Skip to content
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

Add support for dense retrieval with instructions #76

Closed
faberf opened this issue May 29, 2024 · 2 comments · Fixed by #83
Closed

Add support for dense retrieval with instructions #76

faberf opened this issue May 29, 2024 · 2 comments · Fixed by #83
Assignees
Labels
enhancement New feature or request

Comments

@faberf
Copy link
Contributor

faberf commented May 29, 2024

Some newer embedding models such as https://huggingface.co/intfloat/e5-mistral-7b-instruct require a one-sentence instruction that describes the retrieval task in addition to the content that should be embedded. This model in particular is currently implemented in the FES and accessible through the ApiWrapper. It might be useful to extend the DenseEmbedding analyser to support these models as well. To accomplish this the DenseEmbedding analyser (or its methods) needs the task instruction (e.g. 'Given a web search query, retrieve relevant passages that answer the query') as a parameter. I would like to ask for your feedback if this should be configured as part of a query or as part of the field. My intuition is that it is a parameter of the query and thus should be passed as query context to newRetrieverForContent... Any thoughts?

@faberf faberf self-assigned this May 29, 2024
@ppanopticon ppanopticon added the enhancement New feature or request label Jun 17, 2024
@ppanopticon
Copy link
Member

ppanopticon commented Jun 18, 2024

When going through the open issue, we were not quite sure what this is about. So maybe you can bring us up to speed during our next weekly.

@faberf
Copy link
Contributor Author

faberf commented Jul 29, 2024

For housekeeping, this is already implemented in feature branch #83.

@v0idness v0idness linked a pull request Aug 16, 2024 that will close this issue
3 tasks
@faberf faberf closed this as completed Sep 17, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants