v0.2.1

Tencent/WeKnorav0.2.1Dec 8, 2025by lyingbug

AI Summary

This minor release (v0.2.1) introduces Qdrant vector database support with both vector similarity and full-text keyword search capabilities, including Chinese word segmentation via jieba. The release also brings significant infrastructure improvements including Docker Compose profile management for optional services, enhanced database migration with automatic dirty state recovery, and simplified retriever engine configuration through environment variables.

Key Highlights

Qdrant Vector Database integration with full-text keyword search and vector similarity capabilities
Docker Compose profile management with optional services (minio, qdrant, neo4j, jaeger, full)
Database migration system improvements with automatic dirty state recovery and Neo4j retry mechanism
Retriever engine auto-configuration from RETRIEVE_DRIVER environment variable
Fixed Qdrant Chinese keyword search and simplified image URL validation

New Features

Qdrant vector database support with vector similarity and full-text search
Dynamic Qdrant collection creation based on embedding dimensions (e.g., weknora_embeddings_768)
Chinese word segmentation using jieba for keyword queries
Docker Compose profiles for optional services: minio, qdrant, neo4j, jaeger, full
Enhanced dev.sh script with --minio, --qdrant, --neo4j, --jaeger, --full flags
Pinned Qdrant Docker image to v1.16.2
Automatic dirty state recovery for failed migrations
Neo4j connection retry mechanism with exponential backoff
GetEffectiveEngines() method for dynamic engine resolution
Centralized engine mapping in types/tenant.go

Full Release Notes

## [0.2.1] - 2025-12-08

### 🚀 New Features
- **NEW**: Qdrant Vector Database Support
  - Full integration with Qdrant as retriever engine
  - Support for both vector similarity search and full-text keyword search
  - Dynamic collection creation based on embedding dimensions (e.g., `weknora_embeddings_768`)
  - Professional Chinese word segmentation using jieba for keyword queries

### ⚡ Infrastructure Improvements
- **IMPROVED**: Docker Compose Profile Management
  - Added profiles for optional services: `minio`, `qdrant`, `neo4j`, `jaeger`, `full`
  - Enhanced `dev.sh` script with `--minio`, `--qdrant`, `--neo4j`, `--jaeger`, `--full` flags
  - Pinned Qdrant Docker image version to `v1.16.2` for stability
- **IMPROVED**: Database Migration System
  - Added automatic dirty state recovery for failed migrations
  - Added Neo4j connection retry mechanism with exponential backoff
  - Improved migration error handling and logging
- **IMPROVED**: Retriever Engine Configuration
  - Retriever engines now auto-configured from `RETRIEVE_DRIVER` environment variable
  - No longer required to write retriever config during user registration
  - Added `GetEffectiveEngines()` method for dynamic engine resolution
  - Centralized engine mapping in `types/tenant.go`

### 🐛 Bug Fixes
- **FIXED**: Qdrant keyword search returning empty results for Chinese queries
- **FIXED**: Image URL validation logic simplified for better compatibility