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Outdated suggestions cannot be applied.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.
Implements async mode for llm_map and llm_map_elements.
Also adds asynchronous llm implementations for anthropic and gemini (+exponential backoff for openai)
I left out bedrock bc bedrock async looks like "start job, poll get job until job is complete, then download result from s3 (oh by the way tell me where in s3 to put the result" and I didn't want to deal with that. (there might be better ways - there's a converse stream client method that can give you an async iterator over the response that might do the trick but that's a whole 'nother API to deal with)