ChatDOC
@chatdoc_ai
Followers
3K
Following
383
Media
152
Statuses
329
ChatGPT-based file-reading assistant🤖 Quickly extract, locate and summarize information from docs.🚀 Citations are presented for fact-checking 🔍
Joined March 2023
👏We just released OCRflux — a multimodel PDF-to-Markdown toolkit that handles multi-column layouts, table parsing & cross-page merging. 🔵Built on top of finetuning the multimodal LLM Qwen2.5-VL-3B-Instruct, it delivers 3× higher throughput on a GTX 3090 GPU than the
2
2
13
RT @karminski3: 卧槽, 真的 SOTA 了, 正在准备做一个 PDF 转 Markdown 的领域大模型评测, 结果我发现 ChatDOC 的 OCRFlux-3B 在我测试的所有场景均达到了现阶段最理想的效果. 下面直接为大家带来实测:. 场景A:. 让我们直….
0
140
0
🤩Seriously made our day seeing you dig our multi-lingual &column doc parsing! .👇Everyone come give it a spin and tell us what you think! #PDFparsing #OCRFlux #ocr #opensourceai.
PDF parsing is still painful because LLMs reorder text in complex layouts, break tables across pages, and fail on graphs or images. 💡Testing the new open-source OCRFlux model, and here the results are really good for a change. So OCRFlux is a multimodal, LLM based toolkit for
2
0
5
Thanks for the shoutout! 🙌 Even the messiest multi-page tables get stitched together perfectly by our magic. Try it yourself at
PDFの常識を変える？！🤯✨ 新ツール「OCRFlux」が登場しましたよ！.✎. FYIG: PDFをMarkdownに変換する新しいツール「OCRFlux」が発表されたそうです！これがもう、すごい機能満載なんですって！.
0
1
2
RT @csaba_kissi: This PDF-to-Markdown toolkit can convert PDFs and images into clean Markdown, parse complex tables, and much more. Open….
0
8
0
Horizontally split tables across pages? No problem for OCRflux! It recognizes and merges them seamlessly into one page. Check out👇.Try demo: #OCR #pdfparser #pdftomarkdown #OCRFlux #opensourceai
0
0
3
😩Extract tables from PDFs ＝ pure pain? Not anymore! OCRFlux transforms cross-page tables into structured ones, perfectly preserving layouts and auto-removing duplicate headers. Check out the comparison between olmOCR and OCRFlux 👇.Or try it at:
2
0
6
OCRFlux doesn’t just extract text—it understands semantic structure. 👉 Section titles.👉 Multi-Column Layouts.👉 Footnotes.It sees your PDF like a researcher would. Try demo: #OCR #OpenSource #OCRFlux #olmOCR
0
0
3
🥳OCRFlux shines in accuracy! It achieves significantly higher Edit Distance Similarity (EDS) and Tree Edit Distance-based Similarity (TEDS) scores compared to #olmOCR and #Nanonets. Try our demo: #OCRFlux #OCR #Benchmark
0
0
3
1. On each page:.- Convert multi-column layouts into clean text with natural reading order.- Precisely restore the format of complicated tables (i.e. column-span cells, row-span cells, merged cells).- Parse documents with mixed English and Chinese content. - output Latex
0
0
1
2. Merge cross-page paragraphs and tables includes: .- Table Header Repetition: When tables span multiple pages, the header row from the first page is repeated on subsequent pages. - Multi-Line Cell Splitting Cells: The initial lines appear on the preceding page, and remaining
1
0
2
Just dropped: Chatdoc now turns your highlights into HTML with preview. No coding needed. ✏️ Ask for:.– a flowchart.– an email layout.– a slick landing page.– a mini presentation. ⚡ Instantly get:.– Clean HTML.– Live preview.– Copy/download options.– Code linked back to the doc
0
0
2
🚀 Exciting News from ChatDOC! .Seamlessly translate your PDFs and Word documents into 25 languages, while keeping the original format intact. Here’s why you’ll love it: .📰Format Preservation: The layout stays exactly as it was—no more distorted formats. 📉Table Layout
0
0
2
We built ChatDOC for the moment when a messy PDF finally clicks. Because breakthroughs shouldn’t get lost in bad formatting. 🌌
0
0
1
👀Tired of guessing if AI made things up? .⚡️With TapSource in ChatDoc, just highlight text in the response to see EXACTLY where it came from. #ChatDoc #AItools #Productivity #FactCheck #AIinResearch
1
0
3
🎯📂"Half of research is knowing where to look. The other half is knowing when to stop looking.”.— Every grad student ever.Let ChatDOC help with both. #ChatDOC #AItools #Essaydue #chatpdf #AIstudytool
0
1
1
Sick of flipping through 80-page research papers for that one citation? Toss all your papers in ChatDOC and ask for quote. Seat back and watch it snag the exact line, no paraphrasing or guessing. Not Sure? You can highlight the text to view it's source for fact-checking! Try for
0
0
1
📢 ChatDOC PDF Parser Update – April 23. 🥳We are pleased to announce a new output option for the ChatDOC PDF Parser API: Markdown format is now supported, in addition to JSON. This enhancement enables developers to directly obtain well-structured Markdown content from PDF.
1
0
5
🚀 ChatPaper Update: WWW 2025 Papers Are Now Live!.We’ve just added papers from The 2025 ACM Web Conference (WWW 2025) to ChatPaper!.Explore the latest research in web technologies, AI, data mining, and more — all in a clean, searchable format. 🔎 Browse here:
0
0
1