forked from Rockachopa/Timmy-time-dashboard
@@ -16,11 +16,11 @@ class Settings(BaseSettings):
|
||||
ollama_url: str = "http://localhost:11434"
|
||||
|
||||
# LLM model passed to Agno/Ollama — override with OLLAMA_MODEL
|
||||
# qwen3.5:latest is the primary model — better reasoning and tool calling
|
||||
# qwen3:30b is the primary model — better reasoning and tool calling
|
||||
# than llama3.1:8b-instruct while still running locally on modest hardware.
|
||||
# Fallback: llama3.1:8b-instruct if qwen3.5:latest not available.
|
||||
# Fallback: llama3.1:8b-instruct if qwen3:30b not available.
|
||||
# llama3.2 (3B) hallucinated tool output consistently in testing.
|
||||
ollama_model: str = "qwen3.5:latest"
|
||||
ollama_model: str = "qwen3:30b"
|
||||
|
||||
# Context window size for Ollama inference — override with OLLAMA_NUM_CTX
|
||||
# qwen3:30b with default context eats 45GB on a 39GB Mac.
|
||||
@@ -28,12 +28,11 @@ class Settings(BaseSettings):
|
||||
ollama_num_ctx: int = 4096
|
||||
|
||||
# Fallback model chains — override with FALLBACK_MODELS / VISION_FALLBACK_MODELS
|
||||
# as comma-separated strings, e.g. FALLBACK_MODELS="qwen3.5:latest,llama3.1"
|
||||
# as comma-separated strings, e.g. FALLBACK_MODELS="qwen3:30b,llama3.1"
|
||||
# Or edit config/providers.yaml → fallback_chains for the canonical source.
|
||||
fallback_models: list[str] = [
|
||||
"llama3.1:8b-instruct",
|
||||
"llama3.1",
|
||||
"qwen3.5:latest",
|
||||
"qwen2.5:14b",
|
||||
"qwen2.5:7b",
|
||||
"llama3.2:3b",
|
||||
|
||||
Reference in New Issue
Block a user