{"id":36283,"date":"2024-01-07T19:44:45","date_gmt":"2024-01-07T19:44:45","guid":{"rendered":"https:\/\/writer.com\/?page_id=36283"},"modified":"2024-07-09T20:06:30","modified_gmt":"2024-07-09T20:06:30","slug":"product-knowledge-graph","status":"publish","type":"page","link":"https:\/\/writer.com\/product\/graph-based-rag\/","title":{"rendered":"Knowledge Graph"},"content":{"rendered":"
\n
\n
\n
\n
KNOWLEDGE GRAPH<\/div>\n<\/div>\n<\/div>\n\n
\n
\n\n

An innovative approach to knowledge retrieval<\/h1>\n\n<\/div>\n\n
\n\n

Knowledge Graph, our graph-based retrieval-augmented generation (RAG), achieves higher accuracy than traditional RAG approaches that use vector retrieval.<\/p>\n\n<\/div>\n\n

\n
\nRequest a demo<\/a>\n<\/div>\n<\/div>\n<\/div>\n\n
\n
HOW IT WORKS<\/div>\n<\/div>\n\n
\n
\n
\n\n
\"Geometric<\/figure>\n\n<\/div>\n\n
\n
1<\/div>\n\n
\n\n

Richer semantic understanding<\/h3>\n\n\n\n

Knowledge Graph draws on a specialized LLM that\u2019s trained to process data at scale and build valuable semantic relationships between data points. It stores data in a cost-effective, easy-to-update graph structure.<\/p>\n\n<\/div>\n\n

\n What\u2019s the alternative approach? <\/a>\n\n
\n\n

The alternative approach<\/strong><\/p>\n\n\n\n

By converting data into vector embeddings, traditional RAG can only define similarity by distance between data points but has no context on their semantic relationships. Vector databases are also difficult and costly to maintain and update.<\/p>\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n\n

\n
\n\n
\"Digram<\/figure>\n\n<\/div>\n\n
\n
2<\/div>\n\n
\n\n

Accurate retrieval methodology<\/h3>\n\n\n\n

Because graph structures retain semantic relationships, Knowledge Graph accurately retrieves relevant data for each query. Our retrieval-aware compression technique condenses data and indexes it with metadata, which gives it rich context.<\/p>\n\n<\/div>\n\n

\n What\u2019s the alternative approach? <\/a>\n\n
\n\n

The alternative approach<\/strong><\/p>\n\n\n\n

Traditional RAG converts the query into a vector embedding and uses a rough algorithm to find the closest data points to the query, without any understanding of the relationship between the data points. When data is dense, this method fails to return the most relevant data consistently.<\/p>\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n\n

\n
\n\n
\"Palmyra<\/figure>\n\n<\/div>\n\n
\n
3<\/div>\n\n
\n\n

State-of-the-art LLMs<\/h3>\n\n\n\n

To generate a response, Knowledge Graph sends relevant data to our Palmyra LLMs, which are top-ranked<\/a> and trained with 1 trillion tokens of quality data. We apply advanced techniques to enhance performance and minimize hallucinations.<\/p>\n\n<\/div>\n\n

\n What\u2019s the alternative approach? <\/a>\n\n
\n\n

The alternative approach<\/strong><\/p>\n\n\n\n

The quality of the answer depends on the quality of the retrieval, and the level of hallucination depends on the quality of the underlying LLM and the techniques you employ.<\/p>\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n\n

\n\n

Want to learn more about the limitations of RAG approaches that uses vector retrieval?<\/p>\n\n\n\n\r\n Read the blog post<\/span>\r\n \r\n <\/path>\r\n <\/svg>\r\n <\/a>\n\n<\/div>\n<\/div>\n<\/div>\n\n\n

\n
\n
\n
\n
PERFORMANCE<\/div>\n<\/div>\n\n
\n\n

Knowledge Graph achieves unmatched accuracy<\/h2>\n\n\n\n

In a benchmarking study, Writer Knowledge Graph achieved top scores on RobustQA, which measures accuracy in open-domain question-answering, outperforming seven popular RAG approaches that use vector retrieval.<\/p>\n\n<\/div>\n<\/div>\n\n

\n
\n\n
\"\"<\/figure>\n\n<\/div>\n<\/div>\n\n
\n
\nLearn more<\/a>\n<\/div>\n<\/div>\n<\/div>\n<\/div><\/div><\/div>\n\n\n
\n
\n
\n
\n
USE CASES<\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n

Build digital assistants you can trust<\/h2>\n\n\n\n

Knowledge Graph anchors your generative AI solutions in your company knowledge. Create expert assistants for any use case and be confident that your people are getting the correct information.<\/p>\n\n\n

\n\n