Feedback

Showing 31 of 4027

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!

Guest almost 2 years ago in Vector Search 1 Submitted

2 VOTE

Make Push-Based Log Export configurable

Currently both mongod and mongo-audit logs pushed every 5 mins. Not every customer/team interested in same frequency and all logs. It would be great if we can customize what logs to be pushed with granularity. - enable mongod or mongo-audit ind...

Guest 8 months ago in Vector Search 0 Submitted

3 VOTE

if you could please improve the exam issue

completed the GenAI but did not get my badge

Guest about 1 year ago in Vector Search 0 Submitted

3 VOTE

Allow the ability when NVME cluster to autoscale up based on CPU and Memory

To provide autoscaling capability for MongoDB NVME clusters based on CPU utilization and memory metrics. This feature would automatically provision additional resources when predefined thresholds are reached, ensuring optimal performance during us...

Guest about 1 year ago in Performance & Optimization 0 Submitted

4 VOTE

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 },...

Guest over 1 year ago in Vector Search 0 Submitted

3 VOTE

Add support for all type of joins like Postgres has and improve performance

$lookup is a performance killer. Joins are crucial parts in every OLTP system. $lookup is the equivalent to join in SQL, however $lookup is slow, doesn't support hash joins or other efficient join algorithm implemented in Postgres for example. Se...

Guest over 1 year ago in Performance & Optimization 1 Submitted

4 VOTE

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.

Guest almost 2 years ago in Vector Search 0 Submitted

6 VOTE

Implement $bucket and $group on indexed values with sub-linear runtime

We noticed that sum $bucket and $group aggregations such as $min, $max, $count are unexpectedly slow even when fully covered by an index, (partially) because the DB scans through the entire index rather than employing optimization approaches such ...

Guest about 3 years ago in Performance & Optimization 0 Submitted

2 VOTE

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.

Guest over 1 year ago in Vector Search 0 Submitted

1 VOTE

vector search index switch

Since the vector name must be explicitly specified when running a query, it is difficult to update the vector without causing downtime or making code changes. It would be useful to have an option in Atlas to switch between two indexes , or to rena...

Guest 9 months ago in Vector Search 0 Submitted

Please enter your email address

FILTER BY CATEGORY