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>
40 lines
817 B
Python
40 lines
817 B
Python
"""AtoCore configuration via environment variables."""
|
|
|
|
from pathlib import Path
|
|
|
|
from pydantic_settings import BaseSettings
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
debug: bool = False
|
|
data_dir: Path = Path("./data")
|
|
host: str = "127.0.0.1"
|
|
port: int = 8100
|
|
|
|
# Embedding
|
|
embedding_model: str = (
|
|
"sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
|
|
)
|
|
|
|
# Chunking
|
|
chunk_max_size: int = 800
|
|
chunk_overlap: int = 100
|
|
chunk_min_size: int = 50
|
|
|
|
# Context
|
|
context_budget: int = 3000
|
|
context_top_k: int = 15
|
|
|
|
model_config = {"env_prefix": "ATOCORE_"}
|
|
|
|
@property
|
|
def db_path(self) -> Path:
|
|
return self.data_dir / "atocore.db"
|
|
|
|
@property
|
|
def chroma_path(self) -> Path:
|
|
return self.data_dir / "chroma"
|
|
|
|
|
|
settings = Settings()
|