diff --git a/Readme.md b/Readme.md index e69de29..d60ca55 100644 --- a/Readme.md +++ b/Readme.md @@ -0,0 +1,30 @@ + +# What is Docling ? +Docling simplifies document processing, parsing diverse formats โ€” including advanced PDF understanding โ€” and providing seamless integrations with the gen AI ecosystem. + +# Features +- ๐Ÿ—‚๏ธ Parsing of multiple document formats incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, WebVTT, images (PNG, TIFF, JPEG, ...), LaTeX, plain text, and more +- ๐Ÿ“‘ Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more +- ๐Ÿงฌ Unified, expressive DoclingDocument representation format +- โ†ช๏ธ Various export formats and options, including Markdown, HTML, WebVTT, DocTags and lossless JSON +- ๐Ÿ“œ Support of several application-specifc XML schemas incl. USPTO patents, JATS articles, and XBRL financial reports. +- ๐Ÿ”’ Local execution capabilities for sensitive data and air-gapped environments +- ๐Ÿค– Plug-and-play integrations incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI +- ๐Ÿ” Extensive OCR support for scanned PDFs and images +- ๐Ÿ‘“ Support of several Visual Language Models (GraniteDocling) +- ๐ŸŽ™๏ธ Audio support with Automatic Speech Recognition (ASR) models +- ๐Ÿ”Œ Connect to any agent using the MCP server +- ๐Ÿ’ป Simple and convenient CLI + +# What's new +- ๐Ÿ“ค Structured information extraction [๐Ÿงช beta] +- ๐Ÿ“‘ New layout model (Heron) by default, for faster PDF parsing +- ๐Ÿ”Œ MCP server for agentic applications +- ๐Ÿ’ผ Parsing of XBRL (eXtensible Business Reporting Language) documents for financial reports +- ๐Ÿ’ฌ Parsing of WebVTT (Web Video Text Tracks) files and export to WebVTT format +- ๐Ÿ’ฌ Parsing of LaTeX files +- ๐Ÿ“ Parsing of plain-text files (.txt, .text) and Markdown supersets (.qmd, .Rmd) +- ๐Ÿ“ Chart understanding (Barchart, Piechart, LinePlot): converting them into tables, code or adding detailed descriptions +Coming soon +- ๐Ÿ“ Metadata extraction, including title, authors, references & language +- ๐Ÿ“ Complex chemistry understanding (Molecular structures) \ No newline at end of file diff --git a/Readme.pdf b/Readme.pdf new file mode 100644 index 0000000..002de9d Binary files /dev/null and b/Readme.pdf differ diff --git a/doc/Notes.md b/doc/Notes.md index e451d8b..abae258 100644 --- a/doc/Notes.md +++ b/doc/Notes.md @@ -1,2 +1,53 @@ # Docing Testing +## Using Git on Forgejo Server + +## The Forgejo Server + +### Create project + +http://192.168.1.210:3000/stephen/137_Docing-Test + +this creates an empty repository + +### On remote site MacBook + +Open terminal on 01_Projects in the terminal + +```zsh +stephenlohning@Scotty 01_Projects % git clone http://192.168.1.210:3000/stephen/137_Docing-Test +Cloning into '137_Docing-Test'... +warning: You appear to have cloned an empty repository. +``` +This creates a directory called "137_Docing-Test" the same as the repository. There only one file in the directory + +```zsh +stephenlohning@Scotty 137_Docing-Test % ls -la +total 0 +drwxr-xr-x 3 stephenlohning staff 96 May 29 19:42 . +drwxr-xr-x@ 158 stephenlohning staff 5056 May 29 19:42 .. +drwxr-xr-x 9 stephenlohning staff 288 May 29 19:42 .git +stephenlohning@Scotty 137_Docing-Test % git remote -v +origin http://192.168.1.210:3000/stephen/137_Docing-Test (fetch) +origin http://192.168.1.210:3000/stephen/137_Docing-Test (push) +``` + +```zsh +stephenlohning@Scotty 137_Docing-Test % git branch -M main +stephenlohning@Scotty 137_Docing-Test % touch .gitignore +stephenlohning@Scotty 137_Docing-Test % git config --global push.followTags true +stephenlohning@Scotty 137_Docing-Test % +``` +### Create structure you want, template + +```zsh +stephenlohning@Scotty 137_Docing-Test % tree +. +โ”œโ”€โ”€ Readme.md +โ””โ”€โ”€ doc + โ”œโ”€โ”€ Notes.md + โ”œโ”€โ”€ Notes.pdf + โ””โ”€โ”€ images + +3 directories, 3 files +``` \ No newline at end of file diff --git a/doc/Notes.pdf b/doc/Notes.pdf index 449f2cf..04d3f00 100644 Binary files a/doc/Notes.pdf and b/doc/Notes.pdf differ