We’re excited to announce a major upgrade to WhyHow.AI’s Knowledge Graph SDK with schema-controlled automated knowledge graphs. You can now create knowledge graphs that structure data based on your opinion. Upload a user-defined schema through JSON like this {“name”: “side effect”, “description”: “Harmful bodily effects that can be caused by using the medication. Examples of side effects are nausea, swelling, asthma, shock, blisters, rash, liver damage”}, upload your PDFs, and immediately get a knowledge graph that you can query against or plug into your existing RAG system. You can define, extract, store and query, anything and everything you want from your private data into graph structures, for more accurate, deterministic and memory/personalization-capable RAG systems. We are a workflow tool for data orchestration, and graph creation, and work on top of any data extraction model you want to bring. In this case, we work on top of unstructured.io, OpenAI, Neo4j, LangChain, and Pinecone, and will be supporting all data extraction models, LLMs, graph and vector databases. To be part of the Beta program for WhyHow.AI’s Knowledge Graph SDK, reach out to use at team@whyhow.ai or find a time with us at WhyHow.AI. https://medium.com/enterprise-rag/introducing-schema-controlled-automated-knowledge-graphs-02c7f00c3cf3