rigging

rigging copied to clipboard

This is a matter of taste, but wondering if you'd be interested in a pr to parse rg.Tool calls from messages.

In continued chats with multiple tool calls, I usually provide a tool like

class FinalAnswer(rg.Tool):
    @property
    def name(self) -> str:
        return "final_answer"
    
    @property
    def description(self) -> str:
        return "A tool that ends the session with your final true or false answer to the question: 'blah blah"

And then continue chats until this tool call is used, breaking at that point. So it'd be nice to do something like

while True and not chat.last.parse(FinalAnswer):
     # keep doing stuff

Though that might require a new property for chat.last_user or chat.last_tool or something.

Also willing to believe there is a straightforward way of doing this that I'm just missing. Anyway, lemme know!

This is an interesting idea. I'll give some thought for how that would integrate into the library. I'd imagine the best alternative is to define a "FinalAnswer" model and use until_parsed_as along with using to let the model cycle tool calls until it's ready to provide an answer. We did something similar for our small CTF example:

import rigging as rg

class FinalAnswer(rg.Model):
   content: str

...

chat = generator.chat([
   {
   "role": "user",
   "content" : "[do some stuff]. When you are ready, place your final answer between {Answer.xml_example()} tags."
   }
]) \
.using(Tool) \
.until_parsed_as(FinalAnswer, max_rounds=100) \ # LLM will continue calling tools until this model is emitted
.run()

answer = chat.last.parse(FinalAnswer)

Closing this for now