To facilitate Multi-Document Extraction and Memory, the team at WhyHow.AI are open-sourcing an internal table-based multi-document extraction tool called Knowledge Table, which has an agent within each cell to facilitate the extraction process. Controlling Extraction & Memory is now as easy as selecting your documents, running the set of questions you want against the documents selected, and saving it either in CSV or a Knowledge Graph. For devs, we have found that inserting an intermediary tabular step for answer construction in your backend RAG system dramatically improves the accuracy of the information extracted across multiple documents. Some unique features here include: • Vector chunks tied to each cell answer • Rules & Type-based extraction guardrails • Chained Extraction Logic through Cell-to-Cell references You should use Knowledge Table if you are interested in efficiently extracting, storing and querying information across a large set of documents, as a business user or a RAG developer. Between Knowledge Table & the WhyHow Platform, we provide: 1. Multi-Document Accuracy Uplift: 2.5x accuracy over ChatGPT 4o (web browser!) for multi-document retrieval, outperforming Text2Cypher by 2x, and beating GraphRAG. 2. Rule-Based Extraction Guardrails: Granular control of an open-source multi-document extraction process through Extraction Rules & Types 3. Ontology-Based Query Engine: An intuitive query engine that allows the user to call on both specific tools and columns directly when querying, allowing a seamless combination of both structured and unstructured retrieval Article overview: https://medium.com/enterprise-rag/knowledge-table-multi-document-rag-extraction-memory-ec08450e858f Demo: https://knowledge-table-demo.whyhow.ai/ Repo: https://github.com/whyhow-ai/knowledge-table