Commit Graph

18 Commits

Author SHA1 Message Date
ochan.kwon 744a367f16 feat(retriever): add OpenSearch type prep ahead of Phase 3 driver
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).
2026-05-22 20:43:50 +08:00
ochan.kwon fd3d9f547c feat(search): fan-out KB retrieval across bound vector stores
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.
2026-05-20 22:25:39 +08:00
ochan.kwon 0e8de6192c feat(knowledge-base): validate vector store bindings on create, copy, and delete
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.
2026-05-18 15:58:46 +08:00
ochan.kwon 7478e3cddb refactor(retriever): introduce factory for KB-scoped retrieve engine resolution
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.
2026-05-14 15:53:58 +08:00
Claude 0dc32cb0c4 feat(retriever): exponential backoff + safety truncation for embeddings
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
2026-05-06 17:17:07 +08:00
ochan.kwon c5fc05f3d0 feat: add registry dual-map and engine factory for VectorStore
- 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
2026-04-17 00:15:37 +08:00
wizardchen 17604c9b94 perf: 为批量索引添加并发保存优化 2026-01-14 17:21:42 +08:00
wizardchen da1dcb0cda feat: 批量更新tag时更新索引字段 2025-12-30 19:44:53 +08:00
wizardchen b70450ddd8 feat: 支持FAQ索引类型分离,新增is_enabled字段过滤和批量更新优化 2025-12-17 22:04:18 +08:00
wizardchen a50f53d205 feat: Implement delete functionality for generated questions in knowledge base, including API and UI updates 2025-12-04 01:26:30 +08:00
wizardchen eb8bfddfd1 refactor: Update function signatures across multiple files to improve readability by adding context parameters and enhancing code structure 2025-11-28 16:17:52 +08:00
wizardchen 135e33eca4 refactor: Clean up code by removing unnecessary blank lines and improving comments for better readability and maintainability 2025-11-28 16:10:37 +08:00
wizardchen 64c44c9e27 refactor: Update tenant ID handling across the application 2025-11-25 16:30:54 +08:00
wizardchen 057cfd9eb0 feat: Enhance FAQ import functionality and UI improvements
- 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.
2025-11-23 17:32:50 +08:00
wizardchen fdf5d9d781 feat: Implement knowledge tag management and batch updates for FAQ entries
- 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.
2025-11-18 11:48:37 +08:00
wizardchen 25fdaed8ca feat: Implement FAQ functionality in Knowledge Base
- 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.
2025-11-15 01:30:17 +08:00
wizardchen 14d0e663cc feat: Add web search results handling and enhance knowledge retrieval features
- 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.
2025-11-11 22:26:59 +08:00
wizardchen 56eb2bce33 init commit 2025-08-05 15:08:07 +08:00