Skip to content

Vector Search

← MongoDB Feedback Engine
Tell us what challenge you're trying to solve!

Tell us how to improve Atlas Vector Search!

(thinking…)

Enter your idea and we'll search to see if someone has already suggested it.

If a similar idea already exists, you can support and comment on it.

If it doesn't exist, you can post your idea so others can support it.

Enter your idea and we'll search to see if someone has already suggested it.

9 results found

  1. Threshold-based similarity search

    We should support threshold-based similarity search instead of solely topK search. This would allow us to more efficiently gather results by considering a relevancy threshold within the prefilter.

    6 votes
    0 comments  ·  Admin →
    How important is this to you?

  2. Improve Performance when filtering collection as part of Atlas Vector Search

    Adding filters to the $vectorSearch aggregation step should improve performance of vectorSearch given that we are searching over a smaller subset of the collection. Especially if those filters are for fields that we have an index for.

    When testing vectorSearch performance, this is not the case:

    Our setup:
    Index exists with type: vectorSearch, Index Fields: fieldA, fieldB, fieldC. Status is Active.

    Add this filter to the $vectorSearch aggregation step:
    'filter': {
    '$and': [
    {
    ‘fieldA’: value1,
    ‘fieldB’: False,
    }
    ]
    },

    The original query times are as follows:
    P50 Total Query Time: 2.0953004360198975
    P95 Total Query Time: 3.579429221153259
    P99 Total…

    5 votes
    1 comment  ·  Admin →
    How important is this to you?

  3. Vector Search Index support in pymongo

    Currently creating a Search Index of type "vector" is not possible with pymongo v4.6.2. https://www.mongodb.com/community/forums/t/create-vector-search-pymongo-latest-version-returns-command-not-found/267874/3?u=matthieu_mazzolini

    4 votes
    0 comments  ·  Admin →
    How important is this to you?

  4. Atlas Vector Search + Geospatial, please! 🙏

    Would love to be able to do a geospatial query like $geoWithin together with Atlas Vector Search query!

    4 votes
    0 comments  ·  Admin →
    How important is this to you?

  5. RAG and Semantic Search Tools in the Atlas Search Playground

    Have ideas about what features would be helpful for RAG and Semantic Search in the Atlas Search Playground? Let us know!

    2 votes
    0 comments  ·  Admin →
    How important is this to you?

  6. Project out embedding fields by default in $vectorSearch

    We should update the default behavior to project out embeddings, since they are typically not used in subsequent aggregation stages, with an additional query parameter to force include them.

    2 votes
    0 comments  ·  Admin →
    How important is this to you?

  7. if you could please improve the exam issue

    completed the GenAI but did not get my badge

    1 vote
    0 comments  ·  Admin →
    How important is this to you?

  8. Binary and Scalar Quantization

    These capabilities will reduce vector sizes while preserving performance, enabling developers to build powerful semantic search and generative AI applications with more scale—and at a lower cost.

    1 vote
    0 comments  ·  Admin →
    How important is this to you?

  9. Add "await" option for search index operations

    Extend createSearchIndex options to include an await boolean type that polls listSearchIndexes to determine the state of a search index operation. Something like this:

    db.movies.createSearchIndex(
    "example-index",
    { mappings: { dynamic: true }, await: true },
    )

    Index creation used to have an option to create indexes in the "foreground" which is essentially the same as the request in this ticket.

    As Atlas Vector Search becomes more popular, drivers are likely to see a number of user complaints about the asynchronous nature of operating search indexes. The specifications expect users to poll listSearchIndexes to determine the state of the operation. Given…

    1 vote
    0 comments  ·  Admin →
    How important is this to you?
  • Don't see your idea?

Vector Search

Categories

Feedback and Knowledge Base

(thinking…)