Загрузка видео...
Не удалось загрузить видео
Introducing Open Deep Research! A fully open-source Deep Research tool that: • writes comprehensive reports • does multi-hop search and reasoning • generates cover images & pod-casts! We’re releasing everything: evaluation dataset, code and blog.🔥 Example output report👇
66,469 просмотров • 1 год назад •via X (Twitter)
Комментарии: 9

📝 Blog: 🤗 Evaluation Dataset: 🖥️ GithHub:

Tech Stack for Open Deep Research: - @togethercompute for all the LLMs by @Meta, @deepseek_ai, @Alibaba_Qwen - @cartesia_ai - for text-to-speech model - @tavilyai - for the Web search API - @bfl_ml - for FLUX text-to-image model

Architecture We are releasing a deep-dive technical blog sharing practical tips and also the full codebase including all new features: - improved prompting and workflow implementation - cover images and pod-cast generation

We also evaluated the effect of the number of search steps in our Deep Research, and the configurability of our framework allows users freely to adjust the research budget depending on their use cases.

Our Deep Research tool can also output Mermaid JS charts to help with data visualization!

Impressive lineup — Love the commitment to open infrastructure. Curious to see how these models perform in multi-agent coordination and physical-world interfacing scenarios.

Wow... truly amazing. It even covers images & podcast generation.....😀

👏👏👏

Can AI redefine scientific discovery? Dr. Tal Patalon explores OpenAI’s Deep Research in her latest Forbes article. 🎨 Future by Eduardo Kobra, provided by Eden Gallery. @TalPatalon @forbes @edengallery_

