Fix arg length error, add multimodal examples, update video prompt #634
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Outdated suggestions cannot be applied.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 of the change
This PR fixes the "argument list too long" error in the
text_generation.sh
file when using large base64 encoded images by using temporary files to store the encoded data and the JSON payload. This resolves issues encountered when running thetext_gen_multimodal_one_image_prompt
andtext_gen_multimodal_one_image_prompt_streaming
examples.This PR also makes the following additions and updates:
Adds two new multimodal vision examples to
text_generation.sh
:text_gen_multimodal_two_image_prompt
: Demonstrates using two images in a single prompt.text_gen_multimodal_one_image_bounding_box_prompt
: Shows how to generate bounding boxes for objects.Updates the
text_gen_multimodal_video_prompt
example: The prompt is now more comprehensive and does a better job demonstrating Gemini 1.5's multimodal capabilities.Motivation
These examples are being added so they can be included in the revamped vision documentation.
Type of change
Feature request
Checklist
git pull --rebase upstream main
).