| Name | Type | Description |
|---|---|---|
base_url | str | Default: 'http://localhost'The base url where Takeoff Inference Server is |
listening. Defaults to "http* | unknown | //localhost". |
port | int | Default: 3000What port is Takeoff Inference API listening on. |
mgmt_port | int | Default: 3001 |
models | List[ReaderConfig] | Default: [] |
| Name | Type |
|---|---|
| base_url | str |
| port | int |
| mgmt_port | int |
| models | List[ReaderConfig] |
Interface with Takeoff Inference API for embedding models.
Use it to send embedding requests and to deploy embedding readers with Takeoff.
What port is Takeoff Management API listening on.
Any readers you'd like to spin up on.
