Fix Wolfram Alpha action error reporting.

Author: drazvan

CHANGELOG.md

@@ -26,6 +26,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed the overriding of general instructions [#7](https://github.com/NVIDIA/NeMo-Guardrails/issues/7).
 - Fixed action parameters inspection bug [#2](https://github.com/NVIDIA/NeMo-Guardrails/issues/2).
 - Fixed bug related to multi-turn flows [#13](https://github.com/NVIDIA/NeMo-Guardrails/issues/13).
+- Fixed Wolfram Alpha error reporting in the sample execution rail.
 
 ## [0.1.0] - 2023-04-25
 

nemoguardrails/actions/math.py

@@ -49,6 +49,10 @@ async def wolfram_alpha_request(
         return ActionResult(
             return_value=False,
             events=[
+                {
+                    "type": "bot_intent",
+                    "intent": "inform wolfram alpha app id not set",
+                },
                 {
                     "type": "bot_said",
                     "content": "Wolfram Alpha app ID is not set. Please set the WOLFRAM_ALPHA_APP_ID environment variable.",
@@ -68,6 +72,10 @@ async def wolfram_alpha_request(
                 return ActionResult(
                     return_value=False,
                     events=[
+                        {
+                            "type": "bot_intent",
+                            "intent": "inform wolfram alpha not working",
+                        },
                         {
                             "type": "bot_said",
                             "content": "Apologies, but I cannot answer this question at this time. I am having trouble getting the answer from Wolfram Alpha.",