WhyHow.AI

Extracting Information from Multiple Documents? WhyHow.AI is making Rule-Based Extraction cool again with our Open-Source Knowledge Table With the Rules Dashboard, we can now bulk upload a CSV of extraction rules that best conform to the way you want your data to be organized. This makes it easier to bulk-add Rules to your tables without having to manually edit each column, and increase the number of specified Entities that should and could be extracted. Coming up soon includes Rule Logging and Entity Resolution. Also - you can now directly copy and paste cells from an existing Excel or G.Sheet into Knowledge Table for data manipulation, creating a mini-Excel like experience for LLM-driven data cleaning and manipulation We also have a range of other cool UI updates so check it out at https://lnkd.in/eedZa6Qp Thomas Smoker Chris Rec https://lnkd.in/eav-EyPy

Dive into the possibilities of Generative AI with us at #NODES2024 with Andreas Kollegger, Ashleigh N. Faith from IsA DataThing YouTube Channel, Chia Jeng Yang from WhyHow.AI, and Lauren Sharman from One Peak. Let's explore not just how GenAI works but the problems it solves. Join our brilliant panelists as they share perspectives on investment, growth, and practice. https://bit.ly/3BQiA9r #Neo4j #GenAI

Check out how WhyHow.AI solve Chained Extraction through our ‘Split Cell Into Rows’ feature (a more powerful version of Split Text to Columns in Excel). Problem statement: What happens when each cell has a range of different values we want to extract and link the next column of values to? For example, we want to extract the People mentioned in a document, all the Companies they worked for, and then all the Job Titles they held for each Company. Each person may have a wide range of say 1–5 companies, and they may potentially have 1–2 Job Titles per Company. This is hard to represent in a table format, and invalidates all Table-based approach, which also immediately prevents non-technical people from easily contributing to the extraction process. You can now split each set of answers into individual rows, preserving the semantic connections of the extracted answer. With Knowledge Table, complex extraction and graph creation is made much easier.

Cool to see the growth of WhyHow.AI's Knowledge Table tool for an open-source Spreadsheet-based Multi-Document Extraction & Memory in the past 10 days. We're shipping a big upgrade to extend our current capabilities with Rule-Based Extraction, Resolution & Memory soon! Check it out here: https://lnkd.in/e3VufNbJ

Problem Statement: How do we choose the right document from thousands of our documents to retrieve information from in a RAG system? Open-Source Knowledge Table as a Document Metadata generation tool for File Directories. When we at WhyHow.AI were dealing with enterprise systems with thousands of documents, the first most obvious problem to solve for is about which of the documents are appropriate to answer the question, before we then look at the information in those documents to construct the answer in a 2-Step RAG process. This pattern is fairly common, but the biggest restriction here is in generating appropriate labels for documents. With Knowledge Table, one can easily generate and save custom and common metadata of your documents, and saving it in memory with just a single click. Chris Rec Thomas Smoker

What's better than GraphRAG? StructRAG! Imagine asking your AI assistant a complex question that requires piecing together information from multiple sources. With current methods, the AI often struggles to find and connect the relevant bits of information scattered across various documents. But what if the AI could automatically organize that raw information into a clear knowledge structure optimized for the task at hand? That's the key idea behind StructRAG, a new framework that aims to replicate how humans tackle knowledge-intensive reasoning. And here's how it works: 1. StructRAG first identifies the best way to structure the knowledge for the specific task, such as a table, graph, or tree. 2. It then reconstructs the original documents into this structured format, making it easier to see connections and relationships between pieces of information. 3. Finally, it uses this structured knowledge to infer the answer to the original question. StructRAG outperforms existing methods on a range of challenging reasoning tasks that require combining multiple facts and insights. For example, it excels at open-ended science questions that require understanding complex processes and piecing together evidence from multiple studies. By mimicking how humans organize information to solve problems, they were able to match - or even surpass - GraphRAG while being much faster. ↓ Liked this post? Join my newsletter with 50k+ readers that breaks down all you need to know about the latest LLM research: llmwatch.com 💡

What's better than GraphRAG? StructRAG! Imagine asking your AI assistant a complex question that requires piecing together information from multiple sources. With current methods, the AI often struggles to find and connect the relevant bits of information scattered across various documents. But what if the AI could automatically organize that raw information into a clear knowledge structure optimized for the task at hand? That's the key idea behind StructRAG, a new framework that aims to replicate how humans tackle knowledge-intensive reasoning. And here's how it works: 1. StructRAG first identifies the best way to structure the knowledge for the specific task, such as a table, graph, or tree. 2. It then reconstructs the original documents into this structured format, making it easier to see connections and relationships between pieces of information. 3. Finally, it uses this structured knowledge to infer the answer to the original question. StructRAG outperforms existing methods on a range of challenging reasoning tasks that require combining multiple facts and insights. For example, it excels at open-ended science questions that require understanding complex processes and piecing together evidence from multiple studies. By mimicking how humans organize information to solve problems, they were able to match - or even surpass - GraphRAG while being much faster. ↓ Liked this post? Join my newsletter with 50k+ readers that breaks down all you need to know about the latest LLM research: llmwatch.com 💡