mimir Cache Performance
Real-time semantic cache metrics and analytics
API URL:
Connect
Hit Rate
--%
Total Requests
--
Avg Latency
--ms
Cache Hits
--
Cache Misses
--
Requests/min
--
Test Prompt
What is 2+2?
llama3.2:1b
gpt-4
gpt-3.5-turbo
Send
Traffic Generator
Requests:
Delay (ms):
Identical
Similar
Coding
DevOps
Random
Live Logs
Clear
Recent Requests
Time
Status
Similarity
Latency
Prompt
Hit Rate Over Time (%)
Latency Over Time (ms)
Latency Distribution
Similarity Distribution (Cache Hits)
Auto-refreshes every 5 seconds