mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-10-15 16:29:17 +00:00
2afffe8edc
Load sentence-transformers on the existing cache miss and construct the preloaded model off the shared background event loop. Start warm-up before chat restoration inside extensible init_a0, preserving start-hook control and sharing the loaded model with ordinary runtime requests. Remove unused speech preload imports and dead warm-up functions. Seed APT indexes only when absent, skipping the refresh on normal container boots. Keep the existing Python tunnel service and its provider lifecycle. Validation: 49 focused framework tests passed, including extension-hook short-circuit behavior, concurrent embedding-cache reuse, APT cache states, tunnel behavior and CSRF origins. Three cold Fable chat trials per version: median submit-to-first-token 9.588s -> 4.234s; local preparation 6.904s -> 1.197s; HTTP readiness 42.637s -> 41.139s; boot-to-first-token 52.093s -> 46.657s. Provider timing varies; these are local repeated measurements. The live baseline already omitted APT refresh, so it receives no timing credit.
31 lines
1,018 B
Python
31 lines
1,018 B
Python
import asyncio
|
|
from helpers import runtime
|
|
from helpers.print_style import PrintStyle
|
|
import models
|
|
|
|
|
|
async def preload():
|
|
try:
|
|
from plugins._model_config.helpers.model_config import get_embedding_model_config_object
|
|
|
|
emb_cfg = get_embedding_model_config_object()
|
|
if emb_cfg.provider.lower() == "huggingface":
|
|
# Model imports and construction must not block the shared background loop.
|
|
emb_mod = await asyncio.to_thread(
|
|
models.get_embedding_model,
|
|
emb_cfg.provider,
|
|
emb_cfg.name,
|
|
model_config=emb_cfg,
|
|
**emb_cfg.build_kwargs(),
|
|
)
|
|
await emb_mod.aembed_query("test")
|
|
PrintStyle().print("Preload completed.")
|
|
except Exception as e:
|
|
PrintStyle().error(f"Error in preload: {e}")
|
|
|
|
|
|
# preload the configured embedding model
|
|
if __name__ == "__main__":
|
|
PrintStyle().print("Running preload...")
|
|
runtime.initialize()
|
|
asyncio.run(preload())
|