Ensure compatibility bw autoEmbedding indexes with nestedRoot fields

XMLWordPrintableJSON

    • Type: Epic
    • Resolution: Unresolved
    • Priority: Major - P3
    • None
    • Component/s: AI/ML
    • None
    • Support autoEmbed field type nested with nestedRoot
    • Database Experience
    • None
    • Hide

      Summary of necessary driver changes

      •  

      Commits for syncing spec/prose tests
      (and/or refer to an existing language POC if needed)

      •  

      Context for other referenced/linked tickets

      •  
      Show
      Summary of necessary driver changes   Commits for syncing spec/prose tests (and/or refer to an existing language POC if needed)   Context for other referenced/linked tickets  
    • To Do
    • 0
    • 0
    • 0
    • 100
    • None
    • None
    • None
    • Builder Changes Needed
    • $i18n.getText("admin.common.words.hide")
      Key Status/Resolution FixVersion
      CSHARP-6151 Execution Blocked
      JAVA-6269 Execution Blocked
      INTPYTHON-1035 Needs Triage
      PHPLIB-1923 Execution Blocked
      $i18n.getText("admin.common.words.show")
      #scriptField, #scriptField *{ border: 1px solid black; } #scriptField{ border-collapse: collapse; } #scriptField td { text-align: center; /* Center-align text in table cells */ } #scriptField td.key { text-align: left; /* Left-align text in the Key column */ } #scriptField a { text-decoration: none; /* Remove underlines from links */ border: none; /* Remove border from links */ } /* Add green background color to cells with FixVersion */ #scriptField td.hasFixVersion { background-color: #00FF00; /* Green color code */ } #scriptField td.willNotDo { background-color: #FF0000; /* Red color code */ } /* Center-align the first row headers */ #scriptField th { text-align: center; } Key Status/Resolution FixVersion CSHARP-6151 Execution Blocked JAVA-6269 Execution Blocked INTPYTHON-1035 Needs Triage PHPLIB-1923 Execution Blocked
    • None
    • None
    • None
    • None
    • None
    • None

      Summary

      What is the problem or use case, what are we trying to achieve?

      **
      Nested Vector Search (nestedRoot, DRIVERS-3308) and Automated Embeddings
      (autoEmbed, DRIVERS-3389/3315) are each independently supported, but the
      combination – an autoEmbed vector field living inside a
      nestedRoot array – has no dedicated builder support. Today this only
      works via raw BSON index/query documents.

      Motivation

      Who is the affected end user?

      Who are the stakeholders?

      Developers building RAG/chunking use cases who want MongoDB to
      auto-generate embeddings for nested/chunked content.
       

      How does this affect the end user?

      Are they blocked? Are they annoyed? Are they confused?

      Users of statically typed languages can't construct this index/query shape
      through builders and must drop to plain BSON,

      How likely is it that this problem or use case will occur?

      Main path? Edge case?

      Likely for any customer combining nested embeddings with automated
      embeddings .  There will be forthcoming support for auto-chunking with Voyage context models that will predominantly use this path.  See autoEmbeddings driver tickets for frequency of use of autoemebddings through various drivers.

      If the problem does occur, what are the consequences and how severe are they?

      Minor annoyance at a log message? Performance concern? Outage/unavailability? Failover can't complete?

      Is this issue urgent?

      Does this ticket have a required timeline? What is it?

      Ideal to have for autoembeddings GA.  If not, definitely required before support for auto-chunking with autoembedding. 

      Is this ticket required by a downstream team?

      Needed by e.g. Atlas, Shell, Compass?

      Yes, LangChain/LangGraph integration work depends on this
      landing in at least one reference language first

      Is this ticket only for tests?

      Is this ticket have any functional impact, or is it just test improvements?

      Cast of Characters

      Engineering Lead: chunbin.lin@mongodb.com 
      Document Author:
      POCers:
      Product Owner: margaret.matern@mongodb.com 
      Program Manager:
      Stakeholders:

      Channels & Docs

      Slack Channel

      https://docs.google.com/document/d/1AVODSkJemkIKuSgbnqit_uxhJk2-7kT_UVLnqR4NJos/edit?tab=t.0#heading=h.kvsg5knomldr

      Scope

            Assignee:
            Unassigned
            Reporter:
            Margaret Matern
            None
            Votes:
            0 Vote for this issue
            Watchers:
            4 Start watching this issue

              Created:
              Updated:
              None
              None
              None
              None
              None