Skip to content

[ENH] Add impl to stop indexing when metadata index set to false #5060

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.

Sign up for GitHub

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

Draft
wants to merge 1 commit into
base: jai/schema
Choose a base branch
from
Draft

[ENH] Add impl to stop indexing when metadata index set to false #5060

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
76 changes: 76 additions & 0 deletions rust/segment/src/blockfile_metadata.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ use chroma_types::F32_METADATA;
use chroma_types::FULL_TEXT_PLS;
use chroma_types::STRING_METADATA;
use chroma_types::U32_METADATA;
use chroma_types::{CollectionSchema, ValueType};
use chroma_types::{MaterializedLogOperation, MetadataValue, Segment, SegmentUuid};
use core::panic;
use roaring::RoaringBitmap;
Expand All @@ -37,6 +38,7 @@ pub struct MetadataSegmentWriter<'me> {
pub(crate) f32_metadata_index_writer: Option<MetadataIndexWriter<'me>>,
pub(crate) u32_metadata_index_writer: Option<MetadataIndexWriter<'me>>,
pub id: SegmentUuid,
pub schema: Option<HashMap<String, HashMap<ValueType, CollectionSchema>>>,
}

impl Debug for MetadataSegmentWriter<'_> {
Expand Down Expand Up @@ -102,6 +104,7 @@ impl<'me> MetadataSegmentWriter<'me> {
database_id: &DatabaseUuid,
segment: &Segment,
blockfile_provider: &BlockfileProvider,
schema: Option<HashMap<String, HashMap<ValueType, CollectionSchema>>>,
) -> Result<MetadataSegmentWriter<'me>, MetadataSegmentError> {
if segment.r#type != SegmentType::BlockfileMetadata {
return Err(MetadataSegmentError::InvalidSegmentType);
Expand Down Expand Up @@ -316,6 +319,7 @@ impl<'me> MetadataSegmentWriter<'me> {
f32_metadata_index_writer: Some(f32_metadata_index_writer),
u32_metadata_index_writer: Some(u32_metadata_index_writer),
id: segment.id,
schema,
})
}

Expand All @@ -325,6 +329,37 @@ impl<'me> MetadataSegmentWriter<'me> {
key: &MetadataValue,
offset_id: u32,
) -> Result<(), MetadataIndexError> {
let mut should_index = true;
if let Some(schema) = &self.schema {
let schema_key = prefix;
if let Some(value_type_map) = schema.get(schema_key) {
match key {
MetadataValue::Str(_) => {
if let Some(value_type_map) = value_type_map.get(&ValueType::String) {
should_index = value_type_map.metadata_index;
}
}
MetadataValue::Int(_) => {
if let Some(value_type_map) = value_type_map.get(&ValueType::Int) {
should_index = value_type_map.metadata_index;
}
}
MetadataValue::Float(_) => {
if let Some(value_type_map) = value_type_map.get(&ValueType::Float) {
should_index = value_type_map.metadata_index;
}
}
MetadataValue::Bool(_) => {
if let Some(value_type_map) = value_type_map.get(&ValueType::Boolean) {
should_index = value_type_map.metadata_index;
}
}
}
}
}
if !should_index {
return Ok(());
}
match key {
MetadataValue::Str(v) => {
match &self.string_metadata_index_writer {
Expand Down Expand Up @@ -391,6 +426,37 @@ impl<'me> MetadataSegmentWriter<'me> {
key: &MetadataValue,
offset_id: u32,
) -> Result<(), MetadataIndexError> {
let mut should_index = true;
if let Some(schema) = &self.schema {
let schema_key = prefix;
if let Some(value_type_map) = schema.get(schema_key) {
match key {
MetadataValue::Str(_) => {
if let Some(value_type_map) = value_type_map.get(&ValueType::String) {
should_index = value_type_map.metadata_index;
}
}
MetadataValue::Int(_) => {
if let Some(value_type_map) = value_type_map.get(&ValueType::Int) {
should_index = value_type_map.metadata_index;
}
}
MetadataValue::Float(_) => {
if let Some(value_type_map) = value_type_map.get(&ValueType::Float) {
should_index = value_type_map.metadata_index;
}
}
MetadataValue::Bool(_) => {
if let Some(value_type_map) = value_type_map.get(&ValueType::Boolean) {
should_index = value_type_map.metadata_index;
}
}
}
}
}
if !should_index {
return Ok(());
}
match key {
MetadataValue::Str(v) => {
match &self.string_metadata_index_writer {
Expand Down Expand Up @@ -1063,6 +1129,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down Expand Up @@ -1202,6 +1269,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down Expand Up @@ -1291,6 +1359,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down Expand Up @@ -1388,6 +1457,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down Expand Up @@ -1530,6 +1600,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down Expand Up @@ -1658,6 +1729,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down Expand Up @@ -1773,6 +1845,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down Expand Up @@ -1897,6 +1970,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down Expand Up @@ -2001,6 +2075,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down Expand Up @@ -2124,6 +2199,7 @@ mod test {
&database_id,
&metadata_segment,
&blockfile_provider,
None,
)
.await
.expect("Error creating segment writer");
Expand Down
1 change: 1 addition & 0 deletions rust/segment/src/test.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,7 @@ impl TestDistributedSegment {
&self.collection.database_id,
&self.metadata_segment,
&self.blockfile_provider,
self.collection.config.schema.clone(),
)
.await
.expect("Should be able to initialize metadata writer.");
Expand Down
22 changes: 22 additions & 0 deletions rust/types/src/collection_configuration.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -484,6 +484,28 @@ pub struct UpdateCollectionConfiguration {
pub schema: Option<HashMap<String, HashMap<ValueType, CollectionSchema>>>,
}

pub fn diff_metadata_index_enable(
old_schema: &Option<HashMap<String, HashMap<ValueType, CollectionSchema>>>,
update_schema: &HashMap<String, HashMap<ValueType, CollectionSchema>>,
) -> Vec<(String, ValueType)> {
let mut backfill_needed = Vec::new();
for (update_key, update_value) in update_schema {
for (update_value_type, update_collection_schema) in update_value {
let old_metadata_index = old_schema
.as_ref()
.and_then(|s| s.get(update_key))
.and_then(|vt_map| vt_map.get(update_value_type))
.map(|cs| cs.metadata_index)
.unwrap_or(true); // default to true if not present
let new_metadata_index = update_collection_schema.metadata_index;
if !old_metadata_index && new_metadata_index {
backfill_needed.push((update_key.clone(), update_value_type.clone()));
}
}
}
backfill_needed
}

#[cfg(test)]
mod tests {
use crate::hnsw_configuration::HnswConfiguration;
Expand Down
1 change: 1 addition & 0 deletions rust/worker/src/execution/orchestration/compact.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -682,6 +682,7 @@ impl Handler<TaskResult<GetCollectionAndSegmentsOutput, GetCollectionAndSegments
&collection.database_id,
&metadata_segment,
&self.blockfile_provider,
collection.config.schema.clone(),
)
.await,
ctx,
Expand Down
Loading