mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-08-31 00:50:02 +08:00
wizardchen
04f56f9cda
Adds a five-segment progress model for the document parsing pipeline so the UI (PR③) can render a timeline showing where each document is (DocReader → Chunking → Embedding → Multimodal → PostProcess) and which stage failed with what error code. - New table `knowledge_processing_stages` (migration 000052) with one row per (knowledge_id, stage). UPSERT on Begin/Done/Fail bumps an attempt counter so re-parses don't lose history. - StageTracker service exposes Begin/Done/Fail/Skip; all calls are best-effort and never break the pipeline if persistence fails. - Stable error codes (DOCREADER_TIMEOUT / EMBEDDING_RATE_LIMIT / VECTORSTORE_WRITE_FAILED / ...) the UI can map to localized remediation hints. - Tracker call sites added at the four meaningful failure points: convert (DocReader), CreateChunks (Chunking), BatchIndex (Embedding), enqueueImageMultimodalTasks (Multimodal start), KnowledgePostProcess.Handle (Multimodal close + PostProcess). - New endpoint `GET /api/v1/knowledge/:id/stages` returns the five canonical stages — missing rows are synthesized as "pending" so the timeline always renders five segments. Includes current_stage and last_error block.
64 lines
2.8 KiB
Go
64 lines
2.8 KiB
Go
// Package errors: parse stage error codes.
|
|
//
|
|
// These constants are the stable wire format the frontend uses to map a
|
|
// failure to a localized "what to do about it" message. Adding a new code
|
|
// is non-breaking; renaming an existing one requires a coordinated
|
|
// frontend release because the i18n keys are looked up by code.
|
|
//
|
|
// Codes are SCREAMING_SNAKE so they survive JSON case transforms and look
|
|
// distinct from Go identifiers in logs/dashboards.
|
|
package errors
|
|
|
|
const (
|
|
// ErrCodeDocReaderTimeout — DocReader RPC exceeded
|
|
// WEKNORA_DOCREADER_CALL_TIMEOUT (default 30m). Suggest splitting
|
|
// large files or checking docreader load.
|
|
ErrCodeDocReaderTimeout = "DOCREADER_TIMEOUT"
|
|
|
|
// ErrCodeDocReaderUnavailable — no DocReader configured for the
|
|
// requested file type / engine, or the service refused connection.
|
|
ErrCodeDocReaderUnavailable = "DOCREADER_UNAVAILABLE"
|
|
|
|
// ErrCodeDocReaderParseFailed — DocReader returned an explicit parse
|
|
// error (encoding, corrupted file, OCR engine crash, ...).
|
|
ErrCodeDocReaderParseFailed = "DOCREADER_PARSE_FAILED"
|
|
|
|
// ErrCodeChunkingFailed — text chunking step itself failed (rare;
|
|
// usually only on extreme-size inputs).
|
|
ErrCodeChunkingFailed = "CHUNKING_FAILED"
|
|
|
|
// ErrCodeEmbeddingRateLimit — embedding provider returned 429 or
|
|
// equivalent. Suggest retrying later or scaling out.
|
|
ErrCodeEmbeddingRateLimit = "EMBEDDING_RATE_LIMIT"
|
|
|
|
// ErrCodeEmbeddingProviderFail — non-rate-limit embedding error
|
|
// (auth, model not found, bad input). Usually permanent without
|
|
// config changes.
|
|
ErrCodeEmbeddingProviderFail = "EMBEDDING_PROVIDER_FAIL"
|
|
|
|
// ErrCodeVectorStoreWriteFailed — chunks embedded fine but the
|
|
// vector DB write failed (quota, connectivity, schema mismatch).
|
|
ErrCodeVectorStoreWriteFailed = "VECTORSTORE_WRITE_FAILED"
|
|
|
|
// ErrCodeMultimodalVLMFailed — a single image's OCR or caption call
|
|
// failed. Note: per-image failures don't fail the whole parent;
|
|
// see image_multimodal.go finalize-on-last-attempt.
|
|
ErrCodeMultimodalVLMFailed = "MULTIMODAL_VLM_FAILED"
|
|
|
|
// ErrCodeMultimodalAllFailed — every image task hit dead-letter.
|
|
// The parent still completes (caption / OCR is optional content),
|
|
// but stage status is marked failed so the UI can warn.
|
|
ErrCodeMultimodalAllFailed = "MULTIMODAL_ALL_FAILED"
|
|
|
|
// ErrCodeTaskTimeout — asynq retry budget exhausted. Used by the
|
|
// dead-letter callback when promoting a task failure into a stage
|
|
// failure. Distinct from DocReaderTimeout: this is the asynq-level
|
|
// timeout (whole task), not the docreader-call-level timeout.
|
|
ErrCodeTaskTimeout = "TASK_TIMEOUT"
|
|
|
|
// ErrCodeUnknown — fallback when a wrapped error doesn't classify.
|
|
// The full message is still recorded in error_detail so operators
|
|
// can debug; the UI shows a generic "see admin" hint.
|
|
ErrCodeUnknown = "UNKNOWN"
|
|
)
|