Vectorize is a data platform designed to optimize retrieval augmented generation (RAG) by evaluating the best methods for vectorizing data and providing a cloud-scale RAG pipeline engine. This platform ensures that your vector database is populated and kept up-to-date with fresh vector data. It allows users to turn unstructured data into optimized vector search indexes, enhancing productivity and customer experiences through AI.
Vectorize simplifies the process of leveraging large language models (LLMs) on your data in three steps: importing data from various sources, evaluating multiple chunking and embedding strategies, and deploying the selected vector configuration into a real-time pipeline. The platform offers out-of-the-box connectors to popular knowledge repositories, collaboration tools, and CRMs, making it easy to transform organizational knowledge into generative AI.
By automatically creating and updating vector indexes in your preferred vector database, Vectorize ensures accurate and up-to-date search results. It empowers businesses to stay informed on the latest trends in generative AI, enabling them to build innovative AI applications quickly and efficiently.
Pricing
Vectorize offers three pricing plans:
-
Forever Free: Suitable for developers, includes 2 RAG evaluations, 1 RAG pipeline, 5 pipeline hours/month, 1 connector per pipeline, 1k reranking/10k total retrieval endpoint calls/month, and community support via Discord. Free until November 1, 2024, then $0.57/pipeline hour.
-
Starter: Designed for startups, includes 10 RAG evaluations, unlimited RAG pipelines, 2 connectors per pipeline, 3k reranking/30k total retrieval endpoint calls/month, and community support via Discord. Free until November 1, 2024, then $1.35/pipeline hour.
-
Pro: For enterprises, includes 25 RAG evaluations, unlimited RAG pipelines, 3 connectors per pipeline, 5k reranking/50k total retrieval endpoint calls/month, and 12x5 support with SLA. Pricing details available upon contact.