Add multimodal support for CodeAgent #875
Draft
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Outdated suggestions cannot be applied.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.
Description
This PR adds multimodal support to the CodeAgent, allowing it to process images in Slack messages. This is the second part of the implementation, building on PR #11444 in the
cloud
repository which adds the ability to capture image information from Slack messages.Changes
Updated the
LLM
class to support multimodal content:_process_messages_for_multimodal
method that converts image URLs in the format[Image: filename](URL)
to the appropriate multimodal format for Claude 3 models_generate
method to process messages for multimodal content when using Claude 3 modelsUpdated the
CodeAgent
class to use multimodal models by default:multimodal
parameter (default: True) to the constructorHow to Test
Related PRs
This PR builds on PR #11444 in the
cloud
repository, which adds the ability to capture image information from Slack messages.