llmsherpa
grobid
llmsherpa | grobid | |
---|---|---|
6 | 12 | |
970 | 3,094 | |
16.2% | - | |
6.6 | 9.2 | |
7 days ago | 3 days ago | |
Jupyter Notebook | Java | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
llmsherpa
-
LlamaCloud and LlamaParse
To get good RAG performance you will need a good chunking strategy. Simply getting all the text is not good enough and knowing the boundaries of table, list, paragraph, section etc. is helpful.
Great work by llamaindex team. Also feel free to try https://github.com/nlmatics/llmsherpa which takes into account some of the things I mentioned.
-
Show HN: Open-source Rule-based PDF parser for RAG
I wrote about split points and the need for including section hierarchy in this post: https://ambikasukla.substack.com/p/efficient-rag-with-docume...
All this is automated in the llmsherpa parser https://github.com/nlmatics/llmsherpa which you can use as an API over this library.
grobid
- FLaNK-AIM Weekly 06 May 2024
- Show HN: Open-source Rule-based PDF parser for RAG
- How to ingest image based PDFs into private GPT model?
- 🥪 Best Sites For ebooks, articles, research papers etc..🥪
- Grobid – ML software for extracting information from scholarly documents
-
How to create a web app that turns academic papers into text documents
Interesting concept. Grobid tries to do the same https://github.com/kermitt2/grobid
-
Extract research paper`s references
I would suggest using grobid - a pipeline for extracting scientific PDFs into a common XML format which can be easily parsed. Grobid has quite a nice mature REST API that I've used in some of my own projects. It parses references and matches them to their DOI using the CrossRef API with a reported 95% F1 score. This should make your job pretty simple as far as I can tell - all you'd need to do is run your papers through grobid and then build a citation graph by comparing document DOIs.
- Free/open-source alternatives to Connected Papers...?
-
Seeking Advice: How to extract Abstract from scientific journals (.pdfs) 10k+.
Just use science-parse or GROBID. They have been designed for that exact reason.
-
Project to rebuild papers with plaintext markup languages
- I ended up using Grobid, which converts the PDF to a very detailed XML format. The format is not a word processing format though, but a format specifically for representing scientific documents. I don't know, if it would, for example, contain tags about bold or italicized text. The tool is working really well, but since you probably cannot use the output XML format directly, it will need some postprocessing, which would be relatively simple with XML parsing libraries.
What are some alternatives?
unstructured - Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
Parsr - Transforms PDF, Documents and Images into Enriched Structured Data
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
CERMINE - Content ExtRactor and MINEr
llama_parse - Parse files for optimal RAG
Smile - Statistical Machine Intelligence & Learning Engine
science-parse - Science Parse parses scientific papers (in PDF form) and returns them in structured form.
marker - Convert PDF to markdown quickly with high accuracy
datahub - The Metadata Platform for your Data Stack
paperetl - 📄 ⚙️ ETL processes for medical and scientific papers
Deep Java Library (DJL) - An Engine-Agnostic Deep Learning Framework in Java