Fix for Authorino TC (red-hat-data-services#1770)

* add fix for authorino Signed-off-by: Milind Waykole <[email protected]> * add fix for authorino Signed-off-by: Milind Waykole <[email protected]> --------- Signed-off-by: Milind Waykole <[email protected]> Co-authored-by: Milind Waykole <[email protected]>
bdattoma · Sep 3, 2024 · c636a13 · c636a13
1 parent f85a462
commit c636a13
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 11 deletions.
diff --git a/ods_ci/tests/Resources/CLI/ModelServing/llm.resource b/ods_ci/tests/Resources/CLI/ModelServing/llm.resource
@@ -361,7 +361,11 @@ Query Model Multiple Times
     ...    inference_type=${inference_type}    model_name=${model_name}    body_params=${body_params}
     ...    query_text=${EXP_RESPONSES}[queries][${query_idx}][query_text]
     IF    "${token}" != "${None}"
-        Set To Dictionary    ${header}    Authorization    Bearer ${token}
+        IF    "${protocol}" == "grpc"
+            ${header}=   Set Variable   "Authorization: Bearer ${token}" -H ${header}
+            ELSE
+                Set To Dictionary    ${header}    Authorization    Bearer ${token}
+        END
     END
     ${runtime_details}=    Set Variable    ${RUNTIME_FORMATS}[${runtime}][endpoints][${inference_type}][${protocol}]
     ${endpoint}=    Set Variable    ${runtime_details}[endpoint]

diff --git a/ods_ci/tests/Tests/1000__model_serving/1007__model_serving_llm/1007__model_serving_llm.robot b/ods_ci/tests/Tests/1000__model_serving/1007__model_serving_llm/1007__model_serving_llm.robot
@@ -571,16 +571,14 @@ Verify User Can Serve And Query A Model With Token
     Wait For Pods To Be Ready    label_selector=serving.kserve.io/inferenceservice=${flan_model_name}
     ...    namespace=${test_namespace}
     Create Role Binding For Authorino   name=${DEFAULT_BUCKET_PREFIX}   namespace=${test_namespace}
-    # TODO: The token created from this keyword does not work to query the model, it will result in a 401 Unauthorized
-    # error being sent back. Investigate and figure out why, fix the logic.
     ${inf_token}=    Create Inference Access Token   ${test_namespace}   ${DEFAULT_BUCKET_SA_NAME}
     Sleep    600s
     Query Model Multiple Times    model_name=${flan_model_name}
     ...    inference_type=all-tokens    n_times=1
-    ...    namespace=${test_namespace}   token=${inf_token}    protocol=http
+    ...    namespace=${test_namespace}   token=${inf_token}
     Query Model Multiple Times    model_name=${flan_model_name}
     ...    inference_type=streaming    n_times=1
-    ...    namespace=${test_namespace}   token=${inf_token}    protocol=http
+    ...    namespace=${test_namespace}   token=${inf_token}
     [Teardown]    Clean Up Test Project    test_ns=${test_namespace}
     ...    isvc_names=${models_names}    wait_prj_deletion=${FALSE}
 

diff --git a/...ests/Tests/1000__model_serving/1007__model_serving_llm/1007__model_serving_llm_tgis.robot b/...ests/Tests/1000__model_serving/1007__model_serving_llm/1007__model_serving_llm_tgis.robot
@@ -648,27 +648,25 @@ Verify User Can Serve And Query A Model With Token
     Wait For Pods To Be Ready    label_selector=serving.kserve.io/inferenceservice=${flan_model_name}
     ...    namespace=${test_namespace}
     Create Role Binding For Authorino   name=${DEFAULT_BUCKET_PREFIX}   namespace=tgis-standalone-cli
-    # TODO: The token created from this keyword does not work to query the model, it will result in a 401 Unauthorized
-    # error being sent back. Investigate and figure out why, fix the logic.
     ${inf_token}=     Create Inference Access Token   ${test_namespace}    ${DEFAULT_BUCKET_SA_NAME}
     ${pod_name}=  Get Pod Name    namespace=${test_namespace}    
     ...    label_selector=serving.kserve.io/inferenceservice=${flan_model_name}
     IF    ${IS_KSERVE_RAW}     Start Port-forwarding    namespace=${test_namespace}    pod_name=${pod_name}
     Query Model Multiple Times    model_name=${flan_model_name}    runtime=${TGIS_RUNTIME_NAME}
-    ...    inference_type=all-tokens    n_times=1    protocol=http
+    ...    inference_type=all-tokens    n_times=1
     ...    namespace=${test_namespace}    port_forwarding=${IS_KSERVE_RAW}   token=${inf_token}
     Query Model Multiple Times    model_name=${flan_model_name}    runtime=${TGIS_RUNTIME_NAME}
      ...    inference_type=tokenize    n_times=1    port_forwarding=${IS_KSERVE_RAW}
      ...    namespace=${test_namespace}    validate_response=${TRUE}    string_check_only=${TRUE}
-     ...    token=${inf_token}    protocol=http
+     ...    token=${inf_token}
     Query Model Multiple Times    model_name=${flan_model_name}    runtime=${TGIS_RUNTIME_NAME}
     ...    inference_type=model-info    n_times=1    port_forwarding=${IS_KSERVE_RAW}
     ...    namespace=${test_namespace}    validate_response=${TRUE}    string_check_only=${TRUE}
-    ...    token=${inf_token}    protocol=http
+    ...    token=${inf_token}
    Query Model Multiple Times    model_name=${flan_model_name}    runtime=${TGIS_RUNTIME_NAME}
     ...    inference_type=streaming    n_times=1    port_forwarding=${IS_KSERVE_RAW}
     ...    namespace=${test_namespace}    validate_response=${FALSE}
-    ...    token=${inf_token}    protocol=http
+    ...    token=${inf_token}
     [Teardown]    Run Keywords
     ...    Clean Up Test Project    test_ns=${test_namespace}
     ...    isvc_names=${models_names}    wait_prj_deletion=${FALSE}