[BUG] schema: build default with config ef & knn_index, remove #document population in defaults

jairad26 · jairad26 · commit 463f83b9124c · 2025-11-03T12:52:15.000-08:00
diff --git a/go/pkg/sysdb/coordinator/model/collection_configuration.go b/go/pkg/sysdb/coordinator/model/collection_configuration.go
@@ -249,7 +249,7 @@ type ValueTypes struct {
 	SparseVector *SparseVectorValueType `json:"sparse_vector,omitempty"`
 	Int          *IntValueType          `json:"int,omitempty"`
 	Float        *FloatValueType        `json:"float,omitempty"`
-	Boolean      *BoolValueType         `json:"boolean,omitempty"`
+	Boolean      *BoolValueType         `json:"bool,omitempty"`
 }
 
 type Schema struct {
diff --git a/rust/cli/src/commands/vacuum.rs b/rust/cli/src/commands/vacuum.rs
@@ -11,7 +11,7 @@ use chroma_segment::local_segment_manager::LocalSegmentManager;
 use chroma_sqlite::db::SqliteDb;
 use chroma_sysdb::SysDb;
 use chroma_system::System;
-use chroma_types::{CollectionUuid, KnnIndex, ListCollectionsRequest};
+use chroma_types::{CollectionUuid, KnnIndex, ListCollectionsRequest, Schema};
 use clap::Parser;
 use colored::Colorize;
 use dialoguer::Confirm;
@@ -108,10 +108,15 @@ async fn trigger_vector_segments_max_seq_id_migration(
     for collection_id in collection_ids {
         let mut collection = sysdb.get_collection_with_segments(collection_id).await?;
 
-        collection
-            .collection
-            .reconcile_schema_with_config(default_knn_index)
-            .map_err(|e| Box::new(e) as Box<dyn Error>)?;
+        if collection.collection.schema.is_none() {
+            collection.collection.schema = Some(
+                Schema::convert_collection_config_to_schema(
+                    &collection.collection.config,
+                    default_knn_index,
+                )
+                .map_err(|e| Box::new(e) as Box<dyn Error>)?,
+            );
+        }
 
         // If collection is uninitialized, that means nothing has been written yet.
         let dim = match collection.collection.dimension {
diff --git a/rust/frontend/src/get_collection_with_segments_provider.rs b/rust/frontend/src/get_collection_with_segments_provider.rs
@@ -185,14 +185,16 @@ impl CollectionsWithSegmentsProvider {
                 .await?
         };
 
-        // reconcile schema and config
-        let reconciled_schema = Schema::reconcile_schema_and_config(
-            collection_and_segments_sysdb.collection.schema.as_ref(),
-            Some(&collection_and_segments_sysdb.collection.config),
-            knn_index,
-        )
-        .map_err(CollectionsWithSegmentsProviderError::InvalidSchema)?;
-        collection_and_segments_sysdb.collection.schema = Some(reconciled_schema);
+        if collection_and_segments_sysdb.collection.schema.is_none() {
+            collection_and_segments_sysdb.collection.schema = Some(
+                Schema::convert_collection_config_to_schema(
+                    &collection_and_segments_sysdb.collection.config,
+                    knn_index,
+                )
+                .map_err(CollectionsWithSegmentsProviderError::InvalidSchema)?,
+            );
+        }
+
         self.set_collection_with_segments(collection_and_segments_sysdb.clone())
             .await;
         Ok(collection_and_segments_sysdb)
diff --git a/rust/frontend/src/impls/service_based_frontend.rs b/rust/frontend/src/impls/service_based_frontend.rs
@@ -381,7 +381,7 @@ impl ServiceBasedFrontend {
         if self.enable_schema {
             for collection in collections.iter_mut() {
                 collection
-                    .reconcile_schema_with_config(self.default_knn_index)
+                    .reconcile_schema_for_read(self.default_knn_index)
                     .map_err(GetCollectionsError::InvalidSchema)?;
             }
         }
@@ -425,7 +425,7 @@ impl ServiceBasedFrontend {
         if self.enable_schema {
             for collection in &mut collections {
                 collection
-                    .reconcile_schema_with_config(self.default_knn_index)
+                    .reconcile_schema_for_read(self.default_knn_index)
                     .map_err(GetCollectionError::InvalidSchema)?;
             }
         }
@@ -450,7 +450,7 @@ impl ServiceBasedFrontend {
 
         if self.enable_schema {
             collection
-                .reconcile_schema_with_config(self.default_knn_index)
+                .reconcile_schema_for_read(self.default_knn_index)
                 .map_err(GetCollectionByCrnError::InvalidSchema)?;
         }
         Ok(collection)
@@ -630,9 +630,10 @@ impl ServiceBasedFrontend {
         // that was retrieved from sysdb, rather than the one that was passed in
         if self.enable_schema {
             collection
-                .reconcile_schema_with_config(self.default_knn_index)
+                .reconcile_schema_for_read(self.default_knn_index)
                 .map_err(CreateCollectionError::InvalidSchema)?;
         }
+
         Ok(collection)
     }
 
@@ -735,7 +736,7 @@ impl ServiceBasedFrontend {
             .await?;
         collection_and_segments
             .collection
-            .reconcile_schema_with_config(self.default_knn_index)
+            .reconcile_schema_for_read(self.default_knn_index)
             .map_err(ForkCollectionError::InvalidSchema)?;
         let collection = collection_and_segments.collection.clone();
         let latest_collection_logical_size_bytes = collection_and_segments
diff --git a/rust/log/src/local_compaction_manager.rs b/rust/log/src/local_compaction_manager.rs
@@ -15,7 +15,7 @@ use chroma_sysdb::SysDb;
 use chroma_system::Handler;
 use chroma_system::{Component, ComponentContext};
 use chroma_types::{
-    Chunk, CollectionUuid, GetCollectionWithSegmentsError, KnnIndex, LogRecord, SchemaError,
+    Chunk, CollectionUuid, GetCollectionWithSegmentsError, KnnIndex, LogRecord, Schema, SchemaError,
 };
 use serde::{Deserialize, Serialize};
 use thiserror::Error;
@@ -141,9 +141,15 @@ impl Handler<BackfillMessage> for LocalCompactionManager {
             .get_collection_with_segments(message.collection_id)
             .await?;
         let schema_previously_persisted = collection_and_segments.collection.schema.is_some();
-        collection_and_segments
-            .collection
-            .reconcile_schema_with_config(KnnIndex::Hnsw)?;
+        if !schema_previously_persisted {
+            collection_and_segments.collection.schema = Some(
+                Schema::convert_collection_config_to_schema(
+                    &collection_and_segments.collection.config,
+                    KnnIndex::Hnsw,
+                )
+                .map_err(CompactionManagerError::SchemaReconcileError)?,
+            );
+        }
         // If collection is uninitialized, that means nothing has been written yet.
         let dim = match collection_and_segments.collection.dimension {
             Some(dim) => dim,
@@ -267,7 +273,12 @@ impl Handler<PurgeLogsMessage> for LocalCompactionManager {
             .get_collection_with_segments(message.collection_id)
             .await?;
         let mut collection = collection_segments.collection.clone();
-        collection.reconcile_schema_with_config(KnnIndex::Hnsw)?;
+        if collection.schema.is_none() {
+            collection.schema = Some(
+                Schema::convert_collection_config_to_schema(&collection.config, KnnIndex::Hnsw)
+                    .map_err(CompactionManagerError::SchemaReconcileError)?,
+            );
+        }
         // If dimension is None, that means nothing has been written yet.
         let dim = match collection.dimension {
             Some(dim) => dim,
diff --git a/rust/types/src/collection.rs b/rust/types/src/collection.rs
@@ -243,6 +243,23 @@ impl Collection {
         Ok(())
     }
 
+    /// Reconcile the collection schema and configuration when serving read requests.
+    ///
+    /// The read path needs to tolerate collections that only have a configuration persisted.
+    /// This helper hydrates `schema` from the stored configuration when needed, or regenerates
+    /// the configuration from the existing schema to keep both representations consistent.
+    pub fn reconcile_schema_for_read(&mut self, knn_index: KnnIndex) -> Result<(), SchemaError> {
+        if let Some(schema) = self.schema.as_ref() {
+            self.config = InternalCollectionConfiguration::try_from(schema)
+                .map_err(|reason| SchemaError::InvalidSchema { reason })?;
+        } else {
+            let schema = Schema::convert_collection_config_to_schema(&self.config, knn_index)?;
+            self.schema = Some(schema);
+        }
+
+        Ok(())
+    }
+
     pub fn test_collection(dim: i32) -> Self {
         Collection {
             name: "test_collection".to_string(),
diff --git a/rust/types/src/collection_schema.rs b/rust/types/src/collection_schema.rs

Original file line number	Diff line number	Diff line change
`@@ -249,7 +249,7 @@ type ValueTypes struct {`
`249`	`249`	SparseVector *SparseVectorValueType `json:"sparse_vector,omitempty"`
`250`	`250`	Int *IntValueType `json:"int,omitempty"`
`251`	`251`	Float *FloatValueType `json:"float,omitempty"`
`252`		- Boolean *BoolValueType `json:"boolean,omitempty"`
	`252`	+ Boolean *BoolValueType `json:"bool,omitempty"`
`253`	`253`	`}`
`254`	`254`
`255`	`255`	`type Schema struct {`