OpenAI Vision image query functionality #625
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
andrewfrench
changed the title
andrewfrench
force-pushed
the
french/240130_image-to-text
branch
from
68193b2 to
28dc699
Compare
collindutter
force-pushed
the
french/240130_image-to-text
branch
from
9036b22 to
a6e7b0d
Compare
collindutter
reviewed
Feb 7, 2024
CHANGELOG.md
Outdated
| @@ -12,6 +12,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 | |||
| - `AzureMongoDbVectorStoreDriver` for using CosmosDB with MongoDB vCore API. | |||
| - `vector_path` field on `MongoDbAtlasVectorStoreDriver`. | |||
| - `LeonardoImageGenerationDriver` supports image to image generation. | |||
| - `OpenAiVisionImageQueryDriver` to support queries on images using OpenAI's Vision model. | |||
| - `ImageQueryClient` allowing an agent to make queries on images on disk or in memory. | |||
| - Image Query engine and task. | |||
griptape/drivers/image_query/openai_vision_image_query_driver.py
Outdated
Show resolved
Hide resolved
griptape/tasks/image_query_task.py
Outdated
|
|
||
| @define | ||
| class ImageQueryTask(BaseTask): | ||
| image_query_engine: ImageQueryEngine = field(kw_only=True) |
There was a problem hiding this comment.
I'll wait for #591 so we can do this and add the driver to the OpenAI config as well.
emjay07
reviewed
Feb 7, 2024
andrewfrench
force-pushed
the
french/240130_image-to-text
branch
from
a6e7b0d to
b4ce30d
Compare
collindutter
previously approved these changes
Feb 12, 2024
There was a problem hiding this comment.
Overall looks great. Up to you whether you'd like to wait until #591 is merged in first.
emjay07
previously approved these changes
Feb 12, 2024
|
@andrewfrench #591 went in, let me know if you have any questions on how to integrate here. |
andrewfrench
dismissed stale reviews from emjay07 and collindutter
via
57fd01c
andrewfrench
force-pushed
the
french/240130_image-to-text
branch
from
28095c5 to
57fd01c
Compare
collindutter
requested changes
Feb 13, 2024
collindutter
approved these changes
Feb 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.
This PR introduces image query functionality using the OpenAI Vision model.