Develop/AIclinicalresearch
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
40c2f8e148d4af0058936394e8e8a1c1c8ec82e2
AIclinicalresearch/backend/test-pkb-migration.http
HaHafeng 40c2f8e148 feat(rag): Complete RAG engine implementation with pgvector 
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
2026-01-21 20:24:29 +08:00

181 lines
4.8 KiB
HTTP
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
###
# PKB模块迁移 - API测试脚本
# 测试v1和v2路由的功能完整性和一致<EFBFBD>?
###
@baseUrl = http://localhost:3000
@userId = user-mock-001
### ============================================
### 阶段3.1: 健康检<EFBFBD>?
### ============================================
### 1. PKB v2健康检<EFBFBD>?
GET {{baseUrl}}/api/v1/pkb/health
Accept: application/json
### ============================================
### 阶段3.2: 知识库CRUD测试
### ============================================
### 2. 获取知识库列表（v1<EFBFBD>?
GET {{baseUrl}}/api/v1/knowledge-bases
Accept: application/json
### 3. 获取知识库列表（v2<EFBFBD>?
GET {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases
Accept: application/json
### 4. 创建知识库（v2<EFBFBD>?
POST {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases
Content-Type: application/json
{
"name": "测试知识库v2-{{$timestamp}}",
"description": "这是一个通过v2 API创建的测试知识库"
}
### 5. 创建知识库（v1 - 对比<EFBFBD>?
POST {{baseUrl}}/api/v1/knowledge-bases
Content-Type: application/json
{
"name": "测试知识库v1-{{$timestamp}}",
"description": "这是一个通过v1 API创建的测试知识库"
}
### 6. 获取知识库详情（v2<EFBFBD>?
# 替换为实际的知识库ID
@kbId = f6ebe476-c50f-4222-83d2-c2525edc6054
GET {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/{{kbId}}
Accept: application/json
### 7. 获取知识库详情（v1 - 对比<EFBFBD>?
GET {{baseUrl}}/api/v1/knowledge-bases/{{kbId}}
Accept: application/json
### 8. 更新知识库（v2<EFBFBD>?
PUT {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/{{kbId}}
Content-Type: application/json
{
"name": "更新后的知识库名称v2",
"description": "通过v2 API更新的描<EFBFBD>?
}
### 9. 获取知识库统计（v2<EFBFBD>?
GET {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/{{kbId}}/stats
Accept: application/json
### 10. 获取知识库统计（v1 - 对比<EFBFBD>?
GET {{baseUrl}}/api/v1/knowledge-bases/{{kbId}}/stats
Accept: application/json
### ============================================
### 阶段3.3: RAG检索测<EFBFBD>?
### ============================================
### 11. RAG检索（v2<EFBFBD>?
GET {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/{{kbId}}/search?query=阿尔兹海默症的治疗方<EFBFBD>?top_k=5
Accept: application/json
### 12. RAG检索（v1 - 对比<EFBFBD>?
GET {{baseUrl}}/api/v1/knowledge-bases/{{kbId}}/search?query=阿尔兹海默症的治疗方<EFBFBD>?top_k=5
Accept: application/json
### ============================================
### 阶段3.4: 文档选择（全文阅读模式）
### ============================================
### 13. 获取文档选择（v2<EFBFBD>?
GET {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/{{kbId}}/document-selection?max_files=7&max_tokens=750000
Accept: application/json
### 14. 获取文档选择（v1 - 对比<EFBFBD>?
GET {{baseUrl}}/api/v1/knowledge-bases/{{kbId}}/document-selection?max_files=7&max_tokens=750000
Accept: application/json
### ============================================
### 阶段3.5: 文档管理测试
### ============================================
### 15. 获取文档列表（通过知识库详情）
GET {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/{{kbId}}
Accept: application/json
### 16. 获取单个文档详情（v2<EFBFBD>?
# 替换为实际的文档ID
@docId = your-document-id
GET {{baseUrl}}/api/v1/pkb/knowledge/documents/{{docId}}
Accept: application/json
### ============================================
### 阶段3.6: 批处理功能测<EFBFBD>?
### ============================================
### 17. 获取批处理模板（v2<EFBFBD>?
GET {{baseUrl}}/api/v1/pkb/batch-tasks/batch/templates
Accept: application/json
### 18. 创建批处理任务（v2<EFBFBD>?
POST {{baseUrl}}/api/v1/pkb/batch-tasks/batch/execute
Content-Type: application/json
{
"kb_id": "{{kbId}}",
"document_ids": [],
"template_type": "preset",
"template_id": "clinical_research_method",
"model_type": "deepseek-v3",
"task_name": "测试批处理任务v2"
}
### ============================================
### 阶段3.7: 边界条件测试
### ============================================
### 19. 测试不存在的知识库（v2<EFBFBD>?
GET {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/00000000-0000-0000-0000-000000000000
Accept: application/json
### 20. 测试无效的查询参数（v2<EFBFBD>?
GET {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/{{kbId}}/search?query=&top_k=0
Accept: application/json
### 21. 测试超大top_k参数（v2<EFBFBD>?
GET {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/{{kbId}}/search?query=测试&top_k=1000
Accept: application/json
### ============================================
### 阶段3.8: 清理测试数据（可选）
### ============================================
### 22. 删除测试知识库（v2<EFBFBD>?
# @testKbId = 从创建响应中获取的ID
DELETE {{baseUrl}}/api/v1/pkb/knowledge/knowledge-bases/{{testKbId}}
###
Reference in New Issue View Git Blame Copy Permalink