viktor/fire-planner
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

examples: LLM_MODEL env var (default qwen3-8b; swap to qwen3vl-4b in K8s)

Browse source
This commit is contained in:
Viktor Barzin 2026-06-01 19:07:32 +00:00
parent 9b32247fea
commit 536f432a46
1 changed files with 6 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

7
fire_planner/examples/llm_extract.py
View file

@ -11,6 +11,7 @@ from __future__ import annotations
import json
import logging
import os
from decimal import Decimal, InvalidOperation
from typing import Any
@ -21,7 +22,11 @@ from fire_planner.examples.models import ExtractedExample, RawPost
log = logging.getLogger(__name__)
QWEN_MODEL = "qwen3-8b"
# `LLM_MODEL` lets the deployment swap to a smaller model when the GPU is
# contested. Default stays on qwen3-8b for local dev / tests. The "qwen" name
# in the constant is historical — the value can be any llama-swap model id
# (e.g. `qwen3vl-4b` when k8s-node1's VRAM is mostly held by immich-ml).
QWEN_MODEL = os.environ.get("LLM_MODEL", "qwen3-8b")
CLAUDE_AGENT_MODEL = "claude-haiku-4-5"
HTTP_TIMEOUT = httpx.Timeout(60.0)