Add Support for Including the Prompt in the Pattern in SequenceGenerator #1122
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
brandonwillard
changed the title
lapp0
reviewed
Sep 17, 2024
| state = fsm.get_next_state(state=state, token_id=token_id.item()) | ||
| if state < 0: | ||
| raise ValueError(f"Invalid state {state}") | ||
| final_fsm_states.append(state) |
There was a problem hiding this comment.
Would it be better to implement this as a Guide? I've started work on #531 and I'd like to see Guides become more composable.
Also interegular has functionality built in to make this easy.
>>> import interegular
>>> fsm = interegular.parse_pattern("abcd").to_fsm()
>>> fsm.accepts("abcd")
True
>>> partial_fsm = fsm.derive("ab")
>>> partial_fsm.accepts("abcd")
False
>>> partial_fsm.accepts("cd")
True
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Let's say you have a Json schema and you want to generate just a subset of keys from other keys. With the current SequenceGenerator, it's not possible to do that in an easy way.
We add the "include_prompt" argument, where the prompt is included in the pattern.
We just unroll the FSMs with the prompt tokens. We also keep the prompt tokens inside of the output, as they are needed for the output
format_sequencecall in things like json.