adding multi-modal pre-processor for cohere #3219
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
dhrubo-os
requested review from
b4sjoo,
jngz-es,
model-collapse,
rbhavna,
ylwu-amzn,
zane-neo,
Zhangxunmt,
austintlee,
HenryL27,
sam-herman and
xinyual
as code owners
dhrubo-os
temporarily deployed
to
ml-commons-cicd-env
GitHub Actions
Inactive
dhrubo-os
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
Signed-off-by: Dhrubo Saha <dhrubo@amazon.com>
dhrubo-os
temporarily deployed
to
ml-commons-cicd-env
GitHub Actions
Inactive
dhrubo-os
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
ylwu-amzn
reviewed
Nov 14, 2024
| public RemoteInferenceInputDataSet process(MLInput mlInput) { | ||
| TextDocsInputDataSet inputData = (TextDocsInputDataSet) mlInput.getInputDataset(); | ||
| Map<String, String> parametersMap = new HashMap<>(); | ||
| parametersMap.put("images", inputData.getDocs().getFirst()); |
There was a problem hiding this comment.
Only support image input? Should we also consider support text input ?
There was a problem hiding this comment.
Cohere multi-modal doesn't support text with image input. Either image input or text input. Example notebook
For text input, we could use our regular one: connector.pre_process.cohere.embedding
There was a problem hiding this comment.
Got it. Add some java doc to explain this?
Does the model support multiple images or just one ?
There was a problem hiding this comment.
Just one per request.
There was a problem hiding this comment.
An array of image data URIs for the model to embed. Maximum number of images per call is 1.
There was a problem hiding this comment.
Got it, suggest add more java doc to explain these details
dhrubo-os
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
Signed-off-by: Dhrubo Saha <dhrubo@amazon.com>
dhrubo-os
temporarily deployed
to
ml-commons-cicd-env
GitHub Actions
Inactive
dhrubo-os
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
dhrubo-os
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
ylwu-amzn
approved these changes
Nov 15, 2024
|
Regarding to this PR, do we need to do any alternations on current blueprint? |
This is a new pre-process function, so I'll add a new blue print doc. |
b4sjoo
approved these changes
Nov 18, 2024
opensearch-trigger-bot bot
pushed a commit
that referenced
this pull request
Nov 18, 2024
* adding multi-modal pre-processor for cohere Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> * added javadoc Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> --------- Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> (cherry picked from commit 7041c22)
|
The backport to To backport manually, run these commands in your terminal: # Fetch latest updates from GitHub
git fetch
# Create a new working tree
git worktree add .worktrees/backport-feature/multi_tenancy feature/multi_tenancy
# Navigate to the new working tree
cd .worktrees/backport-feature/multi_tenancy
# Create a new branch
git switch --create backport/backport-3219-to-feature/multi_tenancy
# Cherry-pick the merged commit of this pull request and resolve the conflicts
git cherry-pick -x --mainline 1 7041c225875709719262853064ae7465bc4cd042
# Push it to GitHub
git push --set-upstream origin backport/backport-3219-to-feature/multi_tenancy
# Go back to the original working tree
cd ../..
# Delete the working tree
git worktree remove .worktrees/backport-feature/multi_tenancyThen, create a pull request where the |
dhrubo-os
added a commit
to dhrubo-os/ml-commons
that referenced
this pull request
Nov 18, 2024
* adding multi-modal pre-processor for cohere Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> * added javadoc Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> --------- Signed-off-by: Dhrubo Saha <dhrubo@amazon.com>
5 tasks
dhrubo-os
added a commit
that referenced
this pull request
Nov 18, 2024
* adding multi-modal pre-processor for cohere (#3219) * adding multi-modal pre-processor for cohere Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> * added javadoc Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> --------- Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> * changing getFirst method Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> --------- Signed-off-by: Dhrubo Saha <dhrubo@amazon.com>
opensearch-trigger-bot bot
pushed a commit
that referenced
this pull request
Nov 19, 2024
* adding multi-modal pre-processor for cohere (#3219) * adding multi-modal pre-processor for cohere Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> * added javadoc Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> --------- Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> * changing getFirst method Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> --------- Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> (cherry picked from commit 622f73d)
dhrubo-os
added a commit
that referenced
this pull request
Nov 19, 2024
* adding multi-modal pre-processor for cohere (#3219) * adding multi-modal pre-processor for cohere Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> * added javadoc Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> --------- Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> * changing getFirst method Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> --------- Signed-off-by: Dhrubo Saha <dhrubo@amazon.com> (cherry picked from commit 622f73d) Co-authored-by: Dhrubo Saha <dhrubo@amazon.com>
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.
Description
[adding multi-modal pre-processor for cohere
Cohere multi-modal model either accepts array of texts or array of base64 images (but only 1 item in the array). So if customer wants to use images then then they can use this pre-processor.
]
Related Issues
Resolves #[Issue number to be closed when this PR is merged]
Check List
--signoff.By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.