diff --git a/apps/www/_customers/mendableai.mdx b/apps/www/_customers/mendableai.mdx index 70fa0b0075b..2e0a171087d 100644 --- a/apps/www/_customers/mendableai.mdx +++ b/apps/www/_customers/mendableai.mdx @@ -31,7 +31,7 @@ about: Mendable.ai is Chat Powered Search for Documentation. Mendable.ai was experiencing tremendous success, with WAUs growing nearly 300% since March, and started looking for a tool to store and search through large amounts of vector data to improve the efficiency and accuracy of their similarity search operations for their Chat Powered Search for Documentation. They tried Faiss, Weviate, and Pinecone, but found them to be expensive and not very intuitive, especially when it came to storing metadata along with the vectors. Why they chose Supabase: -Mendable.ai discovered that Supabase supports pg_vector and found it to be a simple and cost-effective solution. They were impressed with the open-source nature of Supabase, as well as its ability to store metadata alongside the vectors. They also appreciated the intuitive interface and ease of use. +Mendable.ai discovered that Supabase supports pgvector and found it to be a simple and cost-effective solution. They were impressed with the open source nature of Supabase, as well as its ability to store metadata alongside the vectors. They also appreciated the intuitive interface and ease of use. We tried other vector databases - we tried Faiss, we tried Weviate, we tried Pinecone. We found @@ -41,11 +41,11 @@ Mendable.ai discovered that Supabase supports pg_vector and found it to be a sim ## What They Built -Using Supabase's pg_vector, Mendable.ai was able to build a more efficient and accurate search function for their AI chatbot. By storing vector data alongside metadata in Supabase, Mendable.ai was able to quickly and easily search through their customers documentation to find the most relevant responses to queries. They found that Supabase's solution was just as performant as dedicated vector databases, but without the high cost. +Using Supabase and pgvector, Mendable.ai was able to build a more efficient and accurate search function for their AI chatbot. By storing vector data alongside metadata in Supabase, Mendable.ai was able to quickly and easily search through their customers documentation to find the most relevant responses to queries. They found that Supabase's solution was just as performant as dedicated vector databases, but without the high cost. ## The Results -Thanks to Supabase's pg_vector, Mendable.ai was able to significantly improve the efficiency and accuracy of their Chat Powered Search for Documentation. They were able to build faster and more cost-effectively using Supabase’s open source stack. +Thanks to Supabase and pgvector, Mendable.ai was able to significantly improve the efficiency and accuracy of their Chat Powered Search for Documentation. They were able to build faster and more cost-effectively using Supabase’s open source stack. ## Tech stack