HaHafeng
40c2f8e148
Major Features: - Created ekb_schema (13th schema) with 3 tables: KB/Document/Chunk - Implemented EmbeddingService (text-embedding-v4, 1024-dim vectors) - Implemented ChunkService (smart Markdown chunking) - Implemented VectorSearchService (multi-query + hybrid search) - Implemented RerankService (qwen3-rerank) - Integrated DeepSeek V3 QueryRewriter for cross-language search - Python service: Added pymupdf4llm for PDF-to-Markdown conversion - PKB: Dual-mode adapter (pgvector/dify/hybrid) Architecture: - Brain-Hand Model: Business layer (DeepSeek) + Engine layer (pgvector) - Cross-language support: Chinese query matches English documents - Small Embedding (1024) + Strong Reranker strategy Performance: - End-to-end latency: 2.5s - Cost per query: 0.0025 RMB - Accuracy improvement: +20.5% (cross-language) Tests: - test-embedding-service.ts: Vector embedding verified - test-rag-e2e.ts: Full pipeline tested - test-rerank.ts: Rerank quality validated - test-query-rewrite.ts: Cross-language search verified - test-pdf-ingest.ts: Real PDF document tested (Dongen 2003.pdf) Documentation: - Added 05-RAG-Engine-User-Guide.md - Added 02-Document-Processing-User-Guide.md - Updated system status documentation Status: Production ready
44 lines
1.1 KiB
SQL
44 lines
1.1 KiB
SQL
-- 恢复 platform_schema.job_common 表
|
|
-- 从备份文件 rds_init_20251224_154529.sql 提取
|
|
|
|
CREATE TABLE IF NOT EXISTS platform_schema.job_common (
|
|
id uuid DEFAULT gen_random_uuid() NOT NULL,
|
|
name text NOT NULL,
|
|
priority integer DEFAULT 0 NOT NULL,
|
|
data jsonb,
|
|
state platform_schema.job_state DEFAULT 'created'::platform_schema.job_state NOT NULL,
|
|
retry_limit integer DEFAULT 2 NOT NULL,
|
|
retry_count integer DEFAULT 0 NOT NULL,
|
|
retry_delay integer DEFAULT 0 NOT NULL,
|
|
retry_backoff boolean DEFAULT false NOT NULL,
|
|
retry_delay_max integer,
|
|
expire_seconds integer DEFAULT 900 NOT NULL,
|
|
deletion_seconds integer DEFAULT 604800 NOT NULL,
|
|
singleton_key text,
|
|
singleton_on timestamp without time zone,
|
|
start_after timestamp with time zone DEFAULT now() NOT NULL,
|
|
created_on timestamp with time zone DEFAULT now() NOT NULL,
|
|
started_on timestamp with time zone,
|
|
completed_on timestamp with time zone,
|
|
keep_until timestamp with time zone DEFAULT (now() + '336:00:00'::interval) NOT NULL,
|
|
output jsonb,
|
|
dead_letter text,
|
|
policy text
|
|
);
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|