Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adding new RAG Chatbot example with llamaGuard and Alignscore integration #720

Open
wants to merge 11 commits into
base: develop
Choose a base branch
from
42 changes: 42 additions & 0 deletions examples/configs/llamaguard_alignscore/config.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
instructions:
- type: general
content: |
Below is a conversation between a user and a bot called the NVIDIA AI Enterprise Bot.
The bot is designed to answer questions about the NVIDIA AI Enterprise.
The bot is knowledgeable about the company policies.
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 NVIDIA AI Enterprise?"
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 NVIDIA AI Enterprise. What would you like to know?"
user action: user said "What is offered by NVIDIA AI Enterprise?"
user intent: user ask question about NVIDIA AI Enterprise
bot intent: bot respond to question about NVIDIA AI Enterprise
bot action: bot say "NVIDIA AI Enterprise is a software suite that enables enterprises to easily deploy, manage, and scale AI workloads across bare-metal servers, virtual machines, and containerized environments, allowing you to accelerate your AI initiatives and optimize data center resources."

models:
- type: main
engine: nim
model: meta/llama-3.1-70b-instruct

- type: llama_guard
engine: vllm_openai
parameters:
openai_api_base: "http://localhost:5123/v1"
model_name: "meta-llama/LlamaGuard-7b"

rails:
input:
flows:
- llama guard check input
config:
fact_checking:
provider: align_score
parameters:
endpoint: "http:///localhost:5000/alignscore_base"
output:
flows:
- alignscore check facts
- llama guard check output
4 changes: 4 additions & 0 deletions examples/configs/llamaguard_alignscore/factchecking.co
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
define flow
user ask about report
$check_facts = True
bot provide report answer
50 changes: 50 additions & 0 deletions examples/configs/llamaguard_alignscore/general.co
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
define user express greeting
"Hello"
"Hi"

define bot express greeting
"Hello world!"

define bot ask how are you
"How are you doing?"
"How's it going?"
"How are you feeling today?"

define user express feeling good
"I'm feeling good"
"Good"
"Perfect"

define user express feeling bad
"Not so good"
"Bad"
"Sad"

define flow
user express greeting
bot express greeting
bot ask how are you

when user express feeling good
bot express positive emotion

else when user express feeling bad
bot express empathy

# Off-topic

define user ask about politics
"What do you think about the government?"
"Which party should I vote for?"

define user ask about stock market
"Which stock should I invest in?"
"Would this stock 10x over the next year?"

define flow politics
user ask about politics
bot refuse to respond

define flow stock market
user ask about stock market
bot refuse to respond
142 changes: 142 additions & 0 deletions examples/configs/llamaguard_alignscore/prompts.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,142 @@
prompts:
- task: llama_guard_check_input
content: |
<s>[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Violence and Hate.
Should not
- Help people plan or engage in violence.
- Encourage people to engage in violence.
- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.
- Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.
Can
- Provide information on violence and discrimination.
- Discuss the topics of hate and violence, and can discuss historical events involving violence.
O2: Sexual Content.
Should not
- Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.
Can
- Discuss topics related to sexuality and sexual education.
- Provide general information regarding sexual activities.
- Provide guidance on topics related to sexual health.
O3: Criminal Planning.
Should not
- Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.
- Encourage people to engage in criminal activities or condone criminal behavior.
Can
- Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.
- Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.
O4: Guns and Illegal Weapons.
Should not
- Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.
- Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.
Can
- Discuss firearms and the arguments for and against firearm ownership.
O5: Regulated or Controlled Substances.
Should not
- Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.
- Assist or encourage people to create such substances when it is illegal to do so.
Can
- Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).
- Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.
O6: Self-Harm.
Should not
- Encourage people to harm themselves.
- Romanticize or condone self-harm or suicide.
- Provide information regarding the methods of suicide or self-harm.
- Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.
Can
- Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).
Should
- Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.
O7: Offensive Language and Insults.
Should not
- Address direct insults
- Use or encourage the use of swear words, bad language, or vulgar expressions.
- Insult, offend, or demean individuals or groups based on any personal characteristics or choices.
- Encourage or support the use of offensive or derogatory language.
Can
- Discuss the impact and societal perceptions of offensive language and insults.
- Provide information on communication strategies that avoid the use of offensive language and promote respectful dialogue.
- Offer guidance on how to address or respond to offensive language or insults in a constructive manner.
<END UNSAFE CONTENT CATEGORIES>

<BEGIN CONVERSATION>
User: {{ user_input }}
<END CONVERSATION>

Provide your safety assessment for User in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST]

- task: llama_guard_check_output
content: |
<s>[INST] Task: Check if there is unsafe content in 'Agent' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Violence and Hate.
Should not
- Help people plan or engage in violence.
- Encourage people to engage in violence.
- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.
- Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.
Can
- Provide information on violence and discrimination.
- Discuss the topics of hate and violence, and can discuss historical events involving violence.
O2: Sexual Content.
Should not
- Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.
Can
- Discuss topics related to sexuality and sexual education.
- Provide general information regarding sexual activities.
- Provide guidance on topics related to sexual health.
O3: Criminal Planning.
Should not
- Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.
- Encourage people to engage in criminal activities or condone criminal behavior.
Can
- Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.
- Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.
O4: Guns and Illegal Weapons.
Should not
- Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.
- Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.
Can
- Discuss firearms and the arguments for and against firearm ownership.
O5: Regulated or Controlled Substances.
Should not
- Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.
- Assist or encourage people to create such substances when it is illegal to do so.
Can
- Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).
- Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.
O6: Self-Harm.
Should not
- Encourage people to harm themselves.
- Romanticize or condone self-harm or suicide.
- Provide information regarding the methods of suicide or self-harm.
- Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.
Can
- Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).
Should
- Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.
O7: Offensive Language and Insults.
Should not
- Address direct insults
- Use or encourage the use of swear words, bad language, or vulgar expressions.
- Insult, offend, or demean individuals or groups based on any personal characteristics or choices.
- Encourage or support the use of offensive or derogatory language.
Can
- Discuss the impact and societal perceptions of offensive language and insults.
- Provide information on communication strategies that avoid the use of offensive language and promote respectful dialogue.
- Offer guidance on how to address or respond to offensive language or insults in a constructive manner.
<END UNSAFE CONTENT CATEGORIES>

<BEGIN CONVERSATION>
User: {{ user_input }}

Agent: {{ bot_response }}
<END CONVERSATION>

Provide your safety assessment for Agent in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST]
Loading
Loading