WhyHow.AI

We are proud to announce that WhyHow.AI’s Knowledge Graph Studio now has an enterprise cloud-hosted solution, alongside the backend we open-sourced previously. In this article, we cover key benefits, pricing, and how to think about competing differences. For enterprises, the key benefits of the WhyHow Studio are: - JSON-based data ingestion for Knowledge Graph creation - Python-based APIs for easy interaction with LLM pipelines - Modular, multi-graph infrastructure - Multiplayer graph management and orchestration - Public case-studies with open-source code across a range of different industries & implementation patterns We are focused on providing services and processes to help enterprises ensure they have the data assets needed to build deterministic and reliable LLM systems. Contact us for support deploying the frontend and backend into your environment, and LLM architecture/Knowledge Graph construction support. Thomas Smoker Chris Rec https://lnkd.in/eCfncc4c

Learn how to build an intelligent legal document navigation system using multi-graph, multi-agent recursive retrieval! 🧠📄 This article demonstrates: 🔍 Creating document hierarchy and definition graphs 🤖 Implementing a multi-agent workflow for smart traversal 📊 Leveraging Reducto.AI, WhyHow.AI and LlamaIndex Key features: • Recursive retrieval of clauses and footnotes • Intelligent navigation through document hierarchy • Integration of legal definitions for context Read more: https://lnkd.in/gMUpuEN6 Or check out the repo: https://lnkd.in/g6hywXun

People want deterministic systems, and we are bringing back old ideas into the LLM age. The team at WhyHow.AI have built a Python-based reasoning and validation framework, inspired by Pydantic, that makes it simple for developers and non-technical domain experts to build complex rule and reasoning engines. One of the biggest problems that exist is creating constraints around how systems validate and reason about the information entering the system. As we consume more and more unstructured data through stochastic LLMs, the ability to enforce rules and guardrails become even more important. This process is easily extensible by developers, and we have fine-tuned a model that helps automate the construction of rules from natural language rules/SOP. We have also built a UI that allows for a human-in-the-loop experience for domain experts inserting rules in natural language, as well as developers approving the translated code into the rules engine. This symbolic reasoning and validation framework is useful where you are looking to turn SOPs and other business logic & guardrails into enforceable code. https://lnkd.in/erMf9D89 Chris Rec Thomas Smoker

We at WhyHow.AI believe strongly in the necessity for human-in-the-loop processes to structuring data, including graph structures, and share a bit more about our approach towards Knowledge Graph construction. Chris Rec Thomas Smoker https://lnkd.in/ehgg5RTw

You've heard of Knowledge Graphs. Do you need them? We'll tell you, and, if so, show you how. Otherwise we'll give you your time back. WhyHow.AI hit 1,000 followers recently (or at least a while back and we were too busy building to notice). Thank you! We started thinking more about what we stood for, and it is basically this: Graphs are one of many data structures in an LLM system. They can be used in many more ways than people expect, but how to architect your multi-agent system around graphs is not something most people are familiar with. Adopting Graphs are a bit like Agents. Easy to spin up. Hard to get right. We want to cut through the optimistic hype and pessimistic detractors to actually show how things can be done. This is why we put out real case studies detailing our step by step approach, with our workflows and the hours we put in to get things done - like this one here about medical transcript temporal graphs - https://lnkd.in/eYq6YBEf

Open-Sourcing the WhyHow Knowledge Graph Studio WhyHow.AI Knowledge Graph Studio can help users create Agentic RAG and modular knowledge graph workflows and applications. WhyHow invites the community to explore, experiment, and customize the WhyHow platform to meet their unique needs for Agentic RAG and modular knowledge graph workflows and applications. The open source repository includes the backend logic for running the knowledge graph studio including APIs, database and retrieval logic, prompts, etc. The key missing piece in many existing workflows is in overcoming the limitations of vector search by combining structured and unstructured search together, so that you can find semantically similar sections of information, and bring in all the linked information into the context window in a structured way. By being able to combine Text Chunks with Triples and Nodes, we are able to perform far more accurate, complete and deterministic information workflows as seen in these various case studies here (healthcare), here (legal), or here (finance). WhyHow’s query engine also takes in natural language questions that return the nodes, triples and linked vector chunks that are related to the answer. Part of the secret sauce of WhyHow’s query engine is that it embeds triples, and retrieves it through semantic similarity, taking into account all the relevant properties, relationships and text chunks that are linked accordingly. Embedded triples contain far richer data than simply attempting to retrieve embedded nodes. Link in comments. H/T Chia Jeng Yang For the latest #usecases and #innovation on all things #KnowledgeGraph #AI #GenAI #LLM #AgenticAI #EmergingTech #RAG #GraphRAG, join us in Connected Data London 2024: https://lnkd.in/d_mPvCiU

WhyHow.AI is excited to announce open sourcing our Knowledge Graph Studio platform, built on top of MongoDB. In the article, we talk about some of the unique aspects of WhyHow’s Knowledge Graph Studio like modular graph infrastructure for Agentic RAG systems that require modular segregated graphs, using our secret sauce of embedding triples and tying it to chunks to create a retrieval workflow that allows it to beat graph retrieval benchmarks like Text2Cypher by up to 2x, and to create unique Knowledge Graph structures like our recent case study on Temporal Graphs created through Medical Transcripts. We are aiming to be database agnostic and also working with a number of other partners to bring similar capabilities to other relational and graph databases. Like most OS platforms, our UI will be closed source. If you are interested in using the UI through an enterprise deployment or to get access to our hosted beta version, feel free to hit us up! Chris Rec Thomas Smoker https://lnkd.in/eXm5ghbW

Amazing brain trust in the room at our 2nd #GenAI Graph Gathering with a diverse set of thought leaders from startups like deepset, WhyHow.AI, Contextual AI, and Diffbot to enterprises like Meta Facebook, Microsoft, and Google and even foundations like The AI Alliance. This is great validation of the industry momentum behind #GraphRAG!