Image handling is currently broken #156
Merged
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
Collaborator
jaresty
commented
Aug 12, 2024
jaresty
commented
- When you fetch the image source it formats the messages
- If you try to extract them as text at that point, images will not be processed at all
- In order to process images you have to keep the messages intact from source extraction through to insertion
- When you fetch the image source it formats the messages - If you try to extract them as text at that point, images will not be processed at all - In order to process images you have to keep the messages intact from source extraction through to insertion
jaresty
commented
Aug 12, 2024
| @@ -138,27 +138,22 @@ def gpt_apply_prompt(prompt: str, source: str = "", destination: str = ""): | |||
|
|
|||
| text_to_process: GPTMessageItem = actions.user.gpt_get_source_text(source) | |||
|
|
|||
| # If after creating the message there wasn't anything in the text_to_process, set it to None so | |||
There was a problem hiding this comment.
This check was blocking images from being processed
jaresty
commented
Aug 12, 2024
| @@ -212,72 +207,75 @@ def gpt_insert_response( | |||
| # Skip inserting the response if the user is just viewing the thread in the window | |||
| actions.user.confirmation_gui_refresh_thread() | |||
|
|
|||
| message_text_no_images = extract_message(gpt_message) | |||
There was a problem hiding this comment.
Extract message currently returns text so if there's an image here it will return an empty string
| @@ -40,6 +40,11 @@ def disable_thread(cls): | |||
| @classmethod | |||
| def push_context(cls, context: GPTMessageItem): | |||
| """Add the selected text to the stored context""" | |||
| if context.get("type") != "text": | |||
There was a problem hiding this comment.
This ensures that images don't get inserted into the system messages since that would cause an error
- since only some destination support images, it makes sense to handle them in a separate case - this will now print an error message of someone tries to 'pass clip to window' with an image in their clipboard
C-Loftus
reviewed
Aug 12, 2024
C-Loftus
approved these changes
Aug 13, 2024
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.