Addepto/graph_builder
Open-source toolkit to extract structured knowledge graphs from documents and tables — power analytics, digital twins, and AI-driven assistants.
Extracts tabular data from unstructured documents (PDFs, reports) into in-memory graph structures using configurable entity and relationship schemas, then serves extraction via FastAPI REST endpoints with stateful graph persistence across requests. Built with Python 3.12+, it supports flexible header-based table extraction and integrates with chat platforms (Slack) and RAG systems for knowledge assistants. The roadmap includes vector DB integration, cross-source relationship discovery, and graph visualization dashboards.
No commits in the last 6 months.
Stars
98
Forks
19
Language
Python
License
MIT
Category
Last pushed
Sep 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Addepto/graph_builder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
MysterionRise/adaptive-knowledge-graph
AI-powered adaptive learning platform combining Knowledge Graphs, Local LLMs, and Bayesian skill...
bgokden/reasongraph
Graph-based reasoning library with embedding search, multi-hop traversal, and automatic entity extraction
vtmike2015/Graph-Based-Literature-Review-Tool
This Network-graph based literature review tool uses the open-source version of Neo4j with...
JessEnterprise/graphRAG-retrievers-agents
🚀 Explore GraphRAG by building customized retrievers and agents using Neo4j for advanced...
ma3u/neo4j-agentframework
🚀 Hybrid RAG: Local Neo4j + BitNet.cpp RAG System and Azure SaaS deployment. Fast vector search,...