Skip to content

PR for text2graph extractor #1363

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed

Conversation

intelsharath
Copy link
Contributor

Description

Typical available services were using decoder only model which has limitations in identifying NODE->Relation->NODE. Also the services did not clearly support local models. Checking in a service that can use T5 style encode-decoder model that is more powerful and can handle complex relations.

Once this PR is merged, we will add support for Gaudi. (Running into issues with TGI #1331. Once it is resolved will follow up with other request)

(NOTE: PR #1316 will be closed and reopening this PR instead. )

Issues

n/a

Type of change

List the type of change like below. Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • [ x] New feature (non-breaking change which adds new functionality)
  • Breaking change (fix or feature that would break existing design and interface)
  • Others (enhancement, documentation, validation, etc.)

Dependencies

n/a

Tests

To test the following script has been created which does native testing.
GenAIComps/tests/text2graph/native_text2graph.sh
This downloads a text file and extracts triplets required for graph construction natively on Xeon. Once this PR is merged, we will add support for Gaudi.

@intelsharath
Copy link
Contributor Author

closing refer #1357

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant