Lays type-system groundwork for the upcoming OpenSearch k-NN driver
(Phase 3 PR 2, see Tencent/WeKnora#1440), with strict feature-gate:
this PR ships only inert constants, schema extensions, and an
unreachable normalizer case. No path activates an OpenSearch
VectorStore yet — creation continues to fail with "not a valid engine
type" until the activation switch lands in Phase 3 PR 3.
Changes:
- OpenSearchRetrieverEngineType constant ("opensearch") in
internal/types/retriever.go. Not added to validEngineTypes /
GetVectorStoreTypes / retrieverEngineMapping yet (gated).
- ConnectionConfig.InsecureSkipVerify (bool, default false) in
internal/types/vectorstore.go, placed inside the // Common section
because it is a cross-driver TLS option. Distinct from the
Qdrant-specific UseTLS, which enables TLS on gRPC — InsecureSkipVerify
only controls verification of an already-TLS HTTPS connection.
AES-GCM Value/Scan round-trips the field as plaintext (it travels
alongside the encrypted Password / APIKey but is not sensitive itself).
- VectorStoreFieldInfo gains four optional fields: Immutable (bool),
Min/Max (*float64), Enum ([]string). All omitempty so existing UI
schema entries serialize identically. The fields will drive the UI
in Phase 3 PR 3 (read-only on Edit + range/enum constraints).
- Six new AuditAction constants under vector_store.* and opensearch.*
namespaces. Definitions only — emission lands in Phase 3 PR 3.
- EngineAwareNormalizer.Normalize is restructured to group engines by
the effective score range observed by the normalizer (not the
theoretical raw cosine range):
Range [-1, 1] (raw cosine, mapped via (score + 1) / 2):
- Milvus (COSINE metric mode). Milvus docs explicitly state the
COSINE metric range is [-1, 1].
Range [0, 1] (passthrough — already on the target scale):
- Elasticsearch v8 / ElasticFaiss. The driver issues a
cosineSimilarity(...) script_score script, and Lucene rejects
negative final scores ("Final relevance scores from the
script_score query cannot be negative" — ES docs); the
effective range observed by the normalizer is therefore [0, 1]
for IR-normalized embeddings. ES was previously grouped with
Milvus and over-corrected via (score + 1) / 2, which inflated
every ES result by 50% in mixed-engine RRF fusion.
- OpenSearch. The k-NN plugin's
SpaceType.COSINESIMIL.scoreTranslation maps the underlying
Lucene/Faiss distance (1 - cosine) to (1 + cosine) / 2 ∈ [0, 1]
before the score reaches us. Source:
github.com/opensearch-project/k-NN at
src/main/java/org/opensearch/knn/index/SpaceType.java
(COSINESIMIL enum, scoreTranslation method).
- Weaviate. The driver requests `certainty`, defined by Weaviate
as (2 - distance) / 2 = (1 + cosine) / 2, intrinsically [0, 1].
- Postgres pgvector / SQLite sqlite-vec / Qdrant /
TencentVectorDB / Doris. The driver computes (1 - cosine_distance)
or normalized inner_product, whose theoretical range is [-1, 1].
The IR-normalized positive-component unit vectors WeKnora
targets (BGE / OpenAI text-embedding-3 / Cohere /
sentence-transformers) keep the observed range in [0, 1];
negative-cosine embedding models would silently clamp to 0
downstream — explicitly documented as the IR-normalization
caveat in the struct godoc.
Dead enum references (ElasticFaiss, Infinity) are flagged in the
godoc with a pointer to internal/types/vectorstore.go's existing
"legacy/experimental, no standalone deployable instance" annotation.
Their case labels are kept for switch exhaustiveness.
Test coverage:
- OpenSearch constant wire value + collision check against existing
10 engines + gated invariant (NOT in validEngineTypes).
- ConnectionConfig.InsecureSkipVerify backward-compat (missing JSON
field deserializes as false) + round-trip + AES-GCM coexistence
with encrypted Password / APIKey.
- VectorStoreFieldInfo omitempty preservation + new-field serialization
+ *float64 pointer distinction (min=0 vs nil).
- AuditAction dot-namespace convention enforcement, prefix invariants
for vector_store.* and opensearch.*, no wire-string collisions, exact
wire-value pins for the six new constants.
- EngineAwareNormalizer:
- CosineRange retains its (score + 1) / 2 coverage but now only for
Milvus.
- UnitInterval now covers the full passthrough group (ES /
ElasticFaiss / OpenSearch / Weaviate / Postgres / SQLite / Qdrant /
Infinity / TencentVectorDB / Doris).
- New TestEngineAwareNormalizer_ElasticsearchCosinePassthrough is an
explicit regression guard for the score-range correction: cos=0.5
maps to 0.5 (not (0.5 + 1) / 2 = 0.75 as an earlier draft assumed).
- OpenSearch passthrough across (0 / 0.5 / 0.75 / 1) + engine drift
(1.0001) + defensive negative + ±Inf / NaN edges + keyword
passthrough + nil-ctx safety.
Backward compatibility is preserved at every layer:
- All new struct fields are omitempty / pointer-tagged so existing
rows and existing wire formats remain unchanged.
- Normalizer's new OpenSearch case is unreachable until the driver
lands. The ES regrouping changes the post-normalization value for
every ES vector search result (a correctness fix, not a feature) —
ES vector retrieval is currently the only production path affected.
- AuditAction constants emit no audit_log rows in this PR.
- engine_type=opensearch VectorStore creation still rejected (gated).
Multi-KB hybrid search now groups KBs by their bound VectorStore (partition
key (storeID, owner_tenant_id)), retrieves in parallel via errgroup with a
SetLimit(4) cap and a per-group timeout (MULTI_STORE_RETRIEVE_TIMEOUT_SEC,
default 30s), and merges results. When the collected results span more than
one engine type, an EngineAwareNormalizer rescales vector scores to [0, 1];
keyword (BM25) scores pass through to the existing RRF fusion. Single-group
calls take the fast path with zero fan-out overhead, preserving today's
behavior for deployments where every KB has vector_store_id = NULL.
Embedding-model consistency is now enforced explicitly via
ResolveEmbeddingModelKeys. Multi-KB searches across KBs whose resolved
model identities differ return BadRequest instead of silently producing
incomparable scores. Cross-tenant Organization-shared KBs are preserved by
partitioning on KB.TenantID so the factory's ownership lookup runs against
the source tenant. Foreign-tenant KB UUIDs injected via the request body
are rejected via kbShareService.HasTenantKBPermission (Plan 3 of #1303,
3-D capped) before any retrieval; rejected scopes surface as 404 to avoid
leaking foreign KB existence.
Service-layer typed AppErrors (ErrVectorStoreBindingInvalid 2200 /
ErrVectorStoreUnavailable 2201) are mapped from PR2 sentinel hierarchy and
preserved end-to-end: the iterative FAQ path returns them rather than
swallowing, and the HybridSearch handler routes typed AppErrors to the
client unchanged instead of downgrading to 500.
Part of #993 (Phase 2: Per-KB VectorStore Binding).
Phase 2 roadmap item: PR 4 (Multi-store fan-out search).
Depends on #994, #1310, #1372.
Wires KnowledgeBase.VectorStoreID and the ownership-aware retrieve factory
into the user-facing knowledge-base lifecycle:
- POST /knowledge-bases validates the requested vector_store_id against
the caller's tenant scope and the engine registry. New error codes
ErrVectorStoreBindingInvalid (2200) and ErrVectorStoreUnavailable (2201)
distinguish the typed branches without echoing UUIDs to the client.
- GET / POST / PUT / PUT-pin responses embed the bound store's display
metadata (name, source, engine_type, status) without exposing any
connection credentials. Cross-tenant shared KBs receive a suppressed
payload (vector_store_id stripped, source="shared") so operator-chosen
store names cannot be enumerated across tenants.
- POST /knowledge-bases/copy synchronously rejects clones whose target
has a different embedding model or vector store, before the async
clone task is enqueued. The async clone worker re-applies the same
checks for defense in depth.
- DELETE /vector-stores/:id refuses to remove a store with bound KBs,
inside a transaction that row-locks the store on PostgreSQL and
serializes via WAL on SQLite. unregister-from-registry is wrapped in
defer/recover so a panic surfaces as a structured warning instead of
silently leaking a stale engine.
- vector_store_id is immutable after creation. The GORM <-:create tag
blocks every ORM update path; the service-layer DTO omits the field
entirely; a reflection-based regression test catches any future
maintainer who adds it back to either layer.
- Empty-string vector_store_id is normalized to nil at both the create
path and inside SharesStoreWith, so rows persisted by callers that
did not run Normalize first cannot trip false same-store comparisons.
Part of #993. Depends on #994 and #1310.
Extracts the 25 repeated NewCompositeRetrieveEngine call sites across
seven services into two factory functions with tenant-ownership
verification: CreateRetrieveEngineForKB (synchronous) and
CreateRetrieveEngineFromPayload (async task handlers). Promotes
GetByStoreID from concrete-only to interfaces.RetrieveEngineRegistry.
Extends KBDeletePayload / IndexDeletePayload with an omitempty
VectorStoreID snapshot.
Design highlights
- Factory verifies tenant ownership of the resolved store
(defense-in-depth) so a gap in PR3 validation or a tampered Asynq
payload cannot cross tenants. Cross-tenant attempts return
ErrVectorStoreForbidden with a structured log entry.
- Sentinel errors (ErrTenantInfoMissing, ErrVectorStoreNotFound,
ErrVectorStoreForbidden) let async handlers classify non-retryable
failures as asynq.SkipRetry.
- nil and empty-string pointers for vectorStoreID normalize to
"unbound" so callers never send an empty UUID to GetByStoreID.
- resolveBoundEngine constructs engineInfos directly (with
slices.Clone of Support()) instead of going through
NewCompositeRetrieveEngine. The latter only reads from the
byEngineType map and cannot reach DB stores in byStoreID -- multiple
stores can share the same engine type. Unbound fallbacks still reuse
NewCompositeRetrieveEngine so the tenant effective-engines path is
byte-for-byte unchanged.
- DeleteKnowledgeBase now reads the KB before soft-delete so the
enqueued KBDeletePayload carries a VectorStoreID snapshot; once the
row is soft-deleted GORM's default scope hides it. Cost: +1 SELECT
per KB-delete request (a rare admin operation).
- enqueueIndexDeleteTask gains a vectorStoreID *string parameter that
the single caller (tag.go) populates from the owning KB. The worker
(ProcessIndexDelete) validates ownership via the factory.
- cleanupKnowledgeResources loads the KB so bound-store cleanup routes
correctly. If the load fails it warns and falls back to tenant
effective engines; orphan vectors become observable in logs instead
of disappearing silently.
- DeleteKnowledges (batch) stays on the tenant effective-engines path
-- batches can span stores and multi-store fan-out is PR4 scope.
Noted inline.
Merge safety
All knowledge bases have VectorStoreID = NULL at merge time (introduced
nullable in PR1, Tencent/WeKnora#994). Every factory call falls back to
NewCompositeRetrieveEngine(registry, tenantInfo.GetEffectiveEngines()),
which is the existing code path for these KBs. Async payloads from
before this change decode to VectorStoreID = nil (omitempty) and take
the same fallback.
Testing
- go build ./...
- go vet ./...
- go test -race -count=1 ./internal/application/service/retriever/...
covers unbound (nil/empty), bound, cross-tenant, unregistered store,
ownership infra error, legacy payload shapes (missing field/null/
empty string/nil), tampered payload, and parallel invocation.
- grep -r NewCompositeRetrieveEngine internal/application/service
returns zero results outside factory.go/composite.go.
Refs: Part of Tencent/WeKnora#993. Depends on Tencent/WeKnora#994.
batchEmbedWithBackoff replaces the previous fixed 100ms × 5 retry loop
with proper exponential backoff (200/400/800/1600/3200 ms) and respects
context cancellation between attempts. sanitizeForEmbedding caps any
single embedding input at 20k runes — well above realistic chunk
budgets, so it only triggers on pathologically large inputs and logs
a warning when it does.
https://claude.ai/code/session_01XADhx6mtu2ZYW3DE9Lun6k
- Extend RetrieveEngineRegistry with byStoreID map for DB store engines
- Add StoreRegistry interface and EngineFactory function type
- Create engine factory with per-driver SDK client construction
- Load VectorStore records from DB into registry at startup
- Wire Create/Delete to dynamically register/unregister engines
- Add comprehensive unit tests for registry and service
- Added support for tracking the status of FAQ import tasks, including progress indicators for ongoing imports.
- Introduced new localization strings for processing tasks and batch operations in multiple languages.
- Updated the FAQ entry manager to display import progress and improved user feedback during the import process.
- Enhanced the KnowledgeBase component to reflect the processing state of knowledge items, improving user experience during document uploads.
- Implemented batch deletion functionality for chunks, streamlining the management of knowledge base content.
- Added API functions for listing, creating, updating, and deleting knowledge base tags.
- Introduced batch update functionality for enabling/disabling FAQ entries and updating their tags.
- Enhanced the KnowledgeBase.vue and FAQEntryManager.vue components to support tag management and batch operations.
- Updated localization files to include new strings related to tag management and batch operations.
- Added support for creating and managing FAQ knowledge bases, including new API endpoints for listing, upserting, updating, and deleting FAQ entries.
- Enhanced the frontend to allow users to create FAQ knowledge bases and manage FAQ entries with a dedicated interface.
- Introduced new types and configurations for FAQ handling in the backend, ensuring proper indexing and retrieval of FAQ entries.
- Updated localization files to include new strings related to FAQ management in multiple languages.
- Refactored existing components to accommodate the new FAQ features, improving user experience and functionality.
- Introduced a new endpoint to fetch chunks by ID, improving access to specific knowledge base entries.
- Updated tool result types to include web search results, enhancing the display capabilities in the chat component.
- Enhanced the AgentStreamDisplay component to support rendering web search results with improved HTML formatting.
- Implemented logic for managing web search result summaries and citations, ensuring a cohesive user experience.
- Refactored session management to accommodate new web search functionalities, improving overall system integration.