DatattentionA TensorFlow Serving REST endpoint with no auth
Port 8501 accepts a predict call. Port 8500 is not open.
TensorFlow Serving REST is a predict API, not a chat API. The usual port is 8501. The path is /v1/models/<name>:predict. The body is JSON with an instances array. The answer is a predictions array.
There is no API key on this host's serving port. GET /v1/models/demo reports the model available. The gRPC port that often sits beside REST, 8500, is not published here. Do not point a gRPC client at it.
Chat clients should use the OpenAI or Ollama ports instead. A predict client should use the path below and a small instance so you can see the shape of the answer.
On this host
The open REST server is datattention.com port 8501. No API key.
curl http://datattention.com:8501/v1/models/demo
curl http://datattention.com:8501/v1/models/demo:predict \
-H 'Content-Type: application/json' \
-d '{"instances":[[1.0, 2.0]]}'The full list of ports and paths is on the endpoints page.