enhancement:support Qdrant gRPC mode

[leslie2046]

Description

According my test,gRPC mode seems take lower latency than REST mode.

次数	search （HTTP）latency(s)	search （gRPC）latency(s)	scroll（HTTP） latency(s)	scroll （gRPC）latency(s)	client（HTTP）初始化	client（gRPC）初始化
1	0.0489	0.0157	0.0132	0.0129	0.0043	0.0029
2	0.0490	0.0166	0.0129	0.0105	0.0037	0.0043
3	0.0453	0.0128	0.0172	0.0089	0.0028	0.0029
4	0.0569	0.0092	0.0164	0.0099	0.0040	0.0023
5	0.0494	0.0134	0.0136	0.0085	0.0032	0.0017
avg	0.0491	0.0135	0.0148	0.0107	0.0036	0.0028

User guide

docker deployment

1. We can enable gRPC mode by setting these environment variables in api and worker container in docker-compose.yaml:

QDRANT_GRPC_ENABLED:  'true'    
QDRANT_GRPC_PORT: xxxx

2. Add port mapping to port 6334 of the qdrant container as below:

   qdrant:
     image: langgenius/qdrant:v1.7.3
     restart: always
     volumes:
       - ./volumes/qdrant:/qdrant/storage
     environment:
       QDRANT_API_KEY: 'difyai123456'
     # uncomment to expose qdrant port to host
      ports:
       - "6333:6333"
       - "xxxx:6334"

3. You can replace xxxx to your port

source deployment(api)

1. Add 2 lines to api/.env as below:

QDRANT_GRPC_ENABLED=true
QDRANT_GRPC_PORT=xxxx

2. You can replace xxxx to your port

Fixes # (issue)

Type of Change

Please delete options that are not relevant.

• [ ] Bug fix (non-breaking change which fixes an issue)
• [ ] New feature (non-breaking change which adds functionality)
• [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
• [ ] This change requires a documentation update, included: Dify Document
• [x] Improvement, including but not limited to code refactoring, performance optimization, and UI/UX improvement
• [ ] Dependency upgrade

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

• [ ] TODO

Suggested Checklist:

• [x] I have performed a self-review of my own code
• [ ] I have commented my code, particularly in hard-to-understand areas
• [x] My changes generate no new warnings
• [ ] I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods
• [ ] optional I have made corresponding changes to the documentation
• [ ] optional I have added tests that prove my fix is effective or that my feature works
• [ ] optional New and existing unit tests pass locally with my changes