Update llm-semantic-cache-lookup-policy.md

added usages notes for score threshold values and vary-by for caching sensitive data.

Author: akamenev

articles/api-management/llm-semantic-cache-lookup-policy.md

@@ -68,6 +68,9 @@ Use the `llm-semantic-cache-lookup` policy to perform cache lookup of responses
 - This policy can only be used once in a policy section.
 - Fine-tune the value of `score-threshold` based on your application to ensure that the right sensitivity is used when determining which queries to cache. Start with a low value such as 0.05 and adjust to optimize the ratio of cache hits to misses.
 - The embeddings model should have enough capacity and sufficient context size to accommodate the prompt volume and prompts.
+- Score threshold above 0.2 may lead to cache mismatch. Consider using lower value for sensitive use cases.
+- Control cross-user access to cache entries by specifying `vary-by`with specific user or user-group identifiers.
+- Consider adding [llm-content-safety](./llm-content-safety-policy.md) policy with prompt shield to protect from prompt attacks.
 
 
 ## Examples