正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I packed-up a full-text paper scraper, vector database, and LLM into a CLI to answer questions from only highly-cited peer-reviewed papers. Feels unreal to be able instantly get answers by an LLM "reading" dozens of papers. 1/2

Andrew White 🐦‍⬛

32,612 subscribers

525,414 次观看 • 3 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

9 条评论

Andrew White 🐦‍⬛ 的头像

Andrew White 🐦‍⬛3 年前

Made with @LangChainAI, @OpenAI, textualize, FAISS, @SemanticScholar. Final frame (sorry no alt) 2/2

Andrew White 🐦‍⬛ 的头像

Andrew White 🐦‍⬛3 年前

@OpenAI @SemanticScholar Most of the code (except the interface) is already open source -

Karel Krápník Berka 的头像

Karel Krápník Berka3 年前

Can you ask it a question that bothers me about birds? Why are birds moving their heads in quick succession of interrupted rapid movements?

Teresa Kubacka 的头像

Teresa Kubacka3 年前

Cool! how did you come up with a decision to cut off lower cited papers and what threshold did you choose?

Andrew White 🐦‍⬛ 的头像

Andrew White 🐦‍⬛3 年前

It's a sort from influential citations and cut to 5 papers per search. No citation threshold.

Abdullah Al Nahid 的头像

Abdullah Al Nahid3 年前

Can the code be open-sourced Professor? I want to try too

ashish (@acgt01@genomic.social) 的头像

ashish (@[email protected])3 年前

Is it open sourced ? If not, can you try to open source it ?

Barrett Davis 的头像

Barrett Davis3 年前

I’m new to this stuff. Is there a way to do something similar by reading 10 websites ? Or do 10 websites need to be converted into text and then read

Andrew White 🐦‍⬛ 的头像

Andrew White 🐦‍⬛3 年前

Definitely possible

相关视频

We used Gemini 2 Flash to build Cursor for arXiv papers Highlight any section of a paper to ask questions and “@” other papers to quickly add to context and compare results, benchmarks, etc.

We used Gemini 2 Flash to build Cursor for arXiv papers Highlight any section of a paper to ask questions and “@” other papers to quickly add to context and compare results, benchmarks, etc.

alphaXiv

144,588 次观看 • 1 年前

How to extract data from papers for literature review in seconds? 1. Go to 2. Upload 2-3 papers you already know are relevant 3. Start with clicking on one paper 4. ResearchCollab do the following for the paper ✦ Provide a short overview of the paper ✦ Identify weaknesses in the paper ✦ Share papers that contrast the existing paper ✦ Extract meta data about the paper ✦ Evaluate each part (e.g., methodology) of the paper ✦ Provide AI chat to extract any other data 5. Now click on the Related Papers button at top right 6. You will get papers related to the seed paper 7. You can click on each paper and read its abstract 8. If you find it relevant, just add it to your list of papers 9. Do the same for the other 2 seed papers 10. This way you will collect all relevant papers 11. And extract data from those papers After this, analyse the data and report the findings. Try ResearchCollab today:

How to extract data from papers for literature review in seconds? 1. Go to 2. Upload 2-3 papers you already know are relevant 3. Start with clicking on one paper 4. ResearchCollab do the following for the paper ✦ Provide a short overview of the paper ✦ Identify weaknesses in the paper ✦ Share papers that contrast the existing paper ✦ Extract meta data about the paper ✦ Evaluate each part (e.g., methodology) of the paper ✦ Provide AI chat to extract any other data 5. Now click on the Related Papers button at top right 6. You will get papers related to the seed paper 7. You can click on each paper and read its abstract 8. If you find it relevant, just add it to your list of papers 9. Do the same for the other 2 seed papers 10. This way you will collect all relevant papers 11. And extract data from those papers After this, analyse the data and report the findings. Try ResearchCollab today:

Faheem Ullah

26,494 次观看 • 4 个月前

Introducing o3-mini for understanding arXiv papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

Introducing o3-mini for understanding arXiv papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

66,598 次观看 • 1 年前

Introducing Grok 4 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

Introducing Grok 4 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

88,375 次观看 • 11 个月前

Introducing GPT OSS for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

Introducing GPT OSS for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

29,502 次观看 • 10 个月前

Introducing GLM-5.1 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

Introducing GLM-5.1 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

30,882 次观看 • 2 个月前

Introducing Claude 4 Sonnet for understanding arXiv papers 🚀 Highlight any section of a paper to ask questions and “@” other papers to quickly add to context and compare results, benchmarks, etc.

Introducing Claude 4 Sonnet for understanding arXiv papers 🚀 Highlight any section of a paper to ask questions and “@” other papers to quickly add to context and compare results, benchmarks, etc.

alphaXiv

10,967 次观看 • 1 年前

arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and insights. Curated papers are indexed and power the artifacts. Agent convert papers to LLM wikis (based on Andrej Karpathy idea), which means insights are indexed and easily searchable and reusable. I feel like LLM Artifacts is the natural evolution to LLM Wikis. It's about making that knowledge actionable. Artifacts are customizable via agents. Artifacts can interact with agents and are dynamic in nature. Anything can be injected into the artifact as needed (insights, components, suggested experiments, action items, etc). I can take action on Artifact items with my agent orchestrator (Electron app). So I can ask questions about any paper and automate experiments in the background right from within the artifact. This is more than a visual. It's not a single prompt. It's several proactive agents coordinating to surface interesting facts, knowledge, and insights that I can act on a researcher. Agents are not just for generating useful artifacts, they are useful to keep learning and staying on the cutting edge of knowledge. Stay tuned for more.

arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and insights. Curated papers are indexed and power the artifacts. Agent convert papers to LLM wikis (based on Andrej Karpathy idea), which means insights are indexed and easily searchable and reusable. I feel like LLM Artifacts is the natural evolution to LLM Wikis. It's about making that knowledge actionable. Artifacts are customizable via agents. Artifacts can interact with agents and are dynamic in nature. Anything can be injected into the artifact as needed (insights, components, suggested experiments, action items, etc). I can take action on Artifact items with my agent orchestrator (Electron app). So I can ask questions about any paper and automate experiments in the background right from within the artifact. This is more than a visual. It's not a single prompt. It's several proactive agents coordinating to surface interesting facts, knowledge, and insights that I can act on a researcher. Agents are not just for generating useful artifacts, they are useful to keep learning and staying on the cutting edge of knowledge. Stay tuned for more.

elvis

58,541 次观看 • 1 个月前

Introducing Gemini 3 Flash for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

Introducing Gemini 3 Flash for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

48,596 次观看 • 6 个月前

Introducing Qwen 3 Reasoning for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

Introducing Qwen 3 Reasoning for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

24,011 次观看 • 10 个月前

Introducing Claude Sonnet 4.6 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

Introducing Claude Sonnet 4.6 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

49,066 次观看 • 4 个月前

Introducing GLM 5 Turbo for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

Introducing GLM 5 Turbo for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

23,361 次观看 • 3 个月前

Introducing Gemini 3 Pro for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

Introducing Gemini 3 Pro for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

50,001 次观看 • 7 个月前

Check this!! You can get LLM-ready text from ANY website in 2 mins. Using Firecrawl's /llmstxt endpoint, transform ANY website into clean LLM-ready text—by just specifying a URL. Use this data for RAG, training LLMs, and more. Everything is just 5 lines of code!

Check this!! You can get LLM-ready text from ANY website in 2 mins. Using Firecrawl's /llmstxt endpoint, transform ANY website into clean LLM-ready text—by just specifying a URL. Use this data for RAG, training LLMs, and more. Everything is just 5 lines of code!

Avi Chawla

12,936 次观看 • 1 年前

Would you give a microbiologist, with over 600 peer reviewed papers under his belt- less than 2 minutes of your time? Eye opening 👀

Would you give a microbiologist, with over 600 peer reviewed papers under his belt- less than 2 minutes of your time? Eye opening 👀

Jessica Rojas 🇺🇸💪

30,756 次观看 • 7 个月前

Consensus in an AI-powered search engine that answers your questions with reference to published papers. No hallucinations. No fake citations to papers that don't exist. Here is a new Consensus feature that will make your literature review faster and easier. Ask a question and Consensus will give you a list of relevant papers. You can filter papers by: • Year • Study Type (Meta Analysis, Literature Review, Systematic Review, Case Report, etc.) • Study Details (Controlled Study, Human Study, Sample Size) Here I am asking a question about how people self manage lower back pain. I am filtering papers so I only see meta analyses and systematic reviews published in 2020.

Consensus in an AI-powered search engine that answers your questions with reference to published papers. No hallucinations. No fake citations to papers that don't exist. Here is a new Consensus feature that will make your literature review faster and easier. Ask a question and Consensus will give you a list of relevant papers. You can filter papers by: • Year • Study Type (Meta Analysis, Literature Review, Systematic Review, Case Report, etc.) • Study Details (Controlled Study, Human Study, Sample Size) Here I am asking a question about how people self manage lower back pain. I am filtering papers so I only see meta analyses and systematic reviews published in 2020.

Mushtaq Bilal, PhD

115,743 次观看 • 2 年前

Don’t forget that Dr. Wolfe of ARCCA is an expert in Toyota/Lexus triggering events. He even wrote a peer reviewed paper about it. Lally objected in trial #1 but I have a feeling Karen Read’s defense will be able to get into it since they actually hired ARCCA this time around. #FreeKarenRead #FKR

Don’t forget that Dr. Wolfe of ARCCA is an expert in Toyota/Lexus triggering events. He even wrote a peer reviewed paper about it. Lally objected in trial #1 but I have a feeling Karen Read’s defense will be able to get into it since they actually hired ARCCA this time around. #FreeKarenRead #FKR

MAGA Barbie 🇺🇸👱🏼‍♀️

61,451 次观看 • 1 年前

Introducing Exa Research Papers MCP tool! Semantically search over 100M research papers and get their full text content. Learn how to use below:

Introducing Exa Research Papers MCP tool! Semantically search over 100M research papers and get their full text content. Learn how to use below:

Exa

79,890 次观看 • 1 年前

AI search for papers is here Search anything you want with papers Here are a few examples of what you can do: Semantically search by sentences & phrases. Example: evaluating factuality in LLM outputs Search by concepts. Example: latent diffusion Search by authors names. Example: Ilya Sutskever Hugging Face just crossed 50,000 papers (all the majors ones of the past two years should be covered), with dozens added every day & just enabled semantic search. It's becoming the best place to do collaborative research.

AI search for papers is here Search anything you want with papers Here are a few examples of what you can do: Semantically search by sentences & phrases. Example: evaluating factuality in LLM outputs Search by concepts. Example: latent diffusion Search by authors names. Example: Ilya Sutskever Hugging Face just crossed 50,000 papers (all the majors ones of the past two years should be covered), with dozens added every day & just enabled semantic search. It's becoming the best place to do collaborative research.

AK

35,896 次观看 • 1 年前