type
status
slug
summary
tags
category
password
date
icon
  1. open-deep-research github 仓库
Open source alternative to Gemini Deep Research. Generate reports with AI based on search results.
  1. Agent Open Deep Research
A new agentic capability that conducts multi-step research on the internet for complex tasks.
notion image
  1. Why build deep research
深度研究是为那些在金融、科学、政策和工程等领域进行密集知识工作的人员而构建的,他们需要全面、精确和可靠的研究。它同样对那些寻找超个性化购买建议的精明购物者非常有用,这些购买通常需要仔细研究,比如汽车、电器和家具。每个输出都有完整的文档记录,包含清晰的引用和思考总结,使得引用和验证信息变得容易。它特别擅长寻找小众的、非直观的信息,这些信息通常需要浏览多个网站。深度研究通过允许您仅用一个查询就能卸载和加速复杂、耗时的网络研究,从而节省宝贵的时间。
To accomplish this, it was trained on real-world tasks requiring browser and Python tool use, using the same reinforcement learning methods behind OpenAI o1, our first reasoning model. While o1 demonstrates impressive capabilities in coding, math, and other technical domains, many real-world challenges demand extensive context and information gathering from diverse online sources. Deep research builds on these reasoning capabilities to bridge that gap, allowing it to take on the types of problems people face in work and everyday life.
notion image
  1. How it works
Deep research was trained using end-to-end reinforcement learning on hard browsing and reasoning tasks across a range of domains.
Through that training, it learned to plan and execute a multi-step trajectory to find the data it needs, backtracking and reacting to real-time information where necessary. The model is also able to browse over user uploaded files, plot and iterate on graphs using the python tool, embed both generated graphs and images from websites in its responses, and cite specific sentences or passages from its sources. As a result of this training, it reaches new highs on a number of public evaluations focused on real-world problems.
深度研究通过端到端的强化学习,在多个领域的困难浏览和推理任务上进行了训练。通过这种训练,它学会了规划和执行多步骤轨迹,以找到所需的数据,并在必要时进行回溯和对实时信息作出反应。该模型还能够浏览用户上传的文件,使用 python 工具绘制和迭代图表,在其响应中嵌入生成的图表和来自网站的图像,并引用其来源中的特定句子或段落。由于这种训练,它在多个关注现实世界问题的公共评估中达到了新的高点。
  1. evaluation dataset
GAIA:a public benchmark that evaluates AI on real-world questions, the model powering deep research reaches a new state of the art (SOTA)
  1. 限制
Deep research unlocks significant new capabilities, but it’s still early and has limitations. It can sometimes hallucinate facts in responses or make incorrect inferences, though at a notably lower rate than existing ChatGPT models, according to internal evaluations. It may struggle with distinguishing authoritative information from rumors, and currently shows weakness in confidence calibration, often failing to convey uncertainty accurately. At launch, there may be minor formatting errors in reports and citations, and tasks may take longer to kick off. We expect all these issues to quickly improve with more usage and time.
  1. 现有的框架
它提供与多个 AI 平台的无缝集成,包括 Google、OpenAI、Anthropic、DeepSeek,甚至本地模型——让您可以自由选择最适合您特定研究需求的 AI 模型。
  1. Search Results Retrieval: Using either Google Custom Search or Bing Search API (configurable), the app fetches comprehensive search results for the specified search term.
  1. Content Extraction: Leveraging JinaAI, it retrieves and processes the contents of the selected search results, ensuring accurate and relevant information.
  1. Report Generation: With the curated search results and extracted content, the app generates a detailed report using your chosen AI model (Gemini, GPT-4, Sonnet, etc.), providing insightful and synthesized output tailored to your custom prompts.
  1. Knowledge Base: Save and access your generated reports in a personal knowledge base for future reference and easy retrieval.RAG
关键的能力:
🌳Deep Research Trees: Start with a topic and automatically generate relevant follow-up questions to explore deeper aspects
🔄 Recursive Exploration: Follow research paths down various "rabbit holes" by generating new queries from report insights
🔍 Visual Research Mapping: See your entire research journey mapped out visually, showing connections between different research paths
🎯Smart Query Generation: AI-powered generation of follow-up research questions based on report content
🔗 Report Consolidation: Select multiple related reports and combine them into a single, comprehensive final report
📊Interactive Interface: Drag, arrange, and organize your research flows visually
  1. 简化的版本
Python程序设计NLP 自然语言处理
Loading...
fufu酱
fufu酱
一个爱折腾的大学生
公告
👋
欢迎 欢迎来到fufu酱的blog! 💞️我是22级浙江大学竺可桢学院计算机科学与技术专业的学生 一个爱折腾的大学生 🌱我会在这个网站上更新我的笔记和工具分享 🌈目前all in MLLM 📫你可以用下面的方式联系到我
🍀
今後ともよろしくお願いします