~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
Python academiaanthropicarxivbravedeep-researchencryptionhome-automationhomeserverlocallocal-deep-researchlocal-llmmistralollamaopenaipubmedresearchresearch-toolretrieval-augmented-generationsearxngself-hosted
"""
LLM provider and model management.
"""
from sqlalchemy import JSON, Column, Integer, String, UniqueConstraint
from sqlalchemy_utc import UtcDateTime, utcnow
from .base import Base
class ProviderModel(Base):
"""
Cache available models from all LLM providers.
"""
__tablename__ = "provider_models"
id = Column(Integer, primary_key=True)
provider = Column(String(50), nullable=False, index=True)
model_key = Column(String(255), nullable=False)
model_label = Column(String(255), nullable=False)
model_metadata = Column(JSON, nullable=True) # For additional model info
last_updated = Column(UtcDateTime, server_default=utcnow(), nullable=False)
# Composite unique constraint to prevent duplicates
__table_args__ = (
UniqueConstraint("provider", "model_key", name="uix_provider_model"),
)
def __repr__(self):
return (
f"<ProviderModel(provider={self.provider}, model={self.model_key})>"
)