Lucy
82328b0a45
REST API for per-agent semantic memory retrieval.
- FastAPI server with /api/{agent}/save and /api/{agent}/query
- ChromaDB for persistent vector storage
- all-MiniLM-L6-v2 via sentence-transformers for embeddings
- Per-agent collections for clean separation
- Config through env vars or config.py
- .venv ready with all dependencies
30 lines
815 B
Python
30 lines
815 B
Python
"""Embedding model wrapper — singleton pattern.
|
|
|
|
Uses sentence-transformers with all-MiniLM-L6-v2 (384-dim, ~80MB).
|
|
Loaded once, reused across all requests.
|
|
"""
|
|
|
|
from sentence_transformers import SentenceTransformer
|
|
from config import Config
|
|
|
|
|
|
class Embedder:
|
|
"""Thread-safe singleton wrapper for the embedding model."""
|
|
|
|
_instance = None
|
|
|
|
@classmethod
|
|
def get_instance(cls) -> "Embedder":
|
|
if cls._instance is None:
|
|
cls._instance = cls()
|
|
return cls._instance
|
|
|
|
def __init__(self) -> None:
|
|
self.model = SentenceTransformer(Config.EMBEDDING_MODEL)
|
|
|
|
def embed(self, text: str) -> list[float]:
|
|
return self.model.encode(text).tolist()
|
|
|
|
def embed_batch(self, texts: list[str]) -> list[list[float]]:
|
|
return self.model.encode(texts).tolist()
|