[Feature Request]: Showing document_id and name during retrieval testing

[Said-Apollo]

Is there an existing issue for the same feature request?

• [X] I have checked the existing issues.

Is your feature request related to a problem?

When doing the retrieval testing in the knowledge base, it would be great to know from which document those chunks were retrieved.

Describe the feature you'd like

How it currently looks (version 0.8):

Describe implementation you've considered

The document_id should be known for each chunk already (during parsing and chunking process). The document_id/name could be shown next to the similarity_scores or below the "image" of each chunk

Documentation, adoption, use case

No response

Additional information

No response

[Anushka-N12]

Working on this, sorry I accidently unassigned myself so plz add me back (first time contributing)

[which-W]

@Said-Apollo Thanks so much for your suggestion — and sorry for the delay in getting back to you! 🕐

At the moment, our recall testing doesn't directly display the document ID or name on each chunk. However, recalled documents are shown in the list of selected files 📄. We're evaluating the value of adding this feature and will take your input into account as we continue to improve the experience 💡

Appreciate your interest in the project! Feel free to keep the feedback coming — we’re always glad to hear ideas that help make things better 🙌