Case Study: Firecrawl improves documentation search efficiency and accuracy with Supabase Vector

Firecrawl boosts chat search efficiency by 300% with Supabase

Firecrawl, a company providing chat-powered search for technical documentation, faced a challenge with storing and searching through large amounts of vector data as their user base grew rapidly. They needed a tool to improve the efficiency and accuracy of their similarity search operations. After trying expensive and unintuitive options like Pinecone, they chose Supabase Vector for its cost-effectiveness and ability to handle metadata alongside vectors.

Supabase implemented a solution using its Vector service, allowing Firecrawl to store vector data and metadata together in PostgreSQL. This enabled Firecrawl to build a more efficient and accurate search function for their AI chatbot. The results were a significant improvement in performance and accuracy for their chat-powered search, built faster and more cost-effectively. Supabase's solution was found to be just as performant, if not more, than dedicated vector databases.

Firecrawl