Skip to main content
This page uses Chat Completions for the chat model: base URL https://api.hilinkup.com/v1, final request POST /v1/chat/completions. Embeddings use /v1/embeddings separately.
Choose a Generic OpenAI or OpenAI-compatible LLM provider:
Verify a blank workspace chat before adding documents. Configure an embedding model separately, index one short document, and test retrieval with a question whose answer appears in that document.
A chat model ID cannot be used as an embedding model unless the model explicitly supports the embeddings endpoint.
Last modified on August 12, 2026