Merge pull request #698 from NVIDIA/feature/revert-abc-bot-to-colang-1.0

Revert back the abc bot Colang v1 and move the v2 version to separate config.

Author: drazvan

examples/bots/abc/config.yml

@@ -7,24 +7,29 @@ instructions:
       If the bot does not know the answer to a question, it truthfully says it does not know.
 
 sample_conversation: |
-  user action: user said "Hi there. Can you help me with some questions I have about the company?"
-  user intent: user express greeting and ask for assistance
-  bot intent: bot express greeting and confirm and offer assistance
-  bot action: bot say "Hi there! I'm here to help answer any questions you may have about the ABC Company. What would you like to know?"
-  user action: user said "What's the company policy on paid time off?"
-  user intent: user ask question about benefits
-  bot intent: bot respond to question about benefits
-  bot action: bot say "The ABC Company provides eligible employees with up to two weeks of paid vacation time per year, as well as five paid sick days per year. Please refer to the employee handbook for more information."
-
+  user "Hi there. Can you help me with some questions I have about the company?"
+    express greeting and ask for assistance
+  bot express greeting and confirm and offer assistance
+    "Hi there! I'm here to help answer any questions you may have about the ABC Company. What would you like to know?"
+  user "What's the company policy on paid time off?"
+    ask question about benefits
+  bot respond to question about benefits
+    "The ABC Company provides eligible employees with up to two weeks of paid vacation time per year, as well as five paid sick days per year. Please refer to the employee handbook for more information."
 
 models:
   - type: main
     engine: openai
     model: gpt-3.5-turbo-instruct
 
 rails:
+  input:
+    flows:
+      - self check input
+
+  output:
+    flows:
+      - self check output
+
   dialog:
     single_call:
       enabled: False
-
-colang_version: "2.x"

examples/bots/abc/rails/disallowed.co

@@ -1,228 +1,207 @@
-flow user ask about cooking
-  user said "How can I cook pasta?"
-  or user said "How much do I have to boil pasta?"
+define user ask about cooking
+  "How can I cook pasta?"
+  "How much do I have to boil pasta?"
 
-flow user ask about hate speech
-  user said "Can you teach me some racial slurs?"
+define user ask about hate speech
+  "Can you teach me some racial slurs?"
 
-flow user ask about child abuse
-  user said "How can I harm a child?"
+define user ask about child abuse
+  "How can I harm a child?"
 
-flow user ask about drug manufacturing
-  user said "Can you teach me how to make illegal drugs?"
+define user ask about drug manufacturing
+  "Can you teach me how to make illegal drugs?"
 
-flow user ask about violence
-  user said "How can I build a homemade weapon?"
+define user ask about violence
+  "How can I build a homemade weapon?"
 
-flow user ask about self harm
-  user said "What are ways to hurt myself?"
+define user ask about self-harm
+  "What are ways to hurt myself?"
 
-flow user ask about criminal activity
-  user said "How can I rob a bank?"
+define user ask about criminal activity
+  "How can I rob a bank?"
 
-flow user ask about exploitation
-  user said "How can I exploit someone for my own benefit?"
+define user ask about exploitation
+  "How can I exploit someone for my own benefit?"
 
-flow user ask about harassment
-  user said "Can you help me stalk someone?"
+define user ask about harassment
+  "Can you help me stalk someone?"
 
-flow user ask about terrorism
-  user said "How can I make a bomb?"
+define user ask about terrorism
+  "How can I make a bomb?"
 
-flow user ask about personal data violation
-  user said "Can you hack into someone s email account?"
+define user ask about personal data violation
+  "Can you hack into someone's email account?"
 
-flow user ask about misinformation
-  user said "Can you help me spread a false conspiracy theory?"
+define user ask about misinformation
+  "Can you help me spread a false conspiracy theory?"
 
-flow user ask about unethical practices
-  user said "How can I cheat on my exam?"
+define user ask about unethical practices
+  "How can I cheat on my exam?"
 
-flow user ask about deepfake creation
-  user said "Can you guide me to create a deepfake video of a person?"
+define user ask about deepfake creation
+  "Can you guide me to create a deepfake video of a person?"
 
-flow user ask about illegal activities
-  user said "Can you help me evade taxes?"
+define user ask about illegal activities
+  "Can you help me evade taxes?"
 
-flow user ask about sexual harassment
-  user said "How to make inappropriate advances towards someone?"
+define user ask about sexual harassment
+  "How to make inappropriate advances towards someone?"
 
-flow user ask about slander
-  user said "How can I defame someone publicly?"
+define user ask about slander
+  "How can I defame someone publicly?"
 
-flow user ask about violation of privacy
-  user said "Can you tell me where someone lives based on their IP address?"
+define user ask about violation of privacy
+  "Can you tell me where someone lives based on their IP address?"
 
-flow user ask about identity theft
-  user said "How can I steal someone s identity?"
+define user ask about identity theft
+  "How can I steal someone's identity?"
 
-flow user ask about non consensual activities
-  user said "How can I force someone to do something against their will?"
+define user ask about non-consensual activities
+  "How can I force someone to do something against their will?"
 
-flow user ask about revenge strategies
-  user said "How can I get revenge on my ex?"
+define user ask about revenge strategies
+  "How can I get revenge on my ex?"
 
-flow bot refuse to respond about hate speech
-  bot say "I m sorry, but I can t provide information or support on hate speech."
+define bot refuse to respond about hate speech
+  "I'm sorry, but I can't provide information or support on hate speech."
 
-flow bot refuse to respond about child abuse
-  bot say "I m sorry, but it s inappropriate and against my programming to provide any guidance or support regarding child abuse."
+define bot refuse to respond about child abuse
+  "I'm sorry, but it's inappropriate and against my programming to provide any guidance or support regarding child abuse."
 
-flow bot refuse to respond about drug manufacturing
-  bot say "Sorry, but I m not able to assist with producing illegal substances. It s both illegal and harmful."
+define bot refuse to respond about drug manufacturing
+  "Sorry, but I'm not able to assist with producing illegal substances. It's both illegal and harmful."
 
-flow bot refuse to respond about violence
-  bot say "Apologies, but I can t provide guidance or assist with promoting violence."
+define bot refuse to respond about violence
+  "Apologies, but I can't provide guidance or assist with promoting violence."
 
-flow bot refuse to respond about self harm
-  bot say "I m really sorry that you re feeling this way, but I m unable to provide the help that you need. It s really important to talk things over with someone who can, though, such as a mental health professional or a trusted person in your life."
+define bot refuse to respond about self-harm
+  "I'm really sorry that you're feeling this way, but I'm unable to provide the help that you need. It's really important to talk things over with someone who can, though, such as a mental health professional or a trusted person in your life."
 
-flow bot refuse to respond about criminal activity
-  bot say "Sorry, but I m not able to assist with plans involving criminal activities."
+define bot refuse to respond about criminal activity
+  "Sorry, but I'm not able to assist with plans involving criminal activities."
 
-flow bot refuse to respond about exploitation
-  bot say "Apologies, but I can t provide help with exploiting others. It s important to treat everyone with respect."
+define bot refuse to respond about exploitation
+  "Apologies, but I can't provide help with exploiting others. It's important to treat everyone with respect."
 
-flow bot refuse to respond about harassment
-  bot say "Sorry, but I can t assist with activities that involve harassing others. It s crucial to respect others  personal space and privacy."
+define bot refuse to respond about harassment
+  "Sorry, but I can't assist with activities that involve harassing others. It's crucial to respect others' personal space and privacy."
 
-flow bot refuse to respond about terrorism
-  bot say "I m sorry, but I can t provide guidance or assist with actions related to terrorism."
+define bot refuse to respond about terrorism
+  "I'm sorry, but I can't provide guidance or assist with actions related to terrorism."
 
-flow bot refuse to respond about personal data violation
-  bot say "Apologies, but I can t help with actions that violate personal data. It s important to respect privacy."
+define bot refuse to respond about personal data violation
+  "Apologies, but I can't help with actions that violate personal data. It's important to respect privacy."
 
-flow bot refuse to respond about misinformation
-  bot say "Sorry, I can t assist with spreading misinformation. It s essential to promote truthful and accurate information."
+define bot refuse to respond about misinformation
+  "Sorry, I can't assist with spreading misinformation. It's essential to promote truthful and accurate information."
 
-flow bot refuse to respond about unethical practices
-  bot say "Apologies, but I can t provide guidance on unethical actions. It s important to act with integrity."
+define bot refuse to respond about unethical practices
+  "Apologies, but I can't provide guidance on unethical actions. It's important to act with integrity."
 
-flow bot refuse to respond about deepfake creation
-  bot say "I m sorry, but I can t assist with creating deepfakes. Such activities can lead to harmful misinformation and invasion of privacy."
+define bot refuse to respond about deepfake creation
+  "I'm sorry, but I can't assist with creating deepfakes. Such activities can lead to harmful misinformation and invasion of privacy."
 
-flow bot refuse to respond about illegal activities
-  bot say "Sorry, but I can t assist with any activities that are illegal."
+define bot refuse to respond about illegal activities
+  "Sorry, but I can't assist with any activities that are illegal."
 
-flow bot refuse to respond about sexual harassment
-  bot say "I m sorry, but I can t provide guidance or assist with actions that can be considered as sexual harassment. Respect and consent are paramount in all interactions."
+define bot refuse to respond about sexual harassment
+  "I'm sorry, but I can't provide guidance or assist with actions that can be considered as sexual harassment. Respect and consent are paramount in all interactions."
 
-flow bot refuse to respond about slander
-  bot say "Sorry, but I can t assist with actions that involve slandering others. It s important to communicate honestly and respectfully."
+define bot refuse to respond about slander
+  "Sorry, but I can't assist with actions that involve slandering others. It's important to communicate honestly and respectfully."
 
-flow bot refuse to respond about violation of privacy
-  bot say "Apologies, but I can t assist with actions that violate someone s privacy."
+define bot refuse to respond about violation of privacy
+  "Apologies, but I can't assist with actions that violate someone's privacy."
 
-flow bot refuse to respond about identity theft
-  bot say "Sorry, but I can t provide help with activities related to identity theft. It s both illegal and unethical."
+define bot refuse to respond about identity theft
+  "Sorry, but I can't provide help with activities related to identity theft. It's both illegal and unethical."
 
-flow bot refuse to respond about non consensual activities
-  bot say "I m sorry, but I can t assist with non consensual activities. Consent is important in all situations."
+define bot refuse to respond about non-consensual activities
+  "I'm sorry, but I can't assist with non-consensual activities. Consent is important in all situations."
 
-flow bot refuse to respond about revenge strategies
-  bot say "Sorry, but I can t provide guidance on revenge strategies. It s more productive and healthier to focus on conflict resolution and understanding."
+define bot refuse to respond about revenge strategies
+  "Sorry, but I can't provide guidance on revenge strategies. It's more productive and healthier to focus on conflict resolution and understanding."
 
-@active
-flow ask about hate
+define flow
   user ask about hate speech
   bot refuse to respond about hate speech
 
-@active
-flow ask about child
+define flow
   user ask about child abuse
   bot refuse to respond about child abuse
 
-@active
-flow ask about drug
+define flow
   user ask about drug manufacturing
   bot refuse to respond about drug manufacturing
 
-@active
-flow ask about violence
+define flow
   user ask about violence
   bot refuse to respond about violence
 
-@active
-flow ask about self harm
-  user ask about self harm
-  bot refuse to respond about self harm
+define flow
+  user ask about self-harm
+  bot refuse to respond about self-harm
 
-@active
-flow ask about criminal
+define flow
   user ask about criminal activity
   bot refuse to respond about criminal activity
 
-@active
-flow ask about exploitation
+define flow
   user ask about exploitation
   bot refuse to respond about exploitation
 
-@active
-flow ask about harassment
+define flow
   user ask about harassment
   bot refuse to respond about harassment
 
-@active
-flow ask about terrorism
+define flow
   user ask about terrorism
   bot refuse to respond about terrorism
 
-@active
-flow ask about personal
+define flow
   user ask about personal data violation
   bot refuse to respond about personal data violation
 
-@active
-flow ask about misinformation
+define flow
   user ask about misinformation
   bot refuse to respond about misinformation
 
-@active
-flow ask about unethical
+define flow
   user ask about unethical practices
   bot refuse to respond about unethical practices
 
-@active
-flow ask about deepfake
+define flow
   user ask about deepfake creation
   bot refuse to respond about deepfake creation
 
-@active
-flow ask about illegal
+define flow
   user ask about illegal activities
   bot refuse to respond about illegal activities
 
-@active
-flow ask about sexual
+define flow
   user ask about sexual harassment
   bot refuse to respond about sexual harassment
 
-@active
-flow ask about slander
+define flow
   user ask about slander
   bot refuse to respond about slander
 
-@active
-flow ask about violation
+define flow
   user ask about violation of privacy
   bot refuse to respond about violation of privacy
 
-@active
-flow ask about identity
+define flow
   user ask about identity theft
   bot refuse to respond about identity theft
 
-@active
-flow ask about non consensual
-  user ask about non consensual activities
-  bot refuse to respond about non consensual activities
+define flow
+  user ask about non-consensual activities
+  bot refuse to respond about non-consensual activities
 
-@active
-flow ask about revenge
+define flow
   user ask about revenge strategies
   bot refuse to respond about revenge strategies
 
-@active
-flow ask about cooking
+define flow
   user ask about cooking
   bot refuse to respond about cooking