I created a graph storage from dozens of annual stories (with tables)
Changing PDFs to textual content was attainable however has by no means been simpler.
I lately created a graph knowledge retailer for use in an RAG. In different phrases, we constructed a GraphRAG.
Graph RAGs are a improbable different to different RAG apps like broadly used vector store-backed RAGs. They carry reasoning to the desk. For instance, with semantic similarity search (the approach utilized in vector shops to retrieve info), you might ask who the CFO of XYZ, Inc. was final 12 months. As a result of XYZ, Inc.’s final 12 months’s annual report would explicitly point out its CFO. However consider a query like this: Which two administrators of XYZ, inc. have studied in the identical college? The retrieval course of received’t be capable of fetch the related info with out mentioning a college identify. However graph RAG may do it.
Nonetheless, the important thing situation right here is how we assemble the graph for retrieval. I’ve addressed this situation in a separate submit lately. Considering one other step backward, how can we even put together the annual…
