Ask HN: How to send context when you use LLMs via API for a B2B use-case?

In B2B use-case, we pass on the data to LLMs via API and get the answers and display to the users. It's like a wrapper on top of LLM API. But since API calls are one-off, there dont have much context about a whole chat. How do you send so much of context when communicating with GPT via an API and not directly through chat. Wondering this for a B2B saas use-case.