perplexity/Timmy-time-dashboard
Archived
1
0
Fork 0
forked from Rockachopa/Timmy-time-dashboard
Code Issues Pull Requests 1 Activity

fix: restore ollama as default backend to fix broken build (#161)

Browse Source
This commit is contained in:
Alexander Whitestone
2026-03-10 18:17:47 -04:00
committed by GitHub
parent 755b7e7658
commit 1de97619e8
2 changed files with 4 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/config.py
View File

@@ -41,13 +41,12 @@ class Settings(BaseSettings):
# "airllm" — always use AirLLM (requires pip install ".[bigbrain]")
# "auto" — use AirLLM on Apple Silicon if airllm is installed,
# fall back to Ollama otherwise
timmy_model_backend: Literal["ollama", "airllm", "grok", "claude", "auto"] = "airllm"
timmy_model_backend: Literal["ollama", "airllm", "grok", "claude", "auto"] = "ollama"
# AirLLM model size when backend is airllm or auto.
# Larger = smarter, but needs more RAM / disk.
# 8b ~16 GB | 70b ~140 GB | 405b ~810 GB
# Optimization: Llama-3.3-70B-Instruct-MLX is recommended for Mac M3 36GB.
airllm_model_size: str = "70b"
airllm_model_size: Literal["8b", "70b", "405b"] = "70b"
# ── Grok (xAI) — opt-in premium cloud backend ────────────────────────
# Grok is a premium augmentation layer — local-first ethos preserved.

8
src/timmy/backends.py
View File

@@ -23,10 +23,9 @@ from timmy.prompts import SYSTEM_PROMPT
logger = logging.getLogger(__name__)
# HuggingFace model IDs for each supported size.
# 70b is optimized for Mac M3 36GB using Llama-3.3-70B-Instruct-MLX.
_AIRLLM_MODELS: dict[str, str] = {
"8b": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"70b": "meta-llama/Llama-3.3-70B-Instruct-MLX",
"70b": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"405b": "meta-llama/Meta-Llama-3.1-405B-Instruct",
}
@@ -129,10 +128,7 @@ class TimmyAirLLMAgent:
# ── private helpers ──────────────────────────────────────────────────────
def _build_prompt(self, message: str) -> str:
from timmy.prompts import get_system_prompt
# AirLLM uses 70b by default which is tool-capable
system_prompt = get_system_prompt(tools_enabled=True)
context = system_prompt + "\n\n"
context = SYSTEM_PROMPT + "\n\n"
# Include the last 10 turns (5 exchanges) for continuity.
if self._history:
context += "\n".join(self._history[-10:]) + "\n\n"