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
76 lines
1.2 KiB
Bash
76 lines
1.2 KiB
Bash
#!/bin/bash
|
|
set -e
|
|
|
|
# 鈿狅笍 鍏抽敭锛氫笉缁欓粯璁ゅ€硷紝寮哄埗鍦?SAE 鎺у埗鍙伴厤缃?
|
|
# 濡傛灉鏈厤缃紝鎶ラ敊閫€鍑猴紙閬垮厤浣跨敤閿欒鐨勫悗绔湴鍧€锛?
|
|
if [ -z "$BACKEND_SERVICE_HOST" ]; then
|
|
echo "鉂?ERROR: BACKEND_SERVICE_HOST environment variable is required!"
|
|
echo "Please configure it in SAE console with backend internal IP (e.g., 172.17.x.x)"
|
|
exit 1
|
|
fi
|
|
|
|
if [ -z "$BACKEND_SERVICE_PORT" ]; then
|
|
echo "鈿狅笍 WARNING: BACKEND_SERVICE_PORT not set, using default: 3001"
|
|
export BACKEND_SERVICE_PORT=3001
|
|
fi
|
|
|
|
echo "============================================"
|
|
echo "Starting Frontend Nginx Service"
|
|
echo "Backend Service: ${BACKEND_SERVICE_HOST}:${BACKEND_SERVICE_PORT}"
|
|
echo "Container Timezone: $(cat /etc/timezone)"
|
|
echo "Current Time: $(date)"
|
|
echo "============================================"
|
|
|
|
# 浣跨敤 envsubst 鏇挎崲 Nginx 閰嶇疆涓殑鐜鍙橀噺
|
|
envsubst '${BACKEND_SERVICE_HOST} ${BACKEND_SERVICE_PORT}' \
|
|
< /etc/nginx/templates/nginx.conf.template \
|
|
> /etc/nginx/nginx.conf
|
|
|
|
# 楠岃瘉 Nginx 閰嶇疆
|
|
nginx -t
|
|
|
|
# 鍚姩 Nginx
|
|
exec nginx -g 'daemon off;'
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|