Pinecone and Amazon Web Services (AWS)

Amazon Bedrock provides access to pre-trained foundation models through an API, allowing users to experiment with different foundation models with the ability to easily finetune and augment them.

With this integration, AWS customers can quickly and effortlessly build search and GenAI applications with a workflow called Retrieval Augmented Generation (RAG). RAG powered by Pinecone ensures the most relevant, accurate, and fast responses to end users.

SageMaker is a machine learning service that allows data scientists and developers to easily build, train Large Language Models (LLMs), and then directly deploy them into a production-ready hosted environment.

The integration allows customers to use SageMaker compute and model hosting for LLMs and Pinecone as the knowledge base that keeps our LLMs up to date with the latest information to reduce hallucinations.

• Low latency and high throughput. Speed through data in milliseconds
• Quick and accurate results with real-time data freshness and metadata filtering
• Support both vector search and hybrid search
• Scale beyond billions of vectors cost-effectively without compromising performance

• Get started in seconds with our console that requires no AI expertise
• Fully managed service without the need to maintain infrastructure, or monitor services
• Intuitive APIs and SDKs
• Compatible with any LLMs

• Enterprise-grade security and compliance: GDPR-ready, SOC2 Type II certified, and HIPPA-compliant
• Data encryption in transit and at rest
• Stringent access controls
• Uptime and response time SLAs