Realtime analytics server for AI DIAL. The service consumes the logs stream AI DIAL Core, analyzes the conversation and writes the analytics to InfluxDB
Please remove the "MODEL_RATES" env variable from the Dockerfile as well. It confuses when the variable is declared empty by default in docs but actually being defined on container level.
Currently the rates (per-model prompt and completion prices) are read from
MODEL_RATES
env var.We need to pick the rates instead from the listing served by the core.
Note, that this issue must be resolved first: https://github.com/epam/ai-dial-core/issues/53