Not able to call the actions from colang file

[onkarrajambatwar]

Hi,

I have a simple example of checking the rag custom action.

I have added the config with instruction, sample, self check input. In rails.co I have added below code which very simple. and then in my app.py I have registered actions which i am using.

It is very basic stuff, still the custom action is not getting called. I am not able to understand the problem, also the documentation is saying nothing more than what I have done.
here is the code:

define user express greeting
  "Hello"
  "Hi"

define user ask capabilities
  "What can you do?"
  "What can you help me with?"
  "tell me what you can do"
  "tell me about you"

define flow
  user express greeting
  bot express greeting

define flow
  user ask capabilities
  bot inform capabilities

define bot inform capabilities
  "I am an AI assistant and I'm here to help."

# define limits
define user ask politics
    "what are your political beliefs?"
    "thoughts on the president?"
    "left wing"
    "right wing"

define bot answer politics
    "I'm a AI assistant, I don't like to talk of politics."
    "Sorry I can't talk about politics!"

define flow politics
    user ask politics
    bot answer politics
    bot offer help

define flow self check input
    $allowed = execute self_check_input
    if not $allowed
      bot refuse to respond
      stop

define bot refuse to respond
  "I'm sorry, I can't respond to that..........."


# define RAG intents and flow
define user ask about company policy
      "What Company Policy?"
      "What are the company safty guidlines?"
      "tell me about paid leaves?"
      "what is shopfloor dress code"
      "how to apply leaves?"

define bot express excitement
  "Wow!!, New question"
  "wow"

define flow
    user ask about company policy
    bot express excitement
    $contexts = execute retrieve(query=$last_user_message)
    $answer = execute rag(query=$last_user_message, contexts=$contexts)
    bot $answer`

@action()
async def retrieve(query: str) -> list:
    print(">>> Retrieve Called...")  
    # create query embedding
    vectorstore = FAISS.load_local("store", OpenAIEmbeddings())
    res = vectorstore.as_retriever(
    search_type="similarity",
    search_kwargs={"k": 4, "include_metadata": True})
    # get list of retrieved texts
    contexts = [x['metadata']['chunk'] for x in res['matches']]
    print(contexts)
    return contexts

@action()
async def rag(query: str, contexts: list) -> str:
    print(">>> RAG Called..")  
    # we'll add this so we can see when this is being used
    context_str = "\n".join(contexts)
    # place query and contexts into RAG prompt
    prompt = f"""You are a helpful assistant, below is a query from a user and
    some relevant contexts. Answer the question given the information in those
    contexts. If you cannot find the answer to the question, say "I don't know".
    History:
    {st.session_state.messages[-5:]['content']}
    Contexts:
    {context_str}

    Query: {query}

    Answer: """
    # generate answer
    res = openai.Completion.create(
        engine="gpt-3.5-turbo",
        prompt=prompt,
        temperature=0.5,
        max_tokens=100
    )
    return res['choices'][0]['text']

    
    # Register Nemo Guard rails
config = RailsConfig.from_path('./config')

# print("Config has registered...")
app = LLMRails(config,llm=get_llm(), verbose=True)

#register actions
app.register_action(action=retrieve, name="retrieve")
app.register_action(action=create_retrivalQa_chain, name="rag")

Could you guys provide the input on same

[drazvan]

Can you also add

from nemoguardrails.logging.verbose import set_verbose

set_verbose(True)

to your file and share the logs from a run that does not work. On a first glance, it should work.