,.2f})."
),
mitigation="Recalculate revenue totals and correct line items or Schedule A before filing.",
confidence=0.95,
)
def check_expense_totals(data: ExtractedIrsForm990PfDataSchema) -> AuditFinding:
subtotal = (
data.expenses_breakdown.program_services_expenses
+ data.expenses_breakdown.management_general_expenses
+ data.expenses_breakdown.fundraising_expenses
)
if abs(subtotal - data.expenses_breakdown.total_expenses) <= 1:
return AuditFinding(
check_id="expense_totals",
category="Expenses",
severity=Severity.PASS,
message="Functional expenses match total expenses.",
mitigation="Keep functional allocation workpapers to support the reconciliation.",
confidence=0.95,
)
return AuditFinding(
check_id="expense_totals",
category="Expenses",
severity=Severity.ERROR,
message=(
f"Functional expenses (${subtotal:,.2f}) do not reconcile to total expenses "
f"(${data.expenses_breakdown.total_expenses:,.2f})."
),
mitigation="Review Part I, lines 23–27 and reclassify functional expenses to tie to Part II totals.",
confidence=0.95,
)
def check_fundraising_alignment(
data: ExtractedIrsForm990PfDataSchema,
) -> AuditFinding:
reported_fundraising = data.expenses_breakdown.fundraising_expenses
event_expenses = data.fundraising_grantmaking.total_fundraising_event_expenses
difference = abs(reported_fundraising - event_expenses)
if difference <= 1:
return AuditFinding(
check_id="fundraising_alignment",
category="Fundraising",
severity=Severity.PASS,
message="Fundraising functional expenses align with reported event expenses.",
mitigation="Retain event ledgers and allocations to support matching totals.",
confidence=0.9,
)
severity = (
Severity.WARNING
if reported_fundraising and difference <= reported_fundraising * 0.1
else Severity.ERROR
)
return AuditFinding(
check_id="fundraising_alignment",
category="Fundraising",
severity=severity,
message=(
f"Fundraising functional expenses (${reported_fundraising:,.2f}) differ from "
f"reported event expenses (${event_expenses:,.2f}) by ${difference:,.2f}."
),
mitigation="Reconcile Schedule G and Part I allocations to eliminate the variance.",
confidence=0.85,
)
def check_balance_sheet_presence(
data: ExtractedIrsForm990PfDataSchema,
) -> AuditFinding:
if data.balance_sheet:
return AuditFinding(
check_id="balance_sheet_present",
category="Balance Sheet",
severity=Severity.PASS,
message="Balance sheet data is present.",
mitigation="Ensure ending net assets tie to Part I, line 30.",
confidence=0.7,
)
return AuditFinding(
check_id="balance_sheet_absent",
category="Balance Sheet",
severity=Severity.WARNING,
message="Balance sheet section is empty; confirm Part II filing requirements.",
mitigation="Populate assets, liabilities, and net assets or attach supporting schedules.",
confidence=0.6,
)
def check_governance_policies(
data: ExtractedIrsForm990PfDataSchema,
) -> list[AuditFinding]:
gm = data.governance_management_disclosure
findings: list[AuditFinding] = []
policy_fields = {
"conflict_of_interest_policy": "Document the policy in Part VI or adopt one prior to filing.",
"whistleblower_policy": "Document whistleblower protections for staff and volunteers.",
"document_retention_policy": "Adopt and document a record retention policy.",
}
affirmative_fields = {
"financial_statements_reviewed": "Capture whether the board reviewed or audited year-end financials.",
"form_990_provided_to_governing_body": "Provide Form 990 to the board before submission and note the date of review.",
}
for field, mitigation in policy_fields.items():
value = (getattr(gm, field) or "").strip()
if not value or value.lower() in {"no", "n", "false"}:
findings.append(
AuditFinding(
check_id=f"{field}_missing",
category="Governance",
severity=Severity.WARNING,
message=f"{field.replace('_', ' ').title()} not reported or marked 'No'.",
mitigation=mitigation,
confidence=0.55,
)
)
for field, mitigation in affirmative_fields.items():
value = (getattr(gm, field) or "").strip()
if not value:
findings.append(
AuditFinding(
check_id=f"{field}_blank",
category="Governance",
severity=Severity.WARNING,
message=f"{field.replace('_', ' ').title()} left blank.",
mitigation=mitigation,
confidence=0.5,
)
)
return findings
def check_board_engagement(data: ExtractedIrsForm990PfDataSchema) -> AuditFinding:
hours = [
member.average_hours_per_week
for member in data.officers_directors_trustees_key_employees
if member.average_hours_per_week is not None
]
total_hours = sum(hours)
if total_hours >= 5:
return AuditFinding(
check_id="board_hours",
category="Governance",
severity=Severity.PASS,
message="Officer and director time commitments appear reasonable.",
mitigation="Continue documenting board attendance and oversight responsibilities.",
confidence=0.7,
)
return AuditFinding(
check_id="board_hours",
category="Governance",
severity=Severity.WARNING,
message=(
f"Aggregate reported board hours ({total_hours:.1f} per week) are low; "
"confirm entries reflect actual governance involvement."
),
mitigation="Verify hours in Part VII; update if officers volunteer significant time.",
confidence=0.6,
)
def check_missing_operational_details(
data: ExtractedIrsForm990PfDataSchema,
) -> AuditFinding:
descriptors = (
data.functional_operational_data.fundraising_method_descriptions or ""
).strip()
if descriptors:
return AuditFinding(
check_id="fundraising_methods_documented",
category="Operations",
severity=Severity.PASS,
message="Fundraising method descriptions provided.",
mitigation="Update narratives annually to reflect any new campaigns or joint ventures.",
confidence=0.65,
)
return AuditFinding(
check_id="fundraising_methods_missing",
category="Operations",
severity=Severity.WARNING,
message="Fundraising method descriptions are blank.",
mitigation="Add a brief Schedule G narrative describing major fundraising approaches.",
confidence=0.55,
)
def build_section_summaries(findings: list[AuditFinding]) -> list[AuditSectionSummary]:
grouped: defaultdict[str, list[AuditFinding]] = defaultdict(list)
for finding in findings:
grouped[finding.category].append(finding)
summaries: list[AuditSectionSummary] = []
severity_order = {Severity.ERROR: 3, Severity.WARNING: 2, Severity.PASS: 1}
for category, category_findings in grouped.items():
counter = Counter(f.severity for f in category_findings)
severity = aggregate_findings(category_findings)
summary = ", ".join(
f"{count} {label}"
for label, count in (
("passes", counter.get(Severity.PASS, 0)),
("warnings", counter.get(Severity.WARNING, 0)),
("errors", counter.get(Severity.ERROR, 0)),
)
)
summary_text = f"{category} review: {summary}."
confidence = sum(f.confidence for f in category_findings) / len(
category_findings
)
summaries.append(
AuditSectionSummary(
section=category,
severity=severity,
summary=summary_text,
confidence=confidence,
)
)
summaries.sort(key=lambda s: (-severity_order[s.severity], s.section.lower()))
return summaries
def compose_overall_summary(findings: list[AuditFinding]) -> str:
if not findings:
return "No automated findings generated."
counter = Counter(f.severity for f in findings)
parts = []
if counter.get(Severity.ERROR):
parts.append(f"{counter[Severity.ERROR]} error(s)")
if counter.get(Severity.WARNING):
parts.append(f"{counter[Severity.WARNING]} warning(s)")
if counter.get(Severity.PASS):
parts.append(f"{counter[Severity.PASS]} check(s) passed")
summary = "Overall results: " + ", ".join(parts) + "."
return summary
async def irs_ein_lookup(_ein: str) -> tuple[bool, float, str]:
return False, 0.2, "IRS verification unavailable in current environment."

38
backend/app/agents/form_auditor/cli.py Normal file
View File

@@ -0,0 +1,38 @@
from __future__ import annotations
import argparse
import asyncio
import json
from pathlib import Path
from . import build_audit_report
__all__ = ["build_audit_report", "main"]
def _load_payload(path: Path) -> dict:
text = path.read_text(encoding="utf-8")
return json.loads(text)
def _print_report(report: dict) -> None:
print(json.dumps(report, indent=2))
def main(argv: list[str] | None = None) -> None:
parser = argparse.ArgumentParser(
description="Validate a Form 990 extraction payload using the Form Auditor agent."
)
parser.add_argument(
"payload",
nargs="?",
default="example_data.json",
help="Path to a JSON file containing the extraction payload.",
)
args = parser.parse_args(argv)
payload_path = Path(args.payload).expanduser()
payload = _load_payload(payload_path)
report = asyncio.run(build_audit_report(payload))
_print_report(report.model_dump())

573
backend/app/agents/form_auditor/models.py Normal file
View File

@@ -0,0 +1,573 @@
from __future__ import annotations
from enum import Enum
from typing import Any
from pydantic import BaseModel, Field
class Severity(str, Enum):
PASS = "Pass"
WARNING = "Warning"
ERROR = "Error"
class AuditFinding(BaseModel):
check_id: str
category: str
severity: Severity
message: str
mitigation: str | None = None
confidence: float = Field(ge=0.0, le=1.0)
class AuditSectionSummary(BaseModel):
section: str
severity: Severity
summary: str
confidence: float = Field(ge=0.0, le=1.0)
class AuditReport(BaseModel):
organisation_ein: str
organisation_name: str
year: int | None
overall_severity: Severity
findings: list[AuditFinding]
sections: list[AuditSectionSummary] = Field(default_factory=list)
overall_summary: str | None = None
notes: str | None = None
class CoreOrgMetadata(BaseModel):
ein: str
legal_name: str
return_type: str
accounting_method: str
incorporation_state: str | None = None
class CoreOrganizationMetadata(BaseModel):
ein: str = Field(
...,
description="Unique IRS identifier for the organization.",
title="Employer Identification Number (EIN)",
)
legal_name: str = Field(
...,
description="Official registered name of the organization.",
title="Legal Name of Organization",
)
phone_number: str = Field(
..., description="Primary contact phone number.", title="Phone Number"
)
website_url: str = Field(
..., description="Organization's website address.", title="Website URL"
)
return_type: str = Field(
...,
description="Type of IRS return filed (e.g., 990, 990-EZ, 990-PF).",
title="Return Type",
)
amended_return: str = Field(
...,
description="Indicates if the return is amended.",
title="Amended Return Flag",
)
group_exemption_number: str = Field(
...,
description="IRS group exemption number, if applicable.",
title="Group Exemption Number",
)
subsection_code: str = Field(
...,
description="IRS subsection code (e.g., 501(c)(3)).",
title="Subsection Code",
)
ruling_date: str = Field(
...,
description="Date of IRS ruling or determination letter.",
title="Ruling/Determination Letter Date",
)
accounting_method: str = Field(
...,
description="Accounting method used (cash, accrual, other).",
title="Accounting Method",
)
organization_type: str = Field(
...,
description="Legal structure (corporation, trust, association, etc.).",
title="Organization Type",
)
year_of_formation: str = Field(
..., description="Year the organization was formed.", title="Year of Formation"
)
incorporation_state: str = Field(
..., description="State of incorporation.", title="Incorporation State"
)
class RevenueBreakdown(BaseModel):
total_revenue: float = Field(
..., description="Sum of all revenue sources.", title="Total Revenue"
)
contributions_gifts_grants: float = Field(
...,
description="Revenue from donations and grants.",
title="Contributions, Gifts, and Grants",
)
program_service_revenue: float = Field(
...,
description="Revenue from program services.",
title="Program Service Revenue",
)
membership_dues: float = Field(
..., description="Revenue from membership dues.", title="Membership Dues"
)
investment_income: float = Field(
...,
description="Revenue from interest and dividends.",
title="Investment Income",
)
gains_losses_sales_assets: float = Field(
...,
description="Net gains or losses from asset sales.",
title="Gains/Losses from Sales of Assets",
)
rental_income: float = Field(
...,
description="Income from rental of real estate or equipment.",
title="Rental Income",
)
related_organizations_revenue: float = Field(
...,
description="Revenue from related organizations.",
title="Related Organizations Revenue",
)
gaming_revenue: float = Field(
..., description="Revenue from gaming activities.", title="Gaming Revenue"
)
other_revenue: float = Field(
..., description="Miscellaneous revenue sources.", title="Other Revenue"
)
government_grants: float = Field(
...,
description="Revenue from government grants.",
title="Revenue from Government Grants",
)
foreign_contributions: float = Field(
..., description="Revenue from foreign sources.", title="Foreign Contributions"
)
class ExpensesBreakdown(BaseModel):
total_expenses: float = Field(
..., description="Sum of all expenses.", title="Total Functional Expenses"
)
program_services_expenses: float = Field(
...,
description="Expenses for program services.",
title="Program Services Expenses",
)
management_general_expenses: float = Field(
...,
description="Administrative and management expenses.",
title="Management & General Expenses",
)
fundraising_expenses: float = Field(
...,
description="Expenses for fundraising activities.",
title="Fundraising Expenses",
)
grants_us_organizations: float = Field(
...,
description="Grants and assistance to U.S. organizations.",
title="Grants to U.S. Organizations",
)
grants_us_individuals: float = Field(
...,
description="Grants and assistance to U.S. individuals.",
title="Grants to U.S. Individuals",
)
grants_foreign_organizations: float = Field(
...,
description="Grants and assistance to foreign organizations.",
title="Grants to Foreign Organizations",
)
grants_foreign_individuals: float = Field(
...,
description="Grants and assistance to foreign individuals.",
title="Grants to Foreign Individuals",
)
compensation_officers: float = Field(
...,
description="Compensation paid to officers and key employees.",
title="Compensation of Officers/Key Employees",
)
compensation_other_staff: float = Field(
...,
description="Compensation paid to other staff.",
title="Compensation of Other Staff",
)
payroll_taxes_benefits: float = Field(
...,
description="Payroll taxes and employee benefits.",
title="Payroll Taxes and Benefits",
)
professional_fees: float = Field(
...,
description="Legal, accounting, and lobbying fees.",
title="Professional Fees",
)
office_occupancy_costs: float = Field(
...,
description="Office and occupancy expenses.",
title="Office and Occupancy Costs",
)
information_technology_costs: float = Field(
..., description="IT-related expenses.", title="Information Technology Costs"
)
travel_conference_expenses: float = Field(
...,
description="Travel and conference costs.",
title="Travel and Conference Expenses",
)
depreciation_amortization: float = Field(
...,
description="Depreciation and amortization expenses.",
title="Depreciation and Amortization",
)
insurance: float = Field(..., description="Insurance expenses.", title="Insurance")
class OfficersDirectorsTrusteesKeyEmployee(BaseModel):
name: str = Field(..., description="Full name of the individual.", title="Name")
title_position: str = Field(
..., description="Role or position held.", title="Title/Position"
)
average_hours_per_week: float = Field(
...,
description="Average weekly hours devoted to position.",
title="Average Hours Per Week",
)
related_party_transactions: str = Field(
...,
description="Indicates if related-party transactions occurred.",
title="Related-Party Transactions",
)
former_officer: str = Field(
...,
description="Indicates if the individual is a former officer.",
title="Former Officer Indicator",
)
governance_role: str = Field(
...,
description="Role in governance (voting, independent, etc.).",
title="Governance Role",
)
class GovernanceManagementDisclosure(BaseModel):
governing_body_size: float = Field(
...,
description="Number of voting members on the governing body.",
title="Governing Body Size",
)
independent_members: float = Field(
...,
description="Number of independent voting members.",
title="Number of Independent Members",
)
financial_statements_reviewed: str = Field(
...,
description="Indicates if financial statements were reviewed or audited.",
title="Financial Statements Reviewed/Audited",
)
form_990_provided_to_governing_body: str = Field(
...,
description="Indicates if Form 990 was provided to governing body before filing.",
title="Form 990 Provided to Governing Body",
)
conflict_of_interest_policy: str = Field(
...,
description="Indicates if a conflict-of-interest policy is in place.",
title="Conflict-of-Interest Policy",
)
whistleblower_policy: str = Field(
...,
description="Indicates if a whistleblower policy is in place.",
title="Whistleblower Policy",
)
document_retention_policy: str = Field(
...,
description="Indicates if a document retention/destruction policy is in place.",
title="Document Retention/Destruction Policy",
)
ceo_compensation_review_process: str = Field(
...,
description="Description of CEO compensation review process.",
title="CEO Compensation Review Process",
)
public_disclosure_practices: str = Field(
...,
description="Description of public disclosure practices.",
title="Public Disclosure Practices",
)
class ProgramServiceAccomplishment(BaseModel):
program_name: str = Field(
..., description="Name of the program.", title="Program Name"
)
program_description: str = Field(
..., description="Description of the program.", title="Program Description"
)
expenses: float = Field(
..., description="Expenses for the program.", title="Program Expenses"
)
grants: float = Field(
..., description="Grants made under the program.", title="Program Grants"
)
revenue_generated: float = Field(
..., description="Revenue generated by the program.", title="Revenue Generated"
)
quantitative_outputs: str = Field(
...,
description="Quantitative outputs (e.g., number served, events held).",
title="Quantitative Outputs",
)
class FundraisingGrantmaking(BaseModel):
total_fundraising_event_revenue: float = Field(
...,
description="Total revenue from fundraising events.",
title="Total Fundraising Event Revenue",
)
total_fundraising_event_expenses: float = Field(
...,
description="Total direct expenses for fundraising events.",
title="Total Fundraising Event Expenses",
)
professional_fundraiser_fees: float = Field(
...,
description="Fees paid to professional fundraisers.",
title="Professional Fundraiser Fees",
)
class FunctionalOperationalData(BaseModel):
number_of_employees: float = Field(
..., description="Total number of employees.", title="Number of Employees"
)
number_of_volunteers: float = Field(
..., description="Total number of volunteers.", title="Number of Volunteers"
)
occupancy_costs: float = Field(
..., description="Total occupancy costs.", title="Occupancy Costs"
)
fundraising_method_descriptions: str = Field(
...,
description="Descriptions of fundraising methods used.",
title="Fundraising Method Descriptions",
)
joint_ventures_disregarded_entities: str = Field(
...,
description="Details of joint ventures and disregarded entities.",
title="Joint Ventures and Disregarded Entities",
)
class CompensationDetails(BaseModel):
base_compensation: float = Field(
..., description="Base salary or wages.", title="Base Compensation"
)
bonus: float = Field(
..., description="Bonus or incentive compensation.", title="Bonus Compensation"
)
incentive: float = Field(
..., description="Incentive compensation.", title="Incentive Compensation"
)
other: float = Field(
..., description="Other forms of compensation.", title="Other Compensation"
)
non_fixed_compensation: str = Field(
...,
description="Indicates if compensation is non-fixed.",
title="Non-Fixed Compensation Flag",
)
first_class_travel: str = Field(
...,
description="Indicates if first-class travel was provided.",
title="First-Class Travel",
)
housing_allowance: str = Field(
...,
description="Indicates if housing allowance was provided.",
title="Housing Allowance",
)
expense_account_usage: str = Field(
...,
description="Indicates if expense account was used.",
title="Expense Account Usage",
)
supplemental_retirement: str = Field(
...,
description="Indicates if supplemental retirement or deferred comp was provided.",
title="Supplemental Retirement/Deferred Comp",
)
class PoliticalLobbyingActivities(BaseModel):
lobbying_expenditures_direct: float = Field(
...,
description="Direct lobbying expenditures.",
title="Direct Lobbying Expenditures",
)
lobbying_expenditures_grassroots: float = Field(
...,
description="Grassroots lobbying expenditures.",
title="Grassroots Lobbying Expenditures",
)
election_501h_status: str = Field(
...,
description="Indicates if 501(h) election was made.",
title="501(h) Election Status",
)
political_campaign_expenditures: float = Field(
...,
description="Expenditures for political campaigns.",
title="Political Campaign Expenditures",
)
related_organizations_affiliates: str = Field(
...,
description="Details of related organizations or affiliates involved.",
title="Related Organizations/Affiliates Involved",
)
class InvestmentsEndowment(BaseModel):
investment_types: str = Field(
...,
description="Types of investments held (securities, partnerships, real estate).",
title="Investment Types",
)
donor_restricted_endowment_values: float = Field(
...,
description="Value of donor-restricted endowments.",
title="Donor-Restricted Endowment Values",
)
net_appreciation_depreciation: float = Field(
...,
description="Net appreciation or depreciation of investments.",
title="Net Appreciation/Depreciation",
)
related_organization_transactions: str = Field(
...,
description="Details of transactions with related organizations.",
title="Related Organization Transactions",
)
loans_to_from_related_parties: str = Field(
...,
description="Details of loans to or from related parties.",
title="Loans to/from Related Parties",
)
class TaxCompliancePenalties(BaseModel):
penalties_excise_taxes_reported: str = Field(
...,
description="Reported penalties or excise taxes.",
title="Penalties or Excise Taxes Reported",
)
unrelated_business_income_disclosure: str = Field(
...,
description="Disclosure of unrelated business income (UBI).",
title="Unrelated Business Income Disclosure",
)
foreign_bank_account_reporting: str = Field(
...,
description="Disclosure of foreign bank accounts (FBAR equivalent).",
title="Foreign Bank Account Reporting",
)
schedule_o_narrative_explanations: str = Field(
...,
description="Narrative explanations from Schedule O.",
title="Schedule O Narrative Explanations",
)
class ExtractedIrsForm990PfDataSchema(BaseModel):
core_organization_metadata: CoreOrganizationMetadata = Field(
...,
description="Essential identifiers and attributes for normalizing entities across filings and years.",
title="Core Organization Metadata",
)
revenue_breakdown: RevenueBreakdown = Field(
...,
description="Detailed breakdown of revenue streams for the fiscal year.",
title="Revenue Breakdown",
)
expenses_breakdown: ExpensesBreakdown = Field(
...,
description="Detailed breakdown of expenses for the fiscal year.",
title="Expenses Breakdown",
)
balance_sheet: dict[str, Any] = Field(
...,
description="Assets, liabilities, and net assets at year end.",
title="Balance Sheet Data",
)
officers_directors_trustees_key_employees: list[
OfficersDirectorsTrusteesKeyEmployee
] = Field(
...,
description="List of key personnel and their compensation.",
title="Officers, Directors, Trustees, Key Employees",
)
governance_management_disclosure: GovernanceManagementDisclosure = Field(
...,
description="Governance and management practices, policies, and disclosures.",
title="Governance, Management, and Disclosure",
)
program_service_accomplishments: list[ProgramServiceAccomplishment] = Field(
...,
description="Major programs and their outputs for the fiscal year.",
title="Program Service Accomplishments",
)
fundraising_grantmaking: FundraisingGrantmaking = Field(
...,
description="Fundraising event details and grantmaking activities.",
title="Fundraising & Grantmaking",
)
functional_operational_data: FunctionalOperationalData = Field(
...,
description="Operational metrics and related-organization relationships.",
title="Functional & Operational Data",
)
compensation_details: CompensationDetails = Field(
...,
description="Detailed breakdown of officer compensation and benefits.",
title="Compensation Details",
)
political_lobbying_activities: PoliticalLobbyingActivities = Field(
...,
description="Details of political and lobbying expenditures and affiliations.",
title="Political & Lobbying Activities",
)
investments_endowment: InvestmentsEndowment = Field(
...,
description="Investment holdings, endowment values, and related transactions.",
title="Investments & Endowment",
)
tax_compliance_penalties: TaxCompliancePenalties = Field(
...,
description="Tax compliance indicators, penalties, and narrative explanations.",
title="Tax Compliance / Penalties",
)
class ValidatorState(BaseModel):
extraction: ExtractedIrsForm990PfDataSchema
initial_findings: list[AuditFinding] = Field(default_factory=list)
metadata: dict[str, Any] = Field(default_factory=dict)

608
backend/app/example_data.json Normal file
View File

@@ -0,0 +1,608 @@
{
"extraction": {
"core_organization_metadata": {
"ein": "84-2674654",
"legal_name": "07 IN HEAVEN MEMORIAL SCHOLARSHIP",
"phone_number": "(262) 215-0300",
"website_url": "",
"return_type": "990-PF",
"amended_return": "No",
"group_exemption_number": "",
"subsection_code": "501(c)(3)",
"ruling_date": "",
"accounting_method": "Cash",
"organization_type": "corporation",
"year_of_formation": "",
"incorporation_state": "WI"
},
"revenue_breakdown": {
"total_revenue": 5227,
"contributions_gifts_grants": 5227,
"program_service_revenue": 0,
"membership_dues": 0,
"investment_income": 0,
"gains_losses_sales_assets": 0,
"rental_income": 0,
"related_organizations_revenue": 0,
"gaming_revenue": 0,
"other_revenue": 0,
"government_grants": 0,
"foreign_contributions": 0
},
"expenses_breakdown": {
"total_expenses": 2104,
"program_services_expenses": 0,
"management_general_expenses": 0,
"fundraising_expenses": 2104,
"grants_us_organizations": 0,
"grants_us_individuals": 0,
"grants_foreign_organizations": 0,
"grants_foreign_individuals": 0,
"compensation_officers": 0,
"compensation_other_staff": 0,
"payroll_taxes_benefits": 0,
"professional_fees": 0,
"office_occupancy_costs": 0,
"information_technology_costs": 0,
"travel_conference_expenses": 0,
"depreciation_amortization": 0,
"insurance": 0
},
"balance_sheet": {},
"officers_directors_trustees_key_employees": [
{
"name": "REBECCA TERPSTRA",
"title_position": "PRESIDENT",
"average_hours_per_week": 0.1,
"related_party_transactions": "",
"former_officer": "",
"governance_role": ""
},
{
"name": "ROBERT GUZMAN",
"title_position": "VICE PRESDEINT",
"average_hours_per_week": 0.1,
"related_party_transactions": "",
"former_officer": "",
"governance_role": ""
},
{
"name": "ANDREA VALENTI",
"title_position": "TREASURER",
"average_hours_per_week": 0.1,
"related_party_transactions": "",
"former_officer": "",
"governance_role": ""
},
{
"name": "BETHANY WALSH",
"title_position": "SECRETARY",
"average_hours_per_week": 0.1,
"related_party_transactions": "",
"former_officer": "",
"governance_role": ""
}
],
"governance_management_disclosure": {
"governing_body_size": 4,
"independent_members": 4,
"financial_statements_reviewed": "",
"form_990_provided_to_governing_body": "",
"conflict_of_interest_policy": "",
"whistleblower_policy": "",
"document_retention_policy": "",
"ceo_compensation_review_process": "",
"public_disclosure_practices": "Yes"
},
"program_service_accomplishments": [],
"fundraising_grantmaking": {
"total_fundraising_event_revenue": 0,
"total_fundraising_event_expenses": 2104,
"professional_fundraiser_fees": 0
},
"functional_operational_data": {
"number_of_employees": 0,
"number_of_volunteers": 0,
"occupancy_costs": 0,
"fundraising_method_descriptions": "",
"joint_ventures_disregarded_entities": ""
},
"compensation_details": {
"base_compensation": 0,
"bonus": 0,
"incentive": 0,
"other": 0,
"non_fixed_compensation": "",
"first_class_travel": "",
"housing_allowance": "",
"expense_account_usage": "",
"supplemental_retirement": ""
},
"political_lobbying_activities": {
"lobbying_expenditures_direct": 0,
"lobbying_expenditures_grassroots": 0,
"election_501h_status": "",
"political_campaign_expenditures": 0,
"related_organizations_affiliates": ""
},
"investments_endowment": {
"investment_types": "",
"donor_restricted_endowment_values": 0,
"net_appreciation_depreciation": 0,
"related_organization_transactions": "",
"loans_to_from_related_parties": ""
},
"tax_compliance_penalties": {
"penalties_excise_taxes_reported": "No",
"unrelated_business_income_disclosure": "No",
"foreign_bank_account_reporting": "No",
"schedule_o_narrative_explanations": ""
}
},
"extraction_metadata": {
"core_organization_metadata": {
"ein": {
"value": "84-2674654",
"references": ["0-7"]
},
"legal_name": {
"value": "07 IN HEAVEN MEMORIAL SCHOLARSHIP",
"references": ["0-6"]
},
"phone_number": {
"value": "(262) 215-0300",
"references": ["0-a"]
},
"website_url": {
"value": "",
"references": []
},
"return_type": {
"value": "990-PF",
"references": ["4ade8ed0-bce7-4bd5-bd8d-190e3e4be95b"]
},
"amended_return": {
"value": "No",
"references": ["4ac9edc4-e9bb-430f-b4c4-a42bf4c04b28"]
},
"group_exemption_number": {
"value": "",
"references": []
},
"subsection_code": {
"value": "501(c)(3)",
"references": ["4ac9edc4-e9bb-430f-b4c4-a42bf4c04b28"]
},
"ruling_date": {
"value": "",
"references": []
},
"accounting_method": {
"value": "Cash",
"references": ["0-d"]
},
"organization_type": {
"value": "corporation",
"references": ["4ac9edc4-e9bb-430f-b4c4-a42bf4c04b28"]
},
"year_of_formation": {
"value": "",
"references": []
},
"incorporation_state": {
"value": "WI",
"references": ["4ac9edc4-e9bb-430f-b4c4-a42bf4c04b28"]
}
},
"revenue_breakdown": {
"total_revenue": {
"value": 5227,
"references": ["0-1z"]
},
"contributions_gifts_grants": {
"value": 5227,
"references": ["0-m"]
},
"program_service_revenue": {
"value": 0,
"references": []
},
"membership_dues": {
"value": 0,
"references": []
},
"investment_income": {
"value": 0,
"references": []
},
"gains_losses_sales_assets": {
"value": 0,
"references": []
},
"rental_income": {
"value": 0,
"references": []
},
"related_organizations_revenue": {
"value": 0,
"references": []
},
"gaming_revenue": {
"value": 0,
"references": []
},
"other_revenue": {
"value": 0,
"references": []
},
"government_grants": {
"value": 0,
"references": []
},
"foreign_contributions": {
"value": 0,
"references": []
}
},
"expenses_breakdown": {
"total_expenses": {
"value": 2104,
"references": ["0-2S"]
},
"program_services_expenses": {
"value": 0,
"references": []
},
"management_general_expenses": {
"value": 0,
"references": []
},
"fundraising_expenses": {
"value": 2104,
"references": ["13-d"]
},
"grants_us_organizations": {
"value": 0,
"references": []
},
"grants_us_individuals": {
"value": 0,
"references": []
},
"grants_foreign_organizations": {
"value": 0,
"references": []
},
"grants_foreign_individuals": {
"value": 0,
"references": []
},
"compensation_officers": {
"value": 0,
"references": ["5-1q", "5-1w", "5-1C", "5-1I"]
},
"compensation_other_staff": {
"value": 0,
"references": []
},
"payroll_taxes_benefits": {
"value": 0,
"references": []
},
"professional_fees": {
"value": 0,
"references": []
},
"office_occupancy_costs": {
"value": 0,
"references": []
},
"information_technology_costs": {
"value": 0,
"references": []
},
"travel_conference_expenses": {
"value": 0,
"references": []
},
"depreciation_amortization": {
"value": 0,
"references": []
},
"insurance": {
"value": 0,
"references": []
}
},
"balance_sheet": {},
"officers_directors_trustees_key_employees": [
{
"name": {
"value": "REBECCA TERPSTRA",
"references": ["5-1o"]
},
"title_position": {
"value": "PRESIDENT",
"references": ["5-1p"]
},
"average_hours_per_week": {
"value": 0.1,
"references": ["5-1p"]
},
"related_party_transactions": {
"value": "",
"references": []
},
"former_officer": {
"value": "",
"references": []
},
"governance_role": {
"value": "",
"references": []
}
},
{
"name": {
"value": "ROBERT GUZMAN",
"references": ["5-1u"]
},
"title_position": {
"value": "VICE PRESDEINT",
"references": ["5-1v"]
},
"average_hours_per_week": {
"value": 0.1,
"references": ["5-1v"]
},
"related_party_transactions": {
"value": "",
"references": []
},
"former_officer": {
"value": "",
"references": []
},
"governance_role": {
"value": "",
"references": []
}
},
{
"name": {
"value": "ANDREA VALENTI",
"references": ["5-1A"]
},
"title_position": {
"value": "TREASURER",
"references": ["5-1B"]
},
"average_hours_per_week": {
"value": 0.1,
"references": ["5-1B"]
},
"related_party_transactions": {
"value": "",
"references": []
},
"former_officer": {
"value": "",
"references": []
},
"governance_role": {
"value": "",
"references": []
}
},
{
"name": {
"value": "BETHANY WALSH",
"references": ["5-1G"]
},
"title_position": {
"value": "SECRETARY",
"references": ["5-1H"]
},
"average_hours_per_week": {
"value": 0.1,
"references": ["5-1H"]
},
"related_party_transactions": {
"value": "",
"references": []
},
"former_officer": {
"value": "",
"references": []
},
"governance_role": {
"value": "",
"references": []
}
}
],
"governance_management_disclosure": {
"governing_body_size": {
"value": 4,
"references": ["5-1o", "5-1u", "5-1A", "5-1G"]
},
"independent_members": {
"value": 4,
"references": ["5-1o", "5-1u", "5-1A", "5-1G"]
},
"financial_statements_reviewed": {
"value": "",
"references": []
},
"form_990_provided_to_governing_body": {
"value": "",
"references": []
},
"conflict_of_interest_policy": {
"value": "",
"references": []
},
"whistleblower_policy": {
"value": "",
"references": []
},
"document_retention_policy": {
"value": "",
"references": []
},
"ceo_compensation_review_process": {
"value": "",
"references": []
},
"public_disclosure_practices": {
"value": "Yes",
"references": ["4-g"]
}
},
"program_service_accomplishments": [],
"fundraising_grantmaking": {
"total_fundraising_event_revenue": {
"value": 0,
"references": []
},
"total_fundraising_event_expenses": {
"value": 2104,
"references": ["13-d"]
},
"professional_fundraiser_fees": {
"value": 0,
"references": []
}
},
"functional_operational_data": {
"number_of_employees": {
"value": 0,
"references": []
},
"number_of_volunteers": {
"value": 0,
"references": []
},
"occupancy_costs": {
"value": 0,
"references": []
},
"fundraising_method_descriptions": {
"value": "",
"references": []
},
"joint_ventures_disregarded_entities": {
"value": "",
"references": []
}
},
"compensation_details": {
"base_compensation": {
"value": 0,
"references": ["5-1q", "5-1w"]
},
"bonus": {
"value": 0,
"references": []
},
"incentive": {
"value": 0,
"references": []
},
"other": {
"value": 0,
"references": []
},
"non_fixed_compensation": {
"value": "",
"references": []
},
"first_class_travel": {
"value": "",
"references": []
},
"housing_allowance": {
"value": "",
"references": []
},
"expense_account_usage": {
"value": "",
"references": []
},
"supplemental_retirement": {
"value": "",
"references": []
}
},
"political_lobbying_activities": {
"lobbying_expenditures_direct": {
"value": 0,
"references": []
},
"lobbying_expenditures_grassroots": {
"value": 0,
"references": []
},
"election_501h_status": {
"value": "",
"references": []
},
"political_campaign_expenditures": {
"value": 0,
"references": []
},
"related_organizations_affiliates": {
"value": "",
"references": []
}
},
"investments_endowment": {
"investment_types": {
"value": "",
"references": []
},
"donor_restricted_endowment_values": {
"value": 0,
"references": []
},
"net_appreciation_depreciation": {
"value": 0,
"references": []
},
"related_organization_transactions": {
"value": "",
"references": []
},
"loans_to_from_related_parties": {
"value": "",
"references": []
}
},
"tax_compliance_penalties": {
"penalties_excise_taxes_reported": {
"value": "No",
"references": ["3-I"]
},
"unrelated_business_income_disclosure": {
"value": "No",
"references": ["3-Y"]
},
"foreign_bank_account_reporting": {
"value": "No",
"references": ["4-H"]
},
"schedule_o_narrative_explanations": {
"value": "",
"references": []
}
}
},
"metadata": {
"filename": "markdown.md",
"org_id": null,
"duration_ms": 16656,
"credit_usage": 27.2,
"job_id": "nnmr8lcxtykk5ll5wodjtrnn6",
"version": "extract-20250930"
}
}

342
backend/app/routers/agent.py
View File

@@ -6,6 +6,7 @@ from pydantic_ai.ui.vercel_ai import VercelAIAdapter
from starlette.requests import Request
from starlette.responses import Response
from app.agents import form_auditor
from app.core.config import settings
provider = AzureProvider(
@@ -19,6 +20,347 @@ agent = Agent(model=model)
router = APIRouter(prefix="/api/v1/agent", tags=["Agent"])
@agent.tool_plain()
async def build_audit_report():
"""Calls the audit subagent to get a full audit report of the organization"""
data = {
"extraction": {
"core_organization_metadata": {
"ein": "84-2674654",
"legal_name": "07 IN HEAVEN MEMORIAL SCHOLARSHIP",
"phone_number": "(262) 215-0300",
"website_url": "",
"return_type": "990-PF",
"amended_return": "No",
"group_exemption_number": "",
"subsection_code": "501(c)(3)",
"ruling_date": "",
"accounting_method": "Cash",
"organization_type": "corporation",
"year_of_formation": "",
"incorporation_state": "WI",
},
"revenue_breakdown": {
"total_revenue": 5227,
"contributions_gifts_grants": 5227,
"program_service_revenue": 0,
"membership_dues": 0,
"investment_income": 0,
"gains_losses_sales_assets": 0,
"rental_income": 0,
"related_organizations_revenue": 0,
"gaming_revenue": 0,
"other_revenue": 0,
"government_grants": 0,
"foreign_contributions": 0,
},
"expenses_breakdown": {
"total_expenses": 2104,
"program_services_expenses": 0,
"management_general_expenses": 0,
"fundraising_expenses": 2104,
"grants_us_organizations": 0,
"grants_us_individuals": 0,
"grants_foreign_organizations": 0,
"grants_foreign_individuals": 0,
"compensation_officers": 0,
"compensation_other_staff": 0,
"payroll_taxes_benefits": 0,
"professional_fees": 0,
"office_occupancy_costs": 0,
"information_technology_costs": 0,
"travel_conference_expenses": 0,
"depreciation_amortization": 0,
"insurance": 0,
},
"balance_sheet": {},
"officers_directors_trustees_key_employees": [
{
"name": "REBECCA TERPSTRA",
"title_position": "PRESIDENT",
"average_hours_per_week": 0.1,
"related_party_transactions": "",
"former_officer": "",
"governance_role": "",
},
{
"name": "ROBERT GUZMAN",
"title_position": "VICE PRESDEINT",
"average_hours_per_week": 0.1,
"related_party_transactions": "",
"former_officer": "",
"governance_role": "",
},
{
"name": "ANDREA VALENTI",
"title_position": "TREASURER",
"average_hours_per_week": 0.1,
"related_party_transactions": "",
"former_officer": "",
"governance_role": "",
},
{
"name": "BETHANY WALSH",
"title_position": "SECRETARY",
"average_hours_per_week": 0.1,
"related_party_transactions": "",
"former_officer": "",
"governance_role": "",
},
],
"governance_management_disclosure": {
"governing_body_size": 4,
"independent_members": 4,
"financial_statements_reviewed": "",
"form_990_provided_to_governing_body": "",
"conflict_of_interest_policy": "",
"whistleblower_policy": "",
"document_retention_policy": "",
"ceo_compensation_review_process": "",
"public_disclosure_practices": "Yes",
},
"program_service_accomplishments": [],
"fundraising_grantmaking": {
"total_fundraising_event_revenue": 0,
"total_fundraising_event_expenses": 2104,
"professional_fundraiser_fees": 0,
},
"functional_operational_data": {
"number_of_employees": 0,
"number_of_volunteers": 0,
"occupancy_costs": 0,
"fundraising_method_descriptions": "",
"joint_ventures_disregarded_entities": "",
},
"compensation_details": {
"base_compensation": 0,
"bonus": 0,
"incentive": 0,
"other": 0,
"non_fixed_compensation": "",
"first_class_travel": "",
"housing_allowance": "",
"expense_account_usage": "",
"supplemental_retirement": "",
},
"political_lobbying_activities": {
"lobbying_expenditures_direct": 0,
"lobbying_expenditures_grassroots": 0,
"election_501h_status": "",
"political_campaign_expenditures": 0,
"related_organizations_affiliates": "",
},
"investments_endowment": {
"investment_types": "",
"donor_restricted_endowment_values": 0,
"net_appreciation_depreciation": 0,
"related_organization_transactions": "",
"loans_to_from_related_parties": "",
},
"tax_compliance_penalties": {
"penalties_excise_taxes_reported": "No",
"unrelated_business_income_disclosure": "No",
"foreign_bank_account_reporting": "No",
"schedule_o_narrative_explanations": "",
},
},
"extraction_metadata": {
"core_organization_metadata": {
"ein": {"value": "84-2674654", "references": ["0-7"]},
"legal_name": {
"value": "07 IN HEAVEN MEMORIAL SCHOLARSHIP",
"references": ["0-6"],
},
"phone_number": {"value": "(262) 215-0300", "references": ["0-a"]},
"website_url": {"value": "", "references": []},
"return_type": {
"value": "990-PF",
"references": ["4ade8ed0-bce7-4bd5-bd8d-190e3e4be95b"],
},
"amended_return": {
"value": "No",
"references": ["4ac9edc4-e9bb-430f-b4c4-a42bf4c04b28"],
},
"group_exemption_number": {"value": "", "references": []},
"subsection_code": {
"value": "501(c)(3)",
"references": ["4ac9edc4-e9bb-430f-b4c4-a42bf4c04b28"],
},
"ruling_date": {"value": "", "references": []},
"accounting_method": {"value": "Cash", "references": ["0-d"]},
"organization_type": {
"value": "corporation",
"references": ["4ac9edc4-e9bb-430f-b4c4-a42bf4c04b28"],
},
"year_of_formation": {"value": "", "references": []},
"incorporation_state": {
"value": "WI",
"references": ["4ac9edc4-e9bb-430f-b4c4-a42bf4c04b28"],
},
},
"revenue_breakdown": {
"total_revenue": {"value": 5227, "references": ["0-1z"]},
"contributions_gifts_grants": {"value": 5227, "references": ["0-m"]},
"program_service_revenue": {"value": 0, "references": []},
"membership_dues": {"value": 0, "references": []},
"investment_income": {"value": 0, "references": []},
"gains_losses_sales_assets": {"value": 0, "references": []},
"rental_income": {"value": 0, "references": []},
"related_organizations_revenue": {"value": 0, "references": []},
"gaming_revenue": {"value": 0, "references": []},
"other_revenue": {"value": 0, "references": []},
"government_grants": {"value": 0, "references": []},
"foreign_contributions": {"value": 0, "references": []},
},
"expenses_breakdown": {
"total_expenses": {"value": 2104, "references": ["0-2S"]},
"program_services_expenses": {"value": 0, "references": []},
"management_general_expenses": {"value": 0, "references": []},
"fundraising_expenses": {"value": 2104, "references": ["13-d"]},
"grants_us_organizations": {"value": 0, "references": []},
"grants_us_individuals": {"value": 0, "references": []},
"grants_foreign_organizations": {"value": 0, "references": []},
"grants_foreign_individuals": {"value": 0, "references": []},
"compensation_officers": {
"value": 0,
"references": ["5-1q", "5-1w", "5-1C", "5-1I"],
},
"compensation_other_staff": {"value": 0, "references": []},
"payroll_taxes_benefits": {"value": 0, "references": []},
"professional_fees": {"value": 0, "references": []},
"office_occupancy_costs": {"value": 0, "references": []},
"information_technology_costs": {"value": 0, "references": []},
"travel_conference_expenses": {"value": 0, "references": []},
"depreciation_amortization": {"value": 0, "references": []},
"insurance": {"value": 0, "references": []},
},
"balance_sheet": {},
"officers_directors_trustees_key_employees": [
{
"name": {"value": "REBECCA TERPSTRA", "references": ["5-1o"]},
"title_position": {"value": "PRESIDENT", "references": ["5-1p"]},
"average_hours_per_week": {"value": 0.1, "references": ["5-1p"]},
"related_party_transactions": {"value": "", "references": []},
"former_officer": {"value": "", "references": []},
"governance_role": {"value": "", "references": []},
},
{
"name": {"value": "ROBERT GUZMAN", "references": ["5-1u"]},
"title_position": {
"value": "VICE PRESDEINT",
"references": ["5-1v"],
},
"average_hours_per_week": {"value": 0.1, "references": ["5-1v"]},
"related_party_transactions": {"value": "", "references": []},
"former_officer": {"value": "", "references": []},
"governance_role": {"value": "", "references": []},
},
{
"name": {"value": "ANDREA VALENTI", "references": ["5-1A"]},
"title_position": {"value": "TREASURER", "references": ["5-1B"]},
"average_hours_per_week": {"value": 0.1, "references": ["5-1B"]},
"related_party_transactions": {"value": "", "references": []},
"former_officer": {"value": "", "references": []},
"governance_role": {"value": "", "references": []},
},
{
"name": {"value": "BETHANY WALSH", "references": ["5-1G"]},
"title_position": {"value": "SECRETARY", "references": ["5-1H"]},
"average_hours_per_week": {"value": 0.1, "references": ["5-1H"]},
"related_party_transactions": {"value": "", "references": []},
"former_officer": {"value": "", "references": []},
"governance_role": {"value": "", "references": []},
},
],
"governance_management_disclosure": {
"governing_body_size": {
"value": 4,
"references": ["5-1o", "5-1u", "5-1A", "5-1G"],
},
"independent_members": {
"value": 4,
"references": ["5-1o", "5-1u", "5-1A", "5-1G"],
},
"financial_statements_reviewed": {"value": "", "references": []},
"form_990_provided_to_governing_body": {"value": "", "references": []},
"conflict_of_interest_policy": {"value": "", "references": []},
"whistleblower_policy": {"value": "", "references": []},
"document_retention_policy": {"value": "", "references": []},
"ceo_compensation_review_process": {"value": "", "references": []},
"public_disclosure_practices": {"value": "Yes", "references": ["4-g"]},
},
"program_service_accomplishments": [],
"fundraising_grantmaking": {
"total_fundraising_event_revenue": {"value": 0, "references": []},
"total_fundraising_event_expenses": {
"value": 2104,
"references": ["13-d"],
},
"professional_fundraiser_fees": {"value": 0, "references": []},
},
"functional_operational_data": {
"number_of_employees": {"value": 0, "references": []},
"number_of_volunteers": {"value": 0, "references": []},
"occupancy_costs": {"value": 0, "references": []},
"fundraising_method_descriptions": {"value": "", "references": []},
"joint_ventures_disregarded_entities": {"value": "", "references": []},
},
"compensation_details": {
"base_compensation": {"value": 0, "references": ["5-1q", "5-1w"]},
"bonus": {"value": 0, "references": []},
"incentive": {"value": 0, "references": []},
"other": {"value": 0, "references": []},
"non_fixed_compensation": {"value": "", "references": []},
"first_class_travel": {"value": "", "references": []},
"housing_allowance": {"value": "", "references": []},
"expense_account_usage": {"value": "", "references": []},
"supplemental_retirement": {"value": "", "references": []},
},
"political_lobbying_activities": {
"lobbying_expenditures_direct": {"value": 0, "references": []},
"lobbying_expenditures_grassroots": {"value": 0, "references": []},
"election_501h_status": {"value": "", "references": []},
"political_campaign_expenditures": {"value": 0, "references": []},
"related_organizations_affiliates": {"value": "", "references": []},
},
"investments_endowment": {
"investment_types": {"value": "", "references": []},
"donor_restricted_endowment_values": {"value": 0, "references": []},
"net_appreciation_depreciation": {"value": 0, "references": []},
"related_organization_transactions": {"value": "", "references": []},
"loans_to_from_related_parties": {"value": "", "references": []},
},
"tax_compliance_penalties": {
"penalties_excise_taxes_reported": {
"value": "No",
"references": ["3-I"],
},
"unrelated_business_income_disclosure": {
"value": "No",
"references": ["3-Y"],
},
"foreign_bank_account_reporting": {
"value": "No",
"references": ["4-H"],
},
"schedule_o_narrative_explanations": {"value": "", "references": []},
},
},
"metadata": {
"filename": "markdown.md",
"org_id": None,
"duration_ms": 16656,
"credit_usage": 27.2,
"job_id": "nnmr8lcxtykk5ll5wodjtrnn6",
"version": "extract-20250930",
},
}
result = await form_auditor.build_audit_report(data)
return result.model_dump_json()
@router.post("/chat")
async def chat(request: Request) -> Response:
return await VercelAIAdapter.dispatch_request(request, agent=agent)

125
backend/app/routers/chunking_landingai.py
View File

@@ -2,17 +2,18 @@
Router para procesamiento de PDFs con LandingAI.
Soporta dos modos: rápido (solo parse) y extracción (parse + extract con schema).
"""
import logging
import time
from typing import List, Literal, Optional
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel, Field
from typing import Optional, List, Literal
from langchain_core.documents import Document
from pydantic import BaseModel, Field
from ..services.landingai_service import get_landingai_service
from ..services.chunking_service import get_chunking_service
from ..repositories.schema_repository import get_schema_repository
from ..services.chunking_service import get_chunking_service
from ..services.landingai_service import get_landingai_service
from ..utils.chunking.token_manager import TokenManager
logger = logging.getLogger(__name__)
@@ -22,6 +23,7 @@ router = APIRouter(prefix="/api/v1/chunking-landingai", tags=["chunking-landinga
class ProcessLandingAIRequest(BaseModel):
"""Request para procesar PDF con LandingAI"""
file_name: str = Field(..., description="Nombre del archivo PDF")
tema: str = Field(..., description="Tema/carpeta del archivo")
collection_name: str = Field(..., description="Colección de Qdrant")
@@ -29,34 +31,33 @@ class ProcessLandingAIRequest(BaseModel):
# Modo de procesamiento
mode: Literal["quick", "extract"] = Field(
default="quick",
description="Modo: 'quick' (solo parse) o 'extract' (parse + datos estructurados)"
description="Modo: 'quick' (solo parse) o 'extract' (parse + datos estructurados)",
)
# Schema (obligatorio si mode='extract')
schema_id: Optional[str] = Field(
None,
description="ID del schema a usar (requerido si mode='extract')"
None, description="ID del schema a usar (requerido si mode='extract')"
)
# Configuración de chunks
include_chunk_types: List[str] = Field(
default=["text", "table"],
description="Tipos de chunks a incluir: text, table, figure, etc."
description="Tipos de chunks a incluir: text, table, figure, etc.",
)
max_tokens_per_chunk: int = Field(
default=1500,
ge=500,
le=3000,
description="Tokens máximos por chunk (flexible para tablas/figuras)"
description="Tokens máximos por chunk (flexible para tablas/figuras)",
)
merge_small_chunks: bool = Field(
default=True,
description="Unir chunks pequeños de la misma página y tipo"
default=True, description="Unir chunks pequeños de la misma página y tipo"
)
class ProcessLandingAIResponse(BaseModel):
"""Response del procesamiento con LandingAI"""
success: bool
mode: str
processing_time_seconds: float
@@ -97,9 +98,9 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
start_time = time.time()
try:
logger.info(f"\n{'='*60}")
logger.info(f"INICIANDO PROCESAMIENTO CON LANDINGAI")
logger.info(f"{'='*60}")
logger.info(f"\n{'=' * 60}")
logger.info("INICIANDO PROCESAMIENTO CON LANDINGAI")
logger.info(f"{'=' * 60}")
logger.info(f"Archivo: {request.file_name}")
logger.info(f"Tema: {request.tema}")
logger.info(f"Modo: {request.mode}")
@@ -111,7 +112,7 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
if not request.schema_id:
raise HTTPException(
status_code=400,
detail="schema_id es requerido cuando mode='extract'"
detail="schema_id es requerido cuando mode='extract'",
)
schema_repo = get_schema_repository()
@@ -119,8 +120,7 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
if not custom_schema:
raise HTTPException(
status_code=404,
detail=f"Schema no encontrado: {request.schema_id}"
status_code=404, detail=f"Schema no encontrado: {request.schema_id}"
)
logger.info(f"Schema seleccionado: {custom_schema.schema_name}")
@@ -131,14 +131,12 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
try:
pdf_bytes = await chunking_service.download_pdf_from_blob(
request.file_name,
request.tema
request.file_name, request.tema
)
except Exception as e:
logger.error(f"Error descargando PDF: {e}")
raise HTTPException(
status_code=404,
detail=f"No se pudo descargar el PDF: {str(e)}"
status_code=404, detail=f"No se pudo descargar el PDF: {str(e)}"
)
# 3. Procesar con LandingAI
@@ -150,13 +148,12 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
pdf_bytes=pdf_bytes,
file_name=request.file_name,
custom_schema=custom_schema,
include_chunk_types=request.include_chunk_types
include_chunk_types=request.include_chunk_types,
)
except Exception as e:
logger.error(f"Error en LandingAI: {e}")
raise HTTPException(
status_code=500,
detail=f"Error procesando con LandingAI: {str(e)}"
status_code=500, detail=f"Error procesando con LandingAI: {str(e)}"
)
documents = result["chunks"]
@@ -164,7 +161,7 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
if not documents:
raise HTTPException(
status_code=400,
detail="No se generaron chunks después del procesamiento"
detail="No se generaron chunks después del procesamiento",
)
# 4. Aplicar control flexible de tokens
@@ -172,7 +169,7 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
documents = _apply_flexible_token_control(
documents,
max_tokens=request.max_tokens_per_chunk,
merge_small=request.merge_small_chunks
merge_small=request.merge_small_chunks,
)
# 5. Generar embeddings
@@ -180,13 +177,16 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
texts = [doc.page_content for doc in documents]
try:
embeddings = await chunking_service.embedding_service.generate_embeddings_batch(texts)
embeddings = (
await chunking_service.embedding_service.generate_embeddings_batch(
texts
)
)
logger.info(f"Embeddings generados: {len(embeddings)} vectores")
except Exception as e:
logger.error(f"Error generando embeddings: {e}")
raise HTTPException(
status_code=500,
detail=f"Error generando embeddings: {str(e)}"
status_code=500, detail=f"Error generando embeddings: {str(e)}"
)
# 6. Preparar chunks para Qdrant con IDs determinísticos
@@ -198,38 +198,38 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
chunk_id = chunking_service._generate_deterministic_id(
file_name=request.file_name,
page=doc.metadata.get("page", 1),
chunk_index=doc.metadata.get("chunk_id", str(idx))
chunk_index=doc.metadata.get("chunk_id", str(idx)),
)
qdrant_chunks.append({
"id": chunk_id,
"vector": embedding,
"payload": {
"page_content": doc.page_content,
"metadata": doc.metadata # Metadata rica de LandingAI
qdrant_chunks.append(
{
"id": chunk_id,
"vector": embedding,
"payload": {
"page_content": doc.page_content,
"metadata": doc.metadata, # Metadata rica de LandingAI
},
}
})
)
# 7. Subir a Qdrant
try:
upload_result = await chunking_service.vector_db.add_chunks(
request.collection_name,
qdrant_chunks
request.collection_name, qdrant_chunks
)
logger.info(f"Subida completada: {upload_result['chunks_added']} chunks")
except Exception as e:
logger.error(f"Error subiendo a Qdrant: {e}")
raise HTTPException(
status_code=500,
detail=f"Error subiendo a Qdrant: {str(e)}"
status_code=500, detail=f"Error subiendo a Qdrant: {str(e)}"
)
# Tiempo total
processing_time = time.time() - start_time
logger.info(f"\n{'='*60}")
logger.info(f"\n{'=' * 60}")
logger.info(f"PROCESAMIENTO COMPLETADO")
logger.info(f"{'='*60}")
logger.info(f"{'=' * 60}")
logger.info(f"Tiempo: {processing_time:.2f}s")
logger.info(f"Chunks procesados: {len(documents)}")
logger.info(f"Chunks subidos: {upload_result['chunks_added']}")
@@ -245,23 +245,18 @@ async def process_with_landingai(request: ProcessLandingAIRequest):
schema_used=custom_schema.schema_id if custom_schema else None,
extracted_data=result.get("extracted_data"),
parse_metadata=result["parse_metadata"],
message=f"PDF procesado exitosamente en modo {request.mode}"
message=f"PDF procesado exitosamente en modo {request.mode}",
)
except HTTPException:
raise
except Exception as e:
logger.error(f"Error inesperado en procesamiento: {e}")
raise HTTPException(
status_code=500,
detail=f"Error inesperado: {str(e)}"
)
raise HTTPException(status_code=500, detail=f"Error inesperado: {str(e)}")
def _apply_flexible_token_control(
documents: List[Document],
max_tokens: int,
merge_small: bool
documents: List[Document], max_tokens: int, merge_small: bool
) -> List[Document]:
"""
Aplica control flexible de tokens (Opción C del diseño).
@@ -306,14 +301,10 @@ def _apply_flexible_token_control(
else:
# Intentar merge si es pequeño
if (
merge_small and
tokens < max_tokens * 0.5 and
i < len(documents) - 1
):
if merge_small and tokens < max_tokens * 0.5 and i < len(documents) - 1:
next_doc = documents[i + 1]
if _can_merge(doc, next_doc, max_tokens, token_manager):
logger.debug(f"Merging chunks {i} y {i+1}")
logger.debug(f"Merging chunks {i} y {i + 1}")
doc = _merge_documents(doc, next_doc)
i += 1 # Skip next
@@ -326,9 +317,7 @@ def _apply_flexible_token_control(
def _split_large_chunk(
doc: Document,
max_tokens: int,
token_manager: TokenManager
doc: Document, max_tokens: int, token_manager: TokenManager
) -> List[Document]:
"""Divide un chunk grande en sub-chunks"""
content = doc.page_content
@@ -343,8 +332,7 @@ def _split_large_chunk(
# Guardar chunk actual
sub_content = " ".join(current_chunk)
sub_doc = Document(
page_content=sub_content,
metadata={**doc.metadata, "is_split": True}
page_content=sub_content, metadata={**doc.metadata, "is_split": True}
)
sub_chunks.append(sub_doc)
current_chunk = [word]
@@ -357,8 +345,7 @@ def _split_large_chunk(
if current_chunk:
sub_content = " ".join(current_chunk)
sub_doc = Document(
page_content=sub_content,
metadata={**doc.metadata, "is_split": True}
page_content=sub_content, metadata={**doc.metadata, "is_split": True}
)
sub_chunks.append(sub_doc)
@@ -366,10 +353,7 @@ def _split_large_chunk(
def _can_merge(
doc1: Document,
doc2: Document,
max_tokens: int,
token_manager: TokenManager
doc1: Document, doc2: Document, max_tokens: int, token_manager: TokenManager
) -> bool:
"""Verifica si dos docs se pueden mergear"""
# Misma página
@@ -391,6 +375,5 @@ def _merge_documents(doc1: Document, doc2: Document) -> Document:
"""Mergea dos documentos"""
merged_content = f"{doc1.page_content}\n\n{doc2.page_content}"
return Document(
page_content=merged_content,
metadata={**doc1.metadata, "is_merged": True}
page_content=merged_content, metadata={**doc1.metadata, "is_merged": True}
)

129
backend/app/routers/dataroom.py
View File

@@ -1,10 +1,12 @@
import logging
from typing import Optional
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel
from ..models.dataroom import DataRoom
from ..models.vector_models import CollectionCreateRequest
from ..services.azure_service import azure_service
from ..services.vector_service import vector_service
logger = logging.getLogger(__name__)
@@ -16,9 +18,136 @@ class DataroomCreate(BaseModel):
storage: str = ""
class DataroomInfo(BaseModel):
name: str
collection: str
storage: str
file_count: int
total_size_bytes: int
total_size_mb: float
collection_exists: bool
vector_count: Optional[int]
collection_info: Optional[dict]
file_types: dict
recent_files: list
router = APIRouter(prefix="/dataroom", tags=["Dataroom"])
@router.get("/{dataroom_name}/info")
async def dataroom_info(dataroom_name: str) -> DataroomInfo:
"""
Obtener información detallada de un dataroom específico
"""
try:
# Find the dataroom in Redis
datarooms = DataRoom.find().all()
dataroom = None
for room in datarooms:
if room.name == dataroom_name:
dataroom = room
break
if not dataroom:
raise HTTPException(
status_code=404, detail=f"Dataroom '{dataroom_name}' not found"
)
# Get file information from Azure Storage
try:
files_data = await azure_service.list_files(dataroom_name)
except Exception as e:
logger.warning(f"Could not fetch files for dataroom '{dataroom_name}': {e}")
files_data = []
# Calculate file metrics
file_count = len(files_data)
total_size_bytes = sum(file_data.get("size", 0) for file_data in files_data)
total_size_mb = (
round(total_size_bytes / (1024 * 1024), 2) if total_size_bytes > 0 else 0.0
)
# Analyze file types
file_types = {}
recent_files = []
for file_data in files_data:
# Count file types by extension
filename = file_data.get("name", "")
if "." in filename:
ext = filename.split(".")[-1].lower()
file_types[ext] = file_types.get(ext, 0) + 1
# Collect recent files (up to 5)
if len(recent_files) < 5:
recent_files.append(
{
"name": filename,
"size_mb": round(file_data.get("size", 0) / (1024 * 1024), 2),
"last_modified": file_data.get("last_modified"),
}
)
# Sort recent files by last modified (newest first)
recent_files.sort(key=lambda x: x.get("last_modified", ""), reverse=True)
# Get vector collection information
collection_exists = False
vector_count = None
collection_info = None
try:
collection_exists_response = await vector_service.check_collection_exists(
dataroom_name
)
collection_exists = collection_exists_response.exists
if collection_exists:
collection_info_response = await vector_service.get_collection_info(
dataroom_name
)
if collection_info_response:
collection_info = {
"vectors_count": collection_info_response.vectors_count,
"indexed_vectors_count": collection_info_response.indexed_vectors_count,
"points_count": collection_info_response.points_count,
"segments_count": collection_info_response.segments_count,
"status": collection_info_response.status,
}
vector_count = collection_info_response.vectors_count
except Exception as e:
logger.warning(
f"Could not fetch collection info for '{dataroom_name}': {e}"
)
logger.info(
f"Retrieved info for dataroom '{dataroom_name}': {file_count} files, {total_size_mb}MB"
)
return DataroomInfo(
name=dataroom.name,
collection=dataroom.collection,
storage=dataroom.storage,
file_count=file_count,
total_size_bytes=total_size_bytes,
total_size_mb=total_size_mb,
collection_exists=collection_exists,
vector_count=vector_count,
collection_info=collection_info,
file_types=file_types,
recent_files=recent_files,
)
except HTTPException:
raise
except Exception as e:
logger.error(f"Error getting dataroom info for '{dataroom_name}': {e}")
raise HTTPException(
status_code=500, detail=f"Error getting dataroom info: {str(e)}"
)
@router.get("/")
async def list_datarooms():
"""

5
backend/pyproject.toml
View File

@@ -33,3 +33,8 @@ dependencies = [
[project.scripts]
dev = "uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload"
start = "uvicorn app.main:app --host 0.0.0.0 --port 8000"
[dependency-groups]
dev = [
"ruff>=0.14.4",
]

34
backend/uv.lock generated
View File

@@ -86,6 +86,11 @@ dependencies = [
{ name = "websockets" },
]
[package.dev-dependencies]
dev = [
{ name = "ruff" },
]
[package.metadata]
requires-dist = [
{ name = "azure-storage-blob", specifier = ">=12.26.0" },
@@ -110,6 +115,9 @@ requires-dist = [
{ name = "websockets", specifier = ">=14.1" },
]
[package.metadata.requires-dev]
dev = [{ name = "ruff", specifier = ">=0.14.4" }]
[[package]]
name = "cachetools"
version = "6.2.1"
@@ -1789,6 +1797,32 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/64/8d/0133e4eb4beed9e425d9a98ed6e081a55d195481b7632472be1af08d2f6b/rsa-4.9.1-py3-none-any.whl", hash = "sha256:68635866661c6836b8d39430f97a996acbd61bfa49406748ea243539fe239762", size = 34696, upload-time = "2025-04-16T09:51:17.142Z" },
]
[[package]]
name = "ruff"
version = "0.14.4"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/df/55/cccfca45157a2031dcbb5a462a67f7cf27f8b37d4b3b1cd7438f0f5c1df6/ruff-0.14.4.tar.gz", hash = "sha256:f459a49fe1085a749f15414ca76f61595f1a2cc8778ed7c279b6ca2e1fd19df3", size = 5587844, upload-time = "2025-11-06T22:07:45.033Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/17/b9/67240254166ae1eaa38dec32265e9153ac53645a6c6670ed36ad00722af8/ruff-0.14.4-py3-none-linux_armv6l.whl", hash = "sha256:e6604613ffbcf2297cd5dcba0e0ac9bd0c11dc026442dfbb614504e87c349518", size = 12606781, upload-time = "2025-11-06T22:07:01.841Z" },
{ url = "https://files.pythonhosted.org/packages/46/c8/09b3ab245d8652eafe5256ab59718641429f68681ee713ff06c5c549f156/ruff-0.14.4-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:d99c0b52b6f0598acede45ee78288e5e9b4409d1ce7f661f0fa36d4cbeadf9a4", size = 12946765, upload-time = "2025-11-06T22:07:05.858Z" },
{ url = "https://files.pythonhosted.org/packages/14/bb/1564b000219144bf5eed2359edc94c3590dd49d510751dad26202c18a17d/ruff-0.14.4-py3-none-macosx_11_0_arm64.whl", hash = "sha256:9358d490ec030f1b51d048a7fd6ead418ed0826daf6149e95e30aa67c168af33", size = 11928120, upload-time = "2025-11-06T22:07:08.023Z" },
{ url = "https://files.pythonhosted.org/packages/a3/92/d5f1770e9988cc0742fefaa351e840d9aef04ec24ae1be36f333f96d5704/ruff-0.14.4-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:81b40d27924f1f02dfa827b9c0712a13c0e4b108421665322218fc38caf615c2", size = 12370877, upload-time = "2025-11-06T22:07:10.015Z" },
{ url = "https://files.pythonhosted.org/packages/e2/29/e9282efa55f1973d109faf839a63235575519c8ad278cc87a182a366810e/ruff-0.14.4-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f5e649052a294fe00818650712083cddc6cc02744afaf37202c65df9ea52efa5", size = 12408538, upload-time = "2025-11-06T22:07:13.085Z" },
{ url = "https://files.pythonhosted.org/packages/8e/01/930ed6ecfce130144b32d77d8d69f5c610e6d23e6857927150adf5d7379a/ruff-0.14.4-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:aa082a8f878deeba955531f975881828fd6afd90dfa757c2b0808aadb437136e", size = 13141942, upload-time = "2025-11-06T22:07:15.386Z" },
{ url = "https://files.pythonhosted.org/packages/6a/46/a9c89b42b231a9f487233f17a89cbef9d5acd538d9488687a02ad288fa6b/ruff-0.14.4-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:1043c6811c2419e39011890f14d0a30470f19d47d197c4858b2787dfa698f6c8", size = 14544306, upload-time = "2025-11-06T22:07:17.631Z" },
{ url = "https://files.pythonhosted.org/packages/78/96/9c6cf86491f2a6d52758b830b89b78c2ae61e8ca66b86bf5a20af73d20e6/ruff-0.14.4-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a9f3a936ac27fb7c2a93e4f4b943a662775879ac579a433291a6f69428722649", size = 14210427, upload-time = "2025-11-06T22:07:19.832Z" },
{ url = "https://files.pythonhosted.org/packages/71/f4/0666fe7769a54f63e66404e8ff698de1dcde733e12e2fd1c9c6efb689cb5/ruff-0.14.4-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:95643ffd209ce78bc113266b88fba3d39e0461f0cbc8b55fb92505030fb4a850", size = 13658488, upload-time = "2025-11-06T22:07:22.32Z" },
{ url = "https://files.pythonhosted.org/packages/ee/79/6ad4dda2cfd55e41ac9ed6d73ef9ab9475b1eef69f3a85957210c74ba12c/ruff-0.14.4-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:456daa2fa1021bc86ca857f43fe29d5d8b3f0e55e9f90c58c317c1dcc2afc7b5", size = 13354908, upload-time = "2025-11-06T22:07:24.347Z" },
{ url = "https://files.pythonhosted.org/packages/b5/60/f0b6990f740bb15c1588601d19d21bcc1bd5de4330a07222041678a8e04f/ruff-0.14.4-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:f911bba769e4a9f51af6e70037bb72b70b45a16db5ce73e1f72aefe6f6d62132", size = 13587803, upload-time = "2025-11-06T22:07:26.327Z" },
{ url = "https://files.pythonhosted.org/packages/c9/da/eaaada586f80068728338e0ef7f29ab3e4a08a692f92eb901a4f06bbff24/ruff-0.14.4-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:76158a7369b3979fa878612c623a7e5430c18b2fd1c73b214945c2d06337db67", size = 12279654, upload-time = "2025-11-06T22:07:28.46Z" },
{ url = "https://files.pythonhosted.org/packages/66/d4/b1d0e82cf9bf8aed10a6d45be47b3f402730aa2c438164424783ac88c0ed/ruff-0.14.4-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:f3b8f3b442d2b14c246e7aeca2e75915159e06a3540e2f4bed9f50d062d24469", size = 12357520, upload-time = "2025-11-06T22:07:31.468Z" },
{ url = "https://files.pythonhosted.org/packages/04/f4/53e2b42cc82804617e5c7950b7079d79996c27e99c4652131c6a1100657f/ruff-0.14.4-py3-none-musllinux_1_2_i686.whl", hash = "sha256:c62da9a06779deecf4d17ed04939ae8b31b517643b26370c3be1d26f3ef7dbde", size = 12719431, upload-time = "2025-11-06T22:07:33.831Z" },
{ url = "https://files.pythonhosted.org/packages/a2/94/80e3d74ed9a72d64e94a7b7706b1c1ebaa315ef2076fd33581f6a1cd2f95/ruff-0.14.4-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:5a443a83a1506c684e98acb8cb55abaf3ef725078be40237463dae4463366349", size = 13464394, upload-time = "2025-11-06T22:07:35.905Z" },
{ url = "https://files.pythonhosted.org/packages/54/1a/a49f071f04c42345c793d22f6cf5e0920095e286119ee53a64a3a3004825/ruff-0.14.4-py3-none-win32.whl", hash = "sha256:643b69cb63cd996f1fc7229da726d07ac307eae442dd8974dbc7cf22c1e18fff", size = 12493429, upload-time = "2025-11-06T22:07:38.43Z" },
{ url = "https://files.pythonhosted.org/packages/bc/22/e58c43e641145a2b670328fb98bc384e20679b5774258b1e540207580266/ruff-0.14.4-py3-none-win_amd64.whl", hash = "sha256:26673da283b96fe35fa0c939bf8411abec47111644aa9f7cfbd3c573fb125d2c", size = 13635380, upload-time = "2025-11-06T22:07:40.496Z" },
{ url = "https://files.pythonhosted.org/packages/30/bd/4168a751ddbbf43e86544b4de8b5c3b7be8d7167a2a5cb977d274e04f0a1/ruff-0.14.4-py3-none-win_arm64.whl", hash = "sha256:dd09c292479596b0e6fec8cd95c65c3a6dc68e9ad17b8f2382130f87ff6a75bb", size = 12663065, upload-time = "2025-11-06T22:07:42.603Z" },
]
[[package]]
name = "setuptools"
version = "80.9.0"