Qwen3-Embedding-0.6B -> how do I pass instructions to it?

[linuxd3v]

https://huggingface.co/Qwen/Qwen3-Embedding-0.6B - this embedding model.

Questions:

1. how do I pass instructions to it using llama.cpp embedding api?
   Is it similar to TEI instructions? would I use the same format in llama.cpp?:
   https://huggingface.co/Qwen/Qwen3-Embedding-0.6B#text-embeddings-inference-tei-usage

curl http://localhost:8080/embed \
    -X POST \
    -d '{"inputs": ["Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: What is the capital of China?", "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: Explain gravity"]}' \
    -H "Content-Type: application/json"

2. is "Instruct: X \n Query: X" format important?

3. Can I just use freestyle instructions format like this: ?
   Generate document embeddings like this:

"Represent this food blog post title for semantic search: Easy Homemade Pizza Recipe"

Generate for user searches like this:

"Encode this search query for retrieving food blog posts: quick pizza dough"