adding status field to model get response

clients/python/llmengine/data_types.py

@@ -201,6 +201,9 @@ class GetLLMEndpointResponse(BaseModel):
     source: LLMSource = Field(description="The source of the model, e.g. Hugging Face.")
     """The source of the model, e.g. Hugging Face."""
 
+    status: ModelEndpointStatus = Field(description="The status of the model.")
+    """The status of the model (can be one of "READY", "UPDATE_PENDING", "UPDATE_IN_PROGRESS", "UPDATE_FAILED", "DELETE_IN_PROGRESS")."""
+
     inference_framework: LLMInferenceFramework = Field(
         description="The inference framework used by the model."
     )

clients/python/llmengine/model.py

@@ -242,6 +242,7 @@ def get(
                 "name": "llama-2-7b.suffix.2023-07-18-12-00-00",
                 "model_name": null,
                 "source": "hugging_face",
+                "status": "READY",
                 "inference_framework": "text_generation_inference",
                 "inference_framework_tag": null,
                 "num_shards": null,

docs/api/data_types.md

@@ -35,6 +35,7 @@
             - inference_framework
             - id
             - model_name
+            - status
             - inference_framework_tag
             - num_shards
             - quantize

docs/guides/endpoint_creation.md

@@ -0,0 +1,15 @@
+When creating a model endpoint, you can periodically poll the model status field to
+track the status of your model endpoint. In general, you'll need to wait after the 
+model creation step for the model endpoint to be ready and available for use.
+An example is provided below: 
+
+*Assuming the user has created a model named "llama-2-7b.suffix.2023-07-18-12-00-00"*
+```
+model_name = "llama-2-7b.suffix.2023-07-18-12-00-00"
+response = Model.get(model_name)
+while response.status != "READY":
+    time.sleep(60)
+    response = Model.get(model_name)
+```
+
+Once the endpoint status is ready, you can use your newly created model for inference.