kauabh
commented
3 months ago Hey @kaustubhbhavsar I have tried below setup using configs from this example, folder structure also same. It seems like it works. I modified two files to match your example
- actions file
from typing import Optional from nemoguardrails.actions import action
@action(name="process_input", is_system_action=True) async def process_input(context: Optional[dict] = None): user_message = context.get("user_message")
print(f"User Input: {user_message}")
# A quick hard-coded list of proprietary terms. You can also read this from a file.
proprietary_terms = ["proprietary", "proprietary1", "proprietary2"]
for term in proprietary_terms:
if term in user_message.lower():
return True
return False2. Config.yml -models:
- type: main engine: ollama model: phi3:mini parameters: base_url: http://localhost:11434
instructions:
- type: general content: | Below is a conversation between a user and a bot called the ABC Bot. The bot is designed to answer employee questions about the ABC Company. The bot is knowledgeable about the employee handbook and company policies. If the bot does not know the answer to a question, it truthfully says it does not know.
sample_conversation: | 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."
rails: input: flows:
- self check input
-
process input
output: flows:
- self check output
- Execution code
from nemoguardrails import RailsConfig, LLMRails config = RailsConfig.from_path("./config/config_668/") rails = LLMRails(config=config) response = await rails.generate_async(messages=[{ "role": "user", "content": "Hello", }], options={ "log": { "activated_rails": True, } }) print(response.response[0]["content"]) for rail in response.log.activated_rails: print({key: getattr(rail, key) for key in ["type", "name"] if hasattr(rail, key)}) - Ouput
User Input: Hello Hello! How can I help you today? If you have any questions about working at ABC Company or anything else within my knowledge base related to company policies and procedures, feel free to ask. Otherwise, if your question is outside of this scope, please let me know so we can find the best way forward for both parties involved. {'type': 'input', 'name': 'self check input'} {'type': 'input', 'name': 'process input'} {'type': 'dialog', 'name': 'generate user intent'} {'type': 'dialog', 'name': 'generate next step'} {'type': 'generation', 'name': 'generate bot message'} {'type': 'output', 'name': 'self check output'}It seems like working as expected. Hopefully this helps. Version used 0.9.1.1
kaustubhbhavsar
drazvan
File Structure:
process_input.py:
conversations.co:
flows.co
test.py:
If config.yml is as follows i.e. with 'process input':
then the output is (topical rails are not called):
If config.yml is as follows i.e. after removing 'process input':
then the output is (topical rails are called correctly):
version used is: 0.9.1.1