added fetch-paper function so we can fetch single papers if needed

check_db.py

@@ -0,0 +1,16 @@
+import asyncio
+from src.storage.paper_store import PaperStore
+
+async def check_papers():
+    store = PaperStore()
+    await store.initialize()
+    papers = await store.get_all_papers()
+    print('Papers in PostgreSQL:', len(papers))
+    if papers:
+        print('\nPaper IDs:')
+        for paper in papers:
+            print(f"- {paper['id']}")
+    await store.close()
+
+if __name__ == "__main__":
+    asyncio.run(check_papers())

papers/2501_12948v1.json

@@ -0,0 +1,213 @@
+{
+  "entry_id": "http://arxiv.org/abs/2501.12948v1",
+  "title": "DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning",
+  "authors": [
+    "DeepSeek-AI",
+    "Daya Guo",
+    "Dejian Yang",
+    "Haowei Zhang",
+    "Junxiao Song",
+    "Ruoyu Zhang",
+    "Runxin Xu",
+    "Qihao Zhu",
+    "Shirong Ma",
+    "Peiyi Wang",
+    "Xiao Bi",
+    "Xiaokang Zhang",
+    "Xingkai Yu",
+    "Yu Wu",
+    "Z. F. Wu",
+    "Zhibin Gou",
+    "Zhihong Shao",
+    "Zhuoshu Li",
+    "Ziyi Gao",
+    "Aixin Liu",
+    "Bing Xue",
+    "Bingxuan Wang",
+    "Bochao Wu",
+    "Bei Feng",
+    "Chengda Lu",
+    "Chenggang Zhao",
+    "Chengqi Deng",
+    "Chenyu Zhang",
+    "Chong Ruan",
+    "Damai Dai",
+    "Deli Chen",
+    "Dongjie Ji",
+    "Erhang Li",
+    "Fangyun Lin",
+    "Fucong Dai",
+    "Fuli Luo",
+    "Guangbo Hao",
+    "Guanting Chen",
+    "Guowei Li",
+    "H. Zhang",
+    "Han Bao",
+    "Hanwei Xu",
+    "Haocheng Wang",
+    "Honghui Ding",
+    "Huajian Xin",
+    "Huazuo Gao",
+    "Hui Qu",
+    "Hui Li",
+    "Jianzhong Guo",
+    "Jiashi Li",
+    "Jiawei Wang",
+    "Jingchang Chen",
+    "Jingyang Yuan",
+    "Junjie Qiu",
+    "Junlong Li",
+    "J. L. Cai",
+    "Jiaqi Ni",
+    "Jian Liang",
+    "Jin Chen",
+    "Kai Dong",
+    "Kai Hu",
+    "Kaige Gao",
+    "Kang Guan",
+    "Kexin Huang",
+    "Kuai Yu",
+    "Lean Wang",
+    "Lecong Zhang",
+    "Liang Zhao",
+    "Litong Wang",
+    "Liyue Zhang",
+    "Lei Xu",
+    "Leyi Xia",
+    "Mingchuan Zhang",
+    "Minghua Zhang",
+    "Minghui Tang",
+    "Meng Li",
+    "Miaojun Wang",
+    "Mingming Li",
+    "Ning Tian",
+    "Panpan Huang",
+    "Peng Zhang",
+    "Qiancheng Wang",
+    "Qinyu Chen",
+    "Qiushi Du",
+    "Ruiqi Ge",
+    "Ruisong Zhang",
+    "Ruizhe Pan",
+    "Runji Wang",
+    "R. J. Chen",
+    "R. L. Jin",
+    "Ruyi Chen",
+    "Shanghao Lu",
+    "Shangyan Zhou",
+    "Shanhuang Chen",
+    "Shengfeng Ye",
+    "Shiyu Wang",
+    "Shuiping Yu",
+    "Shunfeng Zhou",
+    "Shuting Pan",
+    "S. S. Li",
+    "Shuang Zhou",
+    "Shaoqing Wu",
+    "Shengfeng Ye",
+    "Tao Yun",
+    "Tian Pei",
+    "Tianyu Sun",
+    "T. Wang",
+    "Wangding Zeng",
+    "Wanjia Zhao",
+    "Wen Liu",
+    "Wenfeng Liang",
+    "Wenjun Gao",
+    "Wenqin Yu",
+    "Wentao Zhang",
+    "W. L. Xiao",
+    "Wei An",
+    "Xiaodong Liu",
+    "Xiaohan Wang",
+    "Xiaokang Chen",
+    "Xiaotao Nie",
+    "Xin Cheng",
+    "Xin Liu",
+    "Xin Xie",
+    "Xingchao Liu",
+    "Xinyu Yang",
+    "Xinyuan Li",
+    "Xuecheng Su",
+    "Xuheng Lin",
+    "X. Q. Li",
+    "Xiangyue Jin",
+    "Xiaojin Shen",
+    "Xiaosha Chen",
+    "Xiaowen Sun",
+    "Xiaoxiang Wang",
+    "Xinnan Song",
+    "Xinyi Zhou",
+    "Xianzu Wang",
+    "Xinxia Shan",
+    "Y. K. Li",
+    "Y. Q. Wang",
+    "Y. X. Wei",
+    "Yang Zhang",
+    "Yanhong Xu",
+    "Yao Li",
+    "Yao Zhao",
+    "Yaofeng Sun",
+    "Yaohui Wang",
+    "Yi Yu",
+    "Yichao Zhang",
+    "Yifan Shi",
+    "Yiliang Xiong",
+    "Ying He",
+    "Yishi Piao",
+    "Yisong Wang",
+    "Yixuan Tan",
+    "Yiyang Ma",
+    "Yiyuan Liu",
+    "Yongqiang Guo",
+    "Yuan Ou",
+    "Yuduan Wang",
+    "Yue Gong",
+    "Yuheng Zou",
+    "Yujia He",
+    "Yunfan Xiong",
+    "Yuxiang Luo",
+    "Yuxiang You",
+    "Yuxuan Liu",
+    "Yuyang Zhou",
+    "Y. X. Zhu",
+    "Yanhong Xu",
+    "Yanping Huang",
+    "Yaohui Li",
+    "Yi Zheng",
+    "Yuchen Zhu",
+    "Yunxian Ma",
+    "Ying Tang",
+    "Yukun Zha",
+    "Yuting Yan",
+    "Z. Z. Ren",
+    "Zehui Ren",
+    "Zhangli Sha",
+    "Zhe Fu",
+    "Zhean Xu",
+    "Zhenda Xie",
+    "Zhengyan Zhang",
+    "Zhewen Hao",
+    "Zhicheng Ma",
+    "Zhigang Yan",
+    "Zhiyu Wu",
+    "Zihui Gu",
+    "Zijia Zhu",
+    "Zijun Liu",
+    "Zilin Li",
+    "Ziwei Xie",
+    "Ziyang Song",
+    "Zizheng Pan",
+    "Zhen Huang",
+    "Zhipeng Xu",
+    "Zhongyu Zhang",
+    "Zhen Zhang"
+  ],
+  "summary": "We introduce our first-generation reasoning models, DeepSeek-R1-Zero and\nDeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement\nlearning (RL) without supervised fine-tuning (SFT) as a preliminary step,\ndemonstrates remarkable reasoning capabilities. Through RL, DeepSeek-R1-Zero\nnaturally emerges with numerous powerful and intriguing reasoning behaviors.\nHowever, it encounters challenges such as poor readability, and language\nmixing. To address these issues and further enhance reasoning performance, we\nintroduce DeepSeek-R1, which incorporates multi-stage training and cold-start\ndata before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1-1217\non reasoning tasks. To support the research community, we open-source\nDeepSeek-R1-Zero, DeepSeek-R1, and six dense models (1.5B, 7B, 8B, 14B, 32B,\n70B) distilled from DeepSeek-R1 based on Qwen and Llama.",
+  "pdf_url": "http://arxiv.org/pdf/2501.12948v1",
+  "categories": [
+    "cs.CL",
+    "cs.AI",
+    "cs.LG"
+  ]
+}

src/main.py

@@ -109,6 +109,47 @@ async def fetch_papers(days: int = 7, categories: Optional[List[str]] = None) ->
             logger.error(f"Error fetching papers: {e}")
             raise
 
+async def fetch_single_paper(paper_id: str) -> None:
+    """Fetch and analyze a single paper by ID."""
+    print(f"\nFetching paper: {paper_id}")
+    
+    async with ArxivClient() as client, AgentController() as agent:
+        try:
+            # Get paper from arXiv
+            paper = await client.get_paper_by_id(paper_id)
+            if not paper:
+                print(f"\nPaper {paper_id} not found on arXiv.")
+                return
+            
+            print(f"\nFound paper: {paper['title']}")
+            print(f"Authors: {', '.join(paper['authors'])}")
+            
+            # Analyze the paper
+            analysis = await agent.analyze_paper(paper)
+            if analysis:
+                print("\nAnalysis:")
+                print("=" * 80)
+                print("\nSummary:")
+                print(analysis.get('summary', 'No summary available'))
+                
+                print("\nTechnical Concepts:")
+                print(analysis.get('technical_concepts', 'No technical concepts available'))
+                
+                fluff = analysis.get('fluff', {})
+                score = fluff.get('score')
+                if score is not None:
+                    color = '\033[92m' if score < 30 else '\033[93m' if score < 70 else '\033[91m'
+                    reset = '\033[0m'
+                    print(f"\nFluff Score: {color}{score}/100{reset}")
+                    print("Analysis:")
+                    print(fluff.get('explanation', 'No explanation available'))
+            else:
+                print("\nPaper was already analyzed or an error occurred during analysis.")
+                
+        except Exception as e:
+            logger.error(f"Error processing paper: {e}")
+            raise
+
 async def process_query(query: str) -> None:
     """Process a search query and display results."""
     async with AgentController() as agent:
@@ -148,9 +189,39 @@ async def process_query(query: str) -> None:
             logger.error(f"Error processing query: {e}")
             raise
 
+async def search_arxiv(query: str, category: Optional[str] = None, max_results: int = 10) -> None:
+    """Search papers directly on arXiv."""
+    print(f"\nSearching arXiv for: {query}")
+    if category:
+        print(f"Category: {category}")
+    
+    async with ArxivClient() as client:
+        try:
+            papers = await client.fetch_papers(query=query, category=category, max_results=max_results)
+            
+            if not papers:
+                print("\nNo papers found matching your query.")
+                return
+                
+            print(f"\nFound {len(papers)} papers:")
+            print("=" * 80)
+            
+            for i, paper in enumerate(papers, 1):
+                print(f"\n{i}. {paper['title']}")
+                print(f"   Authors: {', '.join(paper['authors'])}")
+                print(f"   arXiv ID: {paper['entry_id']}")
+                print(f"   PDF: {paper['pdf_url']}")
+                print("\nAbstract:")
+                print(paper.get('abstract', 'No abstract available'))
+                print("-" * 80)
+                
+        except Exception as e:
+            logger.error(f"Error searching arXiv: {e}")
+            raise
+
 async def main():
     """Main application entry point."""
-    parser = argparse.ArgumentParser(description='Fetch and analyze arXiv papers')
+    parser = argparse.ArgumentParser(description='AI Paper Analysis System')
     subparsers = parser.add_subparsers(dest='command', help='Command to run')
     
     # Fetch papers command
@@ -160,16 +231,31 @@ async def main():
     fetch_parser.add_argument('--categories', nargs='+', default=['cs.AI'],
                             help='arXiv categories to fetch')
     
-    # Search papers command
-    search_parser = subparsers.add_parser('search', help='Search papers')
+    # Fetch single paper command
+    fetch_one_parser = subparsers.add_parser('fetch-paper', help='Fetch and analyze a single paper')
+    fetch_one_parser.add_argument('paper_id', help='arXiv paper ID (e.g., 2502.06788v1)')
+    
+    # Search local papers command
+    search_parser = subparsers.add_parser('search', help='Search papers in local database')
     search_parser.add_argument('query', help='Search query')
     
+    # Search arXiv directly command
+    arxiv_parser = subparsers.add_parser('arxiv-search', help='Search papers directly on arXiv')
+    arxiv_parser.add_argument('query', help='Search query')
+    arxiv_parser.add_argument('--category', help='arXiv category (e.g., cs.AI)')
+    arxiv_parser.add_argument('--max-results', type=int, default=10,
+                          help='Maximum number of results to return')
+    
     args = parser.parse_args()
     
     if args.command == 'fetch':
         await fetch_papers(days=args.days, categories=args.categories)
+    elif args.command == 'fetch-paper':
+        await fetch_single_paper(args.paper_id)
     elif args.command == 'search':
         await process_query(args.query)
+    elif args.command == 'arxiv-search':
+        await search_arxiv(args.query, args.category, args.max_results)
     else:
         parser.print_help()