forked from cardosofelipe/fast-next-template
Felipe Cardoso
b232298c61
- Added `memory_consolidation` to the task list and updated `__all__` in test files. - Updated `source_episode_ids` in `Fact` model to use JSON for cross-database compatibility. - Revised related database migrations to use JSONB instead of ARRAY. - Adjusted test concurrency in Makefile for improved test performance.
106 lines
3.2 KiB
Python
106 lines
3.2 KiB
Python
# app/models/memory/fact.py
|
|
"""
|
|
Fact database model.
|
|
|
|
Stores semantic memories - learned facts in subject-predicate-object
|
|
triple format with confidence scores and source tracking.
|
|
"""
|
|
|
|
from sqlalchemy import (
|
|
CheckConstraint,
|
|
Column,
|
|
DateTime,
|
|
Float,
|
|
ForeignKey,
|
|
Index,
|
|
Integer,
|
|
String,
|
|
Text,
|
|
text,
|
|
)
|
|
from sqlalchemy.dialects.postgresql import UUID as PGUUID
|
|
from sqlalchemy.orm import relationship
|
|
from sqlalchemy.types import JSON
|
|
|
|
from app.models.base import Base, TimestampMixin, UUIDMixin
|
|
|
|
# Import pgvector type
|
|
try:
|
|
from pgvector.sqlalchemy import Vector # type: ignore[import-not-found]
|
|
except ImportError:
|
|
Vector = None
|
|
|
|
|
|
class Fact(Base, UUIDMixin, TimestampMixin):
|
|
"""
|
|
Semantic memory model.
|
|
|
|
Stores learned facts as subject-predicate-object triples:
|
|
- "FastAPI" - "uses" - "Starlette framework"
|
|
- "Project Alpha" - "requires" - "OAuth authentication"
|
|
|
|
Facts have confidence scores that decay over time and can be
|
|
reinforced when the same fact is learned again.
|
|
"""
|
|
|
|
__tablename__ = "facts"
|
|
|
|
# Scoping: project_id is NULL for global facts
|
|
project_id = Column(
|
|
PGUUID(as_uuid=True),
|
|
ForeignKey("projects.id", ondelete="CASCADE"),
|
|
nullable=True,
|
|
index=True,
|
|
)
|
|
|
|
# Triple format
|
|
subject = Column(String(500), nullable=False, index=True)
|
|
predicate = Column(String(255), nullable=False, index=True)
|
|
object = Column(Text, nullable=False)
|
|
|
|
# Confidence score (0.0 to 1.0)
|
|
confidence = Column(Float, nullable=False, default=0.8, index=True)
|
|
|
|
# Source tracking: which episodes contributed to this fact (stored as JSON array of UUID strings)
|
|
source_episode_ids: Column[list] = Column(JSON, default=list, nullable=False)
|
|
|
|
# Learning history
|
|
first_learned = Column(DateTime(timezone=True), nullable=False)
|
|
last_reinforced = Column(DateTime(timezone=True), nullable=False)
|
|
reinforcement_count = Column(Integer, nullable=False, default=1)
|
|
|
|
# Vector embedding for semantic search
|
|
embedding = Column(Vector(1536) if Vector else Text, nullable=True)
|
|
|
|
# Relationships
|
|
project = relationship("Project", foreign_keys=[project_id])
|
|
|
|
__table_args__ = (
|
|
# Unique constraint on triple within project scope
|
|
Index(
|
|
"ix_facts_unique_triple",
|
|
"project_id",
|
|
"subject",
|
|
"predicate",
|
|
"object",
|
|
unique=True,
|
|
postgresql_where=text("project_id IS NOT NULL"),
|
|
),
|
|
# Query patterns
|
|
Index("ix_facts_subject_predicate", "subject", "predicate"),
|
|
Index("ix_facts_project_subject", "project_id", "subject"),
|
|
Index("ix_facts_confidence_time", "confidence", "last_reinforced"),
|
|
# Note: subject already has index=True on Column definition, no need for explicit index
|
|
# Data integrity constraints
|
|
CheckConstraint(
|
|
"confidence >= 0.0 AND confidence <= 1.0",
|
|
name="ck_facts_confidence_range",
|
|
),
|
|
)
|
|
|
|
def __repr__(self) -> str:
|
|
return (
|
|
f"<Fact {self.id} '{self.subject}' - '{self.predicate}' - "
|
|
f"'{self.object[:50]}...' conf={self.confidence:.2f}>"
|
|
)
|