Anto01
b4afbbb53a
Complete implementation of the personal context engine foundation: - FastAPI server with 5 endpoints (ingest, query, context/build, health, debug) - SQLite database with 5 tables (documents, chunks, memories, projects, interactions) - Heading-aware markdown chunker (800 char max, recursive splitting) - Multilingual embeddings via sentence-transformers (EN/FR) - ChromaDB vector store with cosine similarity retrieval - Context builder with project boosting, dedup, and budget enforcement - CLI scripts for batch ingestion and test prompt evaluation - 19 unit tests passing, 79% coverage - Validated on 482 real project files (8383 chunks, 0 errors) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
99 lines
2.9 KiB
Python
99 lines
2.9 KiB
Python
"""SQLite database schema and connection management."""
|
|
|
|
import sqlite3
|
|
from contextlib import contextmanager
|
|
from pathlib import Path
|
|
from typing import Generator
|
|
|
|
from atocore.config import settings
|
|
from atocore.observability.logger import get_logger
|
|
|
|
log = get_logger("database")
|
|
|
|
SCHEMA_SQL = """
|
|
CREATE TABLE IF NOT EXISTS source_documents (
|
|
id TEXT PRIMARY KEY,
|
|
file_path TEXT UNIQUE NOT NULL,
|
|
file_hash TEXT NOT NULL,
|
|
title TEXT,
|
|
doc_type TEXT DEFAULT 'markdown',
|
|
tags TEXT DEFAULT '[]',
|
|
ingested_at DATETIME DEFAULT CURRENT_TIMESTAMP,
|
|
updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS source_chunks (
|
|
id TEXT PRIMARY KEY,
|
|
document_id TEXT NOT NULL REFERENCES source_documents(id) ON DELETE CASCADE,
|
|
chunk_index INTEGER NOT NULL,
|
|
content TEXT NOT NULL,
|
|
heading_path TEXT DEFAULT '',
|
|
char_count INTEGER NOT NULL,
|
|
metadata TEXT DEFAULT '{}',
|
|
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS memories (
|
|
id TEXT PRIMARY KEY,
|
|
memory_type TEXT NOT NULL,
|
|
content TEXT NOT NULL,
|
|
source_chunk_id TEXT REFERENCES source_chunks(id),
|
|
confidence REAL DEFAULT 1.0,
|
|
status TEXT DEFAULT 'active',
|
|
created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
|
|
updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS projects (
|
|
id TEXT PRIMARY KEY,
|
|
name TEXT UNIQUE NOT NULL,
|
|
description TEXT DEFAULT '',
|
|
status TEXT DEFAULT 'active',
|
|
created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
|
|
updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS interactions (
|
|
id TEXT PRIMARY KEY,
|
|
prompt TEXT NOT NULL,
|
|
context_pack TEXT DEFAULT '{}',
|
|
response_summary TEXT DEFAULT '',
|
|
project_id TEXT REFERENCES projects(id),
|
|
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
|
|
);
|
|
|
|
CREATE INDEX IF NOT EXISTS idx_chunks_document ON source_chunks(document_id);
|
|
CREATE INDEX IF NOT EXISTS idx_memories_type ON memories(memory_type);
|
|
CREATE INDEX IF NOT EXISTS idx_memories_status ON memories(status);
|
|
CREATE INDEX IF NOT EXISTS idx_interactions_project ON interactions(project_id);
|
|
"""
|
|
|
|
|
|
def _ensure_data_dir() -> None:
|
|
settings.data_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
|
|
def init_db() -> None:
|
|
"""Initialize the database with schema."""
|
|
_ensure_data_dir()
|
|
with get_connection() as conn:
|
|
conn.executescript(SCHEMA_SQL)
|
|
log.info("database_initialized", path=str(settings.db_path))
|
|
|
|
|
|
@contextmanager
|
|
def get_connection() -> Generator[sqlite3.Connection, None, None]:
|
|
"""Get a database connection with row factory."""
|
|
_ensure_data_dir()
|
|
conn = sqlite3.connect(str(settings.db_path))
|
|
conn.row_factory = sqlite3.Row
|
|
conn.execute("PRAGMA foreign_keys = ON")
|
|
try:
|
|
yield conn
|
|
conn.commit()
|
|
except Exception:
|
|
conn.rollback()
|
|
raise
|
|
finally:
|
|
conn.close()
|