Files
ragflow/conf/models/huaweicloud.json
Hz_ 84add43208 Add HuaweiCloud model provider (#15237)
### What problem does this PR solve?

  This PR adds HuaweiCloud provider integration in RAGFlow.

  Supported capabilities:

  - [x] Chat / Think Chat / Stream Chat / Stream Think Chat
  - [x] Embedding
  - [x] Rerank
  - [x] Model listing
  - [x] Provider connection checking

  Verified examples from the CLI:

  ```
  check instance 'test' from 'HuaweiCloud';

  chat with 'deepseek-v4-flash@test@HuaweiCloud' message 'hello';

  think chat with 'deepseek-v4-flash@test@HuaweiCloud' message 'hello';

  stream chat with 'deepseek-v4-flash@test@HuaweiCloud' message 'hello';

stream think chat with 'deepseek-v4-flash@test@HuaweiCloud' message
'hello';

embed text 'what is rag' 'who are you' with 'bge-m3@test@HuaweiCloud'
dimension 1024;

rerank query 'what is rag' document 'rag is retrieval augmented
generation' 'rag need llm' 'famous rag
project includes ragflow' with 'bge-reranker-v2-m3@test@HuaweiCloud' top
3;

  list supported models from 'HuaweiCloud' 'test';

  LIST MODELS FROM 'HuaweiCloud' 'test';
```
  ### Type of change

  - [x] New Feature
  - [x] Provider integration
2026-05-26 17:13:15 +08:00

219 lines
4.2 KiB
JSON
Executable File

{
"name": "HuaweiCloud",
"url": {
"default": "https://api.modelarts-maas.com",
"cn-southwest-2": "https://api.modelarts-maas.com",
"ap-southeast-1": "https://api-ap-southeast-1.modelarts-maas.com"
},
"url_suffix": {
"chat": "v2/chat/completions",
"async_chat": "v1/chat/completions",
"models": "v2/models",
"embedding": "v1/embeddings",
"rerank": "v1/rerank"
},
"class": "huaweicloud",
"models": [
{
"name": "deepseek-v4-pro",
"max_tokens": 1048576,
"model_types": [
"chat"
],
"thinking": {
"default_value": true,
"clear_thinking": true
}
},
{
"name": "deepseek-v4-flash",
"max_tokens": 1048576,
"model_types": [
"chat"
],
"thinking": {
"default_value": true,
"clear_thinking": true
}
},
{
"name": "deepseek-v3.2",
"max_tokens": 163840,
"model_types": [
"chat"
],
"thinking": {
"default_value": false,
"clear_thinking": true
}
},
{
"name": "deepseek-v3.1-terminus",
"max_tokens": 131072,
"model_types": [
"chat"
],
"thinking": {
"default_value": false,
"clear_thinking": true
}
},
{
"name": "DeepSeek-V3",
"max_tokens": 131072,
"model_types": [
"chat"
]
},
{
"name": "deepseek-r1-250528",
"max_tokens": 131072,
"model_types": [
"chat"
],
"thinking": {
"default_value": true,
"clear_thinking": true
}
},
{
"name": "qwen3-235b-a22b",
"max_tokens": 131072,
"model_types": [
"chat"
],
"thinking": {
"default_value": true,
"clear_thinking": true
}
},
{
"name": "qwen3-32b",
"max_tokens": 131072,
"model_types": [
"chat"
],
"thinking": {
"default_value": true,
"clear_thinking": true
}
},
{
"name": "qwen3-30b-a3b",
"max_tokens": 131072,
"model_types": [
"chat"
],
"thinking": {
"default_value": true,
"clear_thinking": true
}
},
{
"name": "kimi-k2.6",
"max_tokens": 262144,
"model_types": [
"chat"
],
"thinking": {
"default_value": true,
"clear_thinking": true
}
},
{
"name": "longcat-flash-chat",
"max_tokens": 131072,
"model_types": [
"chat"
]
},
{
"name": "glm-5",
"max_tokens": 202752,
"model_types": [
"chat"
],
"thinking": {
"default_value": true,
"clear_thinking": true
}
},
{
"name": "glm-5.1",
"max_tokens": 202752,
"model_types": [
"chat"
],
"thinking": {
"default_value": true,
"clear_thinking": true
}
},
{
"name": "qwen2.5-vl-72b",
"max_tokens": 49152,
"model_types": [
"chat",
"vision"
]
},
{
"name": "bge-m3",
"max_tokens": 8000,
"model_types": [
"embedding"
]
},
{
"name": "bge-reranker-v2-m3",
"max_tokens": 8000,
"model_types": [
"rerank"
]
}
],
"features": {
"thinking": {
"default_value": true,
"supported_models": [
"deepseek-v4-pro",
"deepseek-v4-flash",
"deepseek-v3.2",
"deepseek-v3.1-terminus",
"deepseek-r1-250528",
"qwen3-235b-a22b",
"qwen3-32b",
"qwen3-30b-a3b",
"kimi-k2.6",
"glm-5",
"glm-5.1"
]
},
"clear_thinking": {
"default_value": true,
"supported_models": [
"deepseek-v4-pro",
"deepseek-v4-flash",
"deepseek-v3.2",
"deepseek-v3.1-terminus",
"deepseek-r1-250528",
"qwen3-235b-a22b",
"qwen3-32b",
"qwen3-30b-a3b",
"kimi-k2.6",
"glm-5",
"glm-5.1"
]
},
"reasoning": {
"type": "effort",
"enabled": true,
"default": "high",
"options": [
"high",
"max"
]
}
}
}