~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
"""Queued research model for managing research queue"""
from sqlalchemy import JSON, Boolean, Column, Integer, String
from sqlalchemy_utc import UtcDateTime, utcnow
from .base import Base
class QueuedResearch(Base):
"""Model to track queued research requests"""
__tablename__ = "queued_researches"
# Primary key
id = Column(Integer, primary_key=True, autoincrement=True)
# User and research identifiers
username = Column(String(100), nullable=False, index=True)
research_id = Column(String(36), nullable=False, unique=True) # UUID
# Research parameters
query = Column(String(1000), nullable=False)
mode = Column(String(50), nullable=False)
settings_snapshot = Column(JSON) # All research settings
# Queue metadata
position = Column(Integer, nullable=False) # Position in queue
created_at = Column(UtcDateTime, server_default=utcnow())
# Status
is_processing = Column(Boolean, default=False) # Being processed
def __repr__(self):
return f"<QueuedResearch(username={self.username}, research_id={self.research_id}, position={self.position})>"