mirror of
https://github.com/blakeblackshear/frigate.git
synced 2025-02-18 00:16:41 +01:00
24ac9f3e5a
* swap sqlite_vec for chroma in requirements * load sqlite_vec in embeddings manager * remove chroma and revamp Embeddings class for sqlite_vec * manual minilm onnx inference * remove chroma in clip model * migrate api from chroma to sqlite_vec * migrate event cleanup from chroma to sqlite_vec * migrate embedding maintainer from chroma to sqlite_vec * genai description for sqlite_vec * load sqlite_vec in main thread db * extend the SqliteQueueDatabase class and use peewee db.execute_sql * search with Event type for similarity * fix similarity search * install and add comment about transformers * fix normalization * add id filter * clean up * clean up * fully remove chroma and add transformers env var * readd uvicorn for fastapi * readd tokenizer parallelism env var * remove chroma from docs * remove chroma from UI * try removing custom pysqlite3 build * hard code limit * optimize queries * revert explore query * fix query * keep building pysqlite3 * single pass fetch and process * remove unnecessary re-embed * update deps * move SqliteVecQueueDatabase to db directory * make search thumbnail take up full size of results box * improve typing * improve model downloading and add status screen * daemon downloading thread * catch case when semantic search is disabled * fix typing * build sqlite_vec from source * resolve conflict * file permissions * try build deps * remove sources * sources * fix thread start * include git in build * reorder embeddings after detectors are started * build with sqlite amalgamation * non-platform specific * use wget instead of curl * remove unzip -d * remove sqlite_vec from requirements and load the compiled version * fix build * avoid race in db connection * add scale_factor and bias to description zscore normalization
95 lines
2.8 KiB
Python
95 lines
2.8 KiB
Python
"""SQLite-vec embeddings database."""
|
|
|
|
import json
|
|
import logging
|
|
import multiprocessing as mp
|
|
import os
|
|
import signal
|
|
import threading
|
|
from types import FrameType
|
|
from typing import Optional
|
|
|
|
from setproctitle import setproctitle
|
|
|
|
from frigate.config import FrigateConfig
|
|
from frigate.const import CONFIG_DIR
|
|
from frigate.db.sqlitevecq import SqliteVecQueueDatabase
|
|
from frigate.models import Event
|
|
from frigate.util.services import listen
|
|
|
|
from .embeddings import Embeddings
|
|
from .maintainer import EmbeddingMaintainer
|
|
from .util import ZScoreNormalization
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def manage_embeddings(config: FrigateConfig) -> None:
|
|
# Only initialize embeddings if semantic search is enabled
|
|
if not config.semantic_search.enabled:
|
|
return
|
|
|
|
stop_event = mp.Event()
|
|
|
|
def receiveSignal(signalNumber: int, frame: Optional[FrameType]) -> None:
|
|
stop_event.set()
|
|
|
|
signal.signal(signal.SIGTERM, receiveSignal)
|
|
signal.signal(signal.SIGINT, receiveSignal)
|
|
|
|
threading.current_thread().name = "process:embeddings_manager"
|
|
setproctitle("frigate.embeddings_manager")
|
|
listen()
|
|
|
|
# Configure Frigate DB
|
|
db = SqliteVecQueueDatabase(
|
|
config.database.path,
|
|
pragmas={
|
|
"auto_vacuum": "FULL", # Does not defragment database
|
|
"cache_size": -512 * 1000, # 512MB of cache
|
|
"synchronous": "NORMAL", # Safe when using WAL https://www.sqlite.org/pragma.html#pragma_synchronous
|
|
},
|
|
timeout=max(60, 10 * len([c for c in config.cameras.values() if c.enabled])),
|
|
load_vec_extension=True,
|
|
)
|
|
models = [Event]
|
|
db.bind(models)
|
|
|
|
embeddings = Embeddings(db)
|
|
|
|
# Check if we need to re-index events
|
|
if config.semantic_search.reindex:
|
|
embeddings.reindex()
|
|
|
|
maintainer = EmbeddingMaintainer(
|
|
db,
|
|
config,
|
|
stop_event,
|
|
)
|
|
maintainer.start()
|
|
|
|
|
|
class EmbeddingsContext:
|
|
def __init__(self, db: SqliteVecQueueDatabase):
|
|
self.embeddings = Embeddings(db)
|
|
self.thumb_stats = ZScoreNormalization()
|
|
self.desc_stats = ZScoreNormalization(scale_factor=2.5, bias=0.5)
|
|
|
|
# load stats from disk
|
|
try:
|
|
with open(os.path.join(CONFIG_DIR, ".search_stats.json"), "r") as f:
|
|
data = json.loads(f.read())
|
|
self.thumb_stats.from_dict(data["thumb_stats"])
|
|
self.desc_stats.from_dict(data["desc_stats"])
|
|
except FileNotFoundError:
|
|
pass
|
|
|
|
def save_stats(self):
|
|
"""Write the stats to disk as JSON on exit."""
|
|
contents = {
|
|
"thumb_stats": self.thumb_stats.to_dict(),
|
|
"desc_stats": self.desc_stats.to_dict(),
|
|
}
|
|
with open(os.path.join(CONFIG_DIR, ".search_stats.json"), "w") as f:
|
|
json.dump(contents, f)
|