WhyHow.AI Platform Beta Update — SDK for programmatic flows
WhyHow.AI is a modular platform that works seamlessly with your existing pipelines, and be useful for devs and non-technical experts
Messy Problems
We find messy problems in tech business models and map out frameworks to understand them.
Dormant Last read · last published · next check
Read 3 days ago and current, but nothing has been published for 2 years.
Latest posts
Multiplayer Knowledge Graph Creation, Expert-Led Human Labeling & Neuro-symbolic AI
How Multiplayer Knowledge Graph Creation is helping to turn Domain Expertise Knowledge into Machine-Readable Data
5 Misconceptions of KG & RAG Systems - Building & Using RAG-Native Graphs
RAG-Native Graph Creation have differences from traditional graph creation, covering the realities of the role of network-type data, multi-hop retrieval & graph analytics, large vs small graphs, etc.
Tables/CSVs to Graphs: WhyHow.AI SDK
With this update, you can now create graphs in 3 different ways, depending on how exploratory or pre-defined you want your schema to be.
Understanding the type of Knowledge Graph you need - Fixed vs Dynamic Schema/Data
Fixed vs dynamic data and schemas result in different types of knowledge graphs that you may need.
Introducing Schema Controlled Automated Knowledge Graphs
Through our "Understand" Knowledge Graph SDK, we are building tools to help you structure your data with your opinion.
WhyHow.AI's Knowledge Graph Creation SDK - "Understand"
Using your sample questions as the basis for Knowledge Graph creation, simplifying the creation of structured and deterministic knowledge representation, while capturing only the info you care about.
Deterministic Document Structure based Retrieval
Capturing document structures for deterministic rule-based RAG traversals as the next step for semantic information extraction.
Open-Sourcing Deterministic Rule-based Retrieval for RAG
WhyHow.AI builds developer tools to bring more accuracy and determinism to AI solutions, including graph technologies.
Improving LLMs: ETL to "ECL" (Extract-Contextualize-Load)
As LLMs turn turn data processing into semantic processing, we believe ETL processes will turn into ECL processes, and that a range of tooling will emerge to support such processes.