Show HN: Graphora – Turn text documents into graph databases
Hi HN,
Built this after manually creating graph databases took me a few months at my last company.
Graphora converts unstructured text (documents, emails, reports) into graph databases automatically:
- Upload text → LLM extracts entities & relationships
- Handles entity resolution (same person, different names)
- Interactive ontology designer
- Exports to Neo4j (for now)
Demo: https://demo.graphora.io
You'll need to provide:
- Gemini API key (your own)
- 2 Neo4j instances for staging & Prod. [You can sign up for Free Aura]
All credentials encrypted.
Looking for feedback from anyone who's wrestled with turning messy text into structured relationship data. Let us know! How does it work when uploading documents later? let's say I uploaded a batch of 50 documents, then a week later I uploaded another 20. How does it ensure the correlation and context? The extraction happens based on a schema of nodes and edges. So, let's say you have 2 docs that have related data on a company, then they both will be connected. We use Entity resolution to combine them. So you need a pre-defined schema? and then when uploading, you assign which schema to use? Yes manually assigned for now. Future versions will have detection based on docs