grobid 开源项目推荐（68 个）

titipata /scipdf_parser

Python PDF parser for scientific publications: content and figures

eLifePathways /sciencebeam-parser

A set of tools to allow PDF to XML conversion, utilising Apache Beam and other tools. The aim of this project is to bring multiple tools together to generate a full XML document.

ScienciaLAB /streamlit-pdf-viewer

Streamlit PDF viewer

YS0meone /Corvus

Multi-agent AI research system — finds academic papers via semantic search & citation snowballing, then answers questions over them using agentic RAG with self-reflection. Built with LangGraph, FastAPI, Celery, and Qdrant.

ScienciaLAB /structure-vision

Viewer for the structure extracted by Grobid on PDF documents

papercast-dev /papercast

A Python pipeline tool and plugin ecosystem for processing technical documents. Process papers from arXiv, SemanticScholar, PDF, with GROBID, LangChain, listen as podcast. Customize your own pipelines.

marcpinet /citracer

💬 Trace citation chains for any concept across research papers and render them as an interactive graph.

lfoppiano /grobid-superconductors

Grobid module for superconductor material and properties extraction

alisonmitchell /Biomedical-Knowledge-Graph

从非结构化文本中提取信息，利用传统自然语言处理到预训练的变换器和大型语言模型（用于NER和链接）等技术构建知识图谱，以及关系提取。

jacksongoode /NIME-proceedings-analyzer

A tool for the bibliographic analysis of the NIME proceedings archive

ram02z /grobid

Python library for serializing GROBID TEI XML to dataclass

Joshua-123-ansah /efficient-extraction-pipeline

Field-selective hybrid pipeline for extracting structured metadata from academic paper PDFs, combining GROBID with a large language model.

lfoppiano /supercon2

Staging-area for automatically collected experimental data for the SuperCon database with a curation interface with enhanced-document viewer and curation-ready interface

miku /grobidclient

A Go (golang) client for GROBID.

eliroc98 /zoteroRAG

Question-answering system for Zotero libraries with a 3-stage RAG pipeline: FAISS retrieval → CrossEncoder reranking → extractive QA. Features GROBID parsing, question expansion, multi-color PDF highlighting, and Streamlit interface. Ask questions, get answers with sources.

fs-ise /enlit

ENLIT is a tool that supports scholars in exploring new literature

tomMEM /RAG_with_LM-studio

RAG with LM studio, local LLMs, Scientific PDF text extraction,

fanzru /final-project-university

Final project as Computer Science Student at Telkom University || Stay tune guys at https://skripsi.fanzru.dev.

tmwclaxton /Grobid-Sidecar-App

Grobid couldn't thug it out... This is a Go sidecar app that spins up alongside a Grobid container and limits the flow of requests to it, as Grobid is quite fragile.

ankraj1234 /PaperStack

Smart research paper manager with metadata extraction, in-browser reading, and AI chat.