LLM Stack is a platform that allows engineers to build, test and deploy LLM based APIs to production.

The core offerings of LLM Stack include :-

1. Managing custom endpoints with debugging and monitoring support
2. Create RAG supported endpoints with context based on the request
3. Create custom workflows by chaining multiple LLMs, Vector Stores and Integrations
4. Making available multiple options for LLMs, Vector Stores and Integrations

Currently LLM Stack is charged on a Pay-as-you-Go model. For more details contact on vaibhav@llmstack.dev or DM me on twitter.

No, your data is not stored in cloud. We only store the metadata in following cases :-

1. Request and response metadata is stored for debugging and monitoring purposes.
2. For Vector Stores, we store the Vector and its metadata.

LLM Stack is a cloud based platform. You can use it within your existing infrastructure directly by using our APIs. All the APIs generated can be accessed via REST. All details regarding the APIs can be found in the respective endpoint pages.