Task sequence and RAG LLM improvements

This commit is contained in:
Renn F
2026-01-01 22:15:23 +01:00
parent 3c439d4673
commit 16dda8134b
25 changed files with 2244 additions and 375 deletions
+11 -8
View File
@@ -165,24 +165,27 @@ class Settings(BaseSettings):
openai_api_key: str | None = None # For embeddings
# Default models
default_llm_model: str = "claude-opus-4-5-20251101"
default_embedding_model: str = Field(
default="BAAI/bge-base-en-v1.5",
description="Embedding model",
default="embeddinggemma:300m",
description="Embedding model (Ollama model name)",
)
embedding_dimensions: int = Field(
default=768,
description="Embedding dimensions (768 for BGE-base)",
description="Embedding dimensions (768 for embeddinggemma/BGE-base)",
)
# Local LLM for RAG (HyDE, reranking, etc.)
local_llm_model: str = Field(
default="qwen3:8b",
description="Local LLM model for HyDE and RAG operations",
default="gemma3:4b",
description="Local LLM for HyDE/RAG (non-thinking models are faster)",
)
local_llm_base_url: str = Field(
default="http://192.168.50.111:11434/v1",
description="Base URL for local LLM (Ollama)",
default="http://roboco-ollama:11434/v1",
description="Base URL for local LLM (Ollama OpenAI-compat API)",
)
ollama_base_url: str = Field(
default="http://roboco-ollama:11434",
description="Base URL for Ollama native API (embeddings, model mgmt)",
)
# ==========================================================================