deployment params

Author: Aryanag2

ads/aqua/modeldeployment/deployment.py

@@ -28,7 +28,6 @@
     build_params_string,
     build_pydantic_error_message,
     find_restricted_params,
-    get_combined_params,
     get_container_env_type,
     get_container_params_type,
     get_ocid_substring,
@@ -918,10 +917,31 @@ def _create(
         # The values provided by user will override the ones provided by default config
         env_var = {**config_env, **env_var}
 
-        # validate user provided params
-        user_params = env_var.get("PARAMS", UNKNOWN)
+        # SMM Parameter Resolution Logic
+        # Check the raw user input from create_deployment_details to determine intent.
+        # We cannot use the merged 'env_var' here because it may already contain defaults.
+        user_input_env = create_deployment_details.env_var or {}
+        user_input_params = user_input_env.get("PARAMS")
+
+        deployment_params = ""
+
+        if user_input_params is None:
+            # Case 1: None (CLI default) -> Load full defaults from config
+            logger.info("No PARAMS provided (None). Loading default SMM parameters.")
+            deployment_params = config_params
+        elif str(user_input_params).strip() == "":
+            # Case 2: Empty String (UI Clear) -> Explicitly use no parameters
+            logger.info("Empty PARAMS provided. Clearing all parameters.")
+            deployment_params = ""
+        else:
+            # Case 3: Value Provided -> Use exact user value (No merging)
+            logger.info(
+                f"User provided PARAMS. Using exact user values: {user_input_params}"
+            )
+            deployment_params = user_input_params
 
-        if user_params:
+        # Validate the resolved parameters
+        if deployment_params:
             # todo: remove this check in the future version, logic to be moved to container_index
             if (
                 container_type_key.lower()
@@ -935,16 +955,14 @@ def _create(
                 )
 
             restricted_params = find_restricted_params(
-                params, user_params, container_type_key
+                params, deployment_params, container_type_key
             )
             if restricted_params:
                 raise AquaValueError(
                     f"Parameters {restricted_params} are set by Aqua "
                     f"and cannot be overridden or are invalid."
                 )
 
-        deployment_params = get_combined_params(config_params, user_params)
-
         params = f"{params} {deployment_params}".strip()
 
         if isinstance(aqua_model, DataScienceModelGroup):
@@ -1212,7 +1230,7 @@ def _create_deployment(
 
         # we arbitrarily choose last 8 characters of OCID to identify MD in telemetry
         deployment_short_ocid = get_ocid_substring(deployment_id, key_len=8)
-        
+
         # Prepare telemetry kwargs
         telemetry_kwargs = {"ocid": deployment_short_ocid}
 
@@ -2048,9 +2066,11 @@ def recommend_shape(self, **kwargs) -> Union[Table, ShapeRecommendationReport]:
         self.telemetry.record_event_async(
             category="aqua/deployment",
             action="recommend_shape",
-            detail=get_ocid_substring(model_id, key_len=8)
-            if is_valid_ocid(ocid=model_id)
-            else model_id,
+            detail=(
+                get_ocid_substring(model_id, key_len=8)
+                if is_valid_ocid(ocid=model_id)
+                else model_id
+            ),
             **kwargs,
         )
 

models.json

@@ -0,0 +1,18 @@
+[
+  {
+    "model_id": "ocid1.datasciencemodel.oc1.iad.amaaaaaam3xyxziacjn3gsjl4mmvesis5pjeu43lj2vyzjxluoffuqm734da",
+    "gpu_count": 1,
+    "model_name": "llama3-8b-instruct",
+    "fine_tune_weights": [
+      {
+        "model_id": "ocid1.datasciencemodel.oc1.iad.amaaaaaav66vvniabwlacbrsjukmrwk7mmec5ukpumcuefxmclz6suvygywq",
+        "model_name": "my-llama-v3.1-8b-instruct-ft"
+      },
+      {
+        "model_id": "ocid1.datasciencemodel.oc1.iad.amaaaaaav66vvniabxhq42ft6ujro4vb5mwa5kelegkj6lle3g6hpaleomeq",
+        "model_name": "llama-oasst-ft"
+      }
+    ]
+  }
+]
+

test_inference.py

@@ -0,0 +1,42 @@
+import json
+import requests
+import ads
+
+# Set up OCI security token authentication
+ads.set_auth("security_token")
+
+# Your Model Deployment OCID and endpoint URL
+md_ocid = "ocid1.datasciencemodeldeploymentint.oc1.iad.amaaaaaav66vvniasakhgqe4hk6eqgci7jmj2nvxjzldaqlnb7ji7vjr5p6a"
+endpoint = "https://modeldeployment-int.us-ashburn-1.oci.oc-test.com/ocid1.datasciencemodeldeploymentint.oc1.iad.amaaaaaav66vvniasakhgqe4hk6eqgci7jmj2nvxjzldaqlnb7ji7vjr5p6a/predict"
+
+# OCI request signer
+auth = ads.common.auth.default_signer()["signer"]
+
+
+def predict(model_name):
+    predict_data = {
+        "model": model_name,
+        "prompt": "[user] Write a SQL query to answer the question based on the table schema.\n\ncontext: CREATE TABLE table_name_74 (icao VARCHAR, airport VARCHAR)\n\nquestion: Name the ICAO for lilongwe international airport [/user] [assistant]",
+        "max_tokens": 100,
+        "temperature": 0,
+    }
+    predict_headers = {"cx": "application/json", "opc-request-id": "test-id"}
+    response = requests.post(
+        endpoint,
+        headers=predict_headers,
+        data=json.dumps(predict_data),
+        auth=auth,
+        verify=False,  # Use verify=True in production!
+    )
+    print("Status:", response.status_code)
+    try:
+        print(json.dumps(response.json(), indent=2))
+    except Exception as e:
+        print("Error parsing JSON:", e)
+        print("Response.text:", response.text)
+
+
+if __name__ == "__main__":
+    ft_model_name = "my-llama-v3.1-8b-instruct-ft"
+    print(f"Testing FT model: {ft_model_name}")
+    predict(ft_model_name)