fix stateful llama-index examples #416
Merged
Conversation
This file contains hidden or 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
tylerslaton
requested review from
mme,
ranst91,
ataibarkai,
maxkorp and
NathanTarbert
as code owners
tylerslaton
changed the title
tylerslaton
changed the title
Signed-off-by: Tyler Slaton <[email protected]>
tylerslaton
force-pushed
the
logan/fix_stateful_examples
branch
from
fa3bc53 to
a68e5b7
Compare
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Outdated suggestions cannot be applied.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.
Port of #415 for testing + small chore fixes
Original description
There was a small bug in the llama-index examples that used state
Basically, the tools that modify state need to save it at the end. Otherwise, there is a final state snapshot event emitted from the integration code that will erase all the modifications that have been made to the state so far
The fix is just to add await ctx.store.set("state", state) -- however, newer versions of llama-index workflows have an async context manager to make it even easier to access and modify state safely. Within the context manager, no other tool can modify state, so its safe if the agent makes multiple tool calls at once.