$ show ResearAI/DeepReviewer-v2
DeepReviewer-v2 is a backend-only application designed for automated academic paper review. It processes PDF papers through a pipeline involving MinerU for markdown conversion, an LLM-based review agent with tool usage (e.g., paper search, annotation), and PDF report generation with annotated source overlays. The system operates asynchronously with job persistence, featuring a CLI for job submission, status tracking, and result retrieval. Optional integration with PASA (via vLLM) enables external paper search. The architecture is modular, separating concerns into adapters, tools, state management, and report generation components, all coordinated via an async runner.
The LLM identified 2 files worth highlighting for reuse:
Provides atomic file write utilities for JSON and text, along with append-only event logging. Ensures data integrity in concurrent environments and implements a reusable pattern for safe file operations and audit trails applicable to any application requiring crash-resistant storage.
Implements a thread-safe job state manager using RLock and atomic persistence. Handles loading, updating, and saving job state with file-based storage, offering a reusable pattern for managing state in long-running processes that require durability and concurrency safety.