Improving readability

[cozmosisosis]

Would there be any draw backs to pulling out some of the data and functions into different files for readability?

For example, I would want to remove the prompts to a separate file called 'agent_prompts.py'.
Or pulling out other functions into a 'helper.py' file.

Turning this:

def exec(self, inputs):
        """Call the LLM to decide whether to search or answer."""
        question, context = inputs
        
        print(f"🤔 Agent deciding what to do next...")
        
        # Create a prompt to help the LLM decide what to do next with proper yaml formatting
        prompt = f"""
### CONTEXT
You are a research assistant that can search the web.
Question: {question}
Previous Research: {context}

### ACTION SPACE
[1] search
  Description: Look up more information on the web
  Parameters:
    - query (str): What to search for

[2] answer
  Description: Answer the question with current knowledge
  Parameters:
    - answer (str): Final answer to the question

## NEXT ACTION
Decide the next action based on the context and available actions.
Return your response in this format:

```yaml
thinking: |
    <your step-by-step reasoning process>
action: search OR answer
reason: <why you chose this action>
answer: <if action is answer>
search_query: <specific search query if action is search>
```
IMPORTANT: Make sure to:
1. Use proper indentation (4 spaces) for all multi-line fields
2. Use the | character for multi-line text fields
3. Keep single-line fields without the | character
"""
        
        # Call the LLM to make a decision
        response = call_llm(prompt)
        
        # Parse the response to get the decision
        yaml_str = response.split("```yaml")[1].split("```")[0].strip()
        decision = yaml.safe_load(yaml_str)
        
        return decision

Into this:

import decide_agent_prompt from agent_prompts

def exec(self, inputs):
        """Call the LLM to decide whether to search or answer."""
        question, context = inputs
        
        print(f"🤔 Agent deciding what to do next...")
        
        # Create a prompt to help the LLM decide what to do next with proper yaml formatting
        prompt = decide_agent_prompt(question, context)

        # Call the LLM to make a decision
        response = call_llm(prompt)
        
        # Parse the response to get the decision
        yaml_str = response.split("```yaml")[1].split("```")[0].strip()
        decision = yaml.safe_load(yaml_str)
        
        return decision

This concept could be expanded on further if you would like more examples, maybe with functions pulled out to a helper file. If you would be interested in this I could work on a pull request.

Let me know your thoughts.

[zachary62]

Yeah it's more a style preference. I personally want to read raw prompt but do that if it's more organized.