langchain

38210b28 - Add async versions of predict() and predict_messages() (#4867)

Add async versions of predict() and predict_messages() (#4867) # Add async versions of predict() and predict_messages() #4615 introduced a unifying interface for "base" and "chat" LLM models via the new `predict()` and `predict_messages()` methods that allow both types of models to operate on string and message-based inputs, respectively. This PR adds async versions of the same (`apredict()` and `apredict_messages()`) that are identical except for their use of `agenerate()` in place of `generate()`, which means they repurpose all existing work on the async backend. ## Who can review? Community members can review the PR once tests pass. Tag maintainers/contributors who might be interested: @hwchase17 (follows his work on #4615) @agola11 (async) --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>