feat: 新增对多家平台的模型适配

This commit is contained in:
nullkey
2025-12-29 01:31:27 +08:00
committed by lyingbug
parent 0b711a6739
commit e9a2a7b3e5
38 changed files with 2963 additions and 132 deletions
+293 -70
View File
@@ -2,22 +2,100 @@
[返回目录](./README.md)
| 方法 | 路径 | 描述 |
| ------ | --------------------- | --------------------- |
| POST | `/models` | 创建模型 |
| GET | `/models` | 获取模型列表 |
| GET | `/models/:id` | 获取模型详情 |
| PUT | `/models/:id` | 更新模型 |
| DELETE | `/models/:id` | 删除模型 |
| 方法 | 路径 | 描述 |
| ------ | ----------------------- | --------------------- |
| POST | `/models` | 创建模型 |
| GET | `/models` | 获取模型列表 |
| GET | `/models/:id` | 获取模型详情 |
| PUT | `/models/:id` | 更新模型 |
| DELETE | `/models/:id` | 删除模型 |
| GET | `/models/providers` | 获取模型服务商列表 |
## 服务商支持 (Provider Support)
WeKnora 支持多种主流 AI 模型服务商,在创建模型时可通过 `provider` 字段指定服务商类型以获得更好的兼容性。
### 支持的服务商列表
| 服务商标识 | 名称 | 支持的模型类型 |
| -------------- | ------------------ | ------------------------------- |
| `generic` | 自定义API OpenAI 兼容 | Chat, Embedding, Rerank, VLLM |
| `aliyun` | 阿里云 DashScope | Chat, Embedding, Rerank, VLLM |
| `zhipu` | 智谱 AI | Chat, Embedding, Rerank, VLLM |
| `volcengine` | 火山引擎 | Chat, Embedding, VLLM |
| `hunyuan` | 腾讯混元 | Chat, Embedding, VLLM |
| `deepseek` | DeepSeek | Chat |
| `minimax` | MiniMax | Chat, Embedding, VLLM |
| `mimo` | 小米 Mimo | Chat |
| `siliconflow` | 硅基流动 | Chat, Embedding, Rerank |
| `jina` | Jina AI | Embedding, Rerank |
| `openrouter` | OpenRouter | Chat |
| `openai` | OpenAI | Chat, Embedding, VLLM |
| `gemini` | Google Gemini | Chat, Embedding, VLLM |
## GET `/models/providers` - 获取模型服务商列表
根据模型类型获取支持的服务商列表及配置信息。
**请求参数**:
| 参数 | 类型 | 必填 | 描述 |
| ---------- | ------ | ---- | ---------------------------------------------- |
| model_type | string | 否 | 模型类型:`chat`, `embedding`, `rerank`, `vllm` |
**请求**:
```curl
# 获取所有服务商
curl --location 'http://localhost:8080/api/v1/models/providers' \
--header 'X-API-Key: your_api_key'
# 获取支持 Embedding 类型的服务商
curl --location 'http://localhost:8080/api/v1/models/providers?model_type=embedding' \
--header 'X-API-Key: your_api_key'
```
**响应**:
```json
{
"success": true,
"data": [
{
"value": "aliyun",
"label": "阿里云 DashScope",
"description": "阿里云百炼大模型服务",
"defaultUrls": {
"chat": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"embedding": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"rerank": "https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank"
},
"modelTypes": ["chat", "embedding", "rerank", "vllm"]
},
{
"value": "zhipu",
"label": "智谱 AI",
"description": "智谱清言大模型",
"defaultUrls": {
"chat": "https://open.bigmodel.cn/api/paas/v4",
"embedding": "https://open.bigmodel.cn/api/paas/v4/embeddings"
},
"modelTypes": ["chat", "embedding", "vllm"]
}
]
}
```
## POST `/models` - 创建模型
### 创建对话模型(KnowledgeQA)
**本地 Ollama 模型**:
```curl
curl --location 'http://localhost:8080/api/v1/models' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: sk-vQHV2NZI_LK5W7wHQvH3yGYExX8YnhaHwZipUYbiZKCYJbBQ' \
--header 'X-API-Key: your_api_key' \
--data '{
"name": "qwen3:8b",
"type": "KnowledgeQA",
@@ -26,17 +104,37 @@ curl --location 'http://localhost:8080/api/v1/models' \
"parameters": {
"base_url": "",
"api_key": ""
},
"is_default": false
}
}'
```
**远程 API 模型(指定服务商)**:
```curl
curl --location 'http://localhost:8080/api/v1/models' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: your_api_key' \
--data '{
"name": "qwen-plus",
"type": "KnowledgeQA",
"source": "remote",
"description": "阿里云 Qwen 大模型",
"parameters": {
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"api_key": "sk-your-dashscope-api-key",
"provider": "aliyun"
}
}'
```
### 创建嵌入模型(Embedding)
**本地 Ollama 模型**:
```curl
curl --location 'http://localhost:8080/api/v1/models' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: sk-vQHV2NZI_LK5W7wHQvH3yGYExX8YnhaHwZipUYbiZKCYJbBQ' \
--header 'X-API-Key: your_api_key' \
--data '{
"name": "nomic-embed-text:latest",
"type": "Embedding",
@@ -49,27 +147,112 @@ curl --location 'http://localhost:8080/api/v1/models' \
"dimension": 768,
"truncate_prompt_tokens": 0
}
},
"is_default": false
}
}'
```
**远程 API 模型(阿里云 DashScope)**:
```curl
curl --location 'http://localhost:8080/api/v1/models' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: your_api_key' \
--data '{
"name": "text-embedding-v3",
"type": "Embedding",
"source": "remote",
"description": "阿里云通义千问 Embedding 模型",
"parameters": {
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"api_key": "sk-your-dashscope-api-key",
"provider": "aliyun",
"embedding_parameters": {
"dimension": 1024,
"truncate_prompt_tokens": 0
}
}
}'
```
**远程 API 模型(Jina AI)**:
```curl
curl --location 'http://localhost:8080/api/v1/models' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: your_api_key' \
--data '{
"name": "jina-embeddings-v3",
"type": "Embedding",
"source": "remote",
"description": "Jina AI Embedding 模型",
"parameters": {
"base_url": "https://api.jina.ai/v1",
"api_key": "jina_your_api_key",
"provider": "jina",
"embedding_parameters": {
"dimension": 1024,
"truncate_prompt_tokens": 0
}
}
}'
```
### 创建排序模型(Rerank)
**远程 API 模型(阿里云 DashScope)**:
```curl
curl --location 'http://localhost:8080/api/v1/models' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: sk-vQHV2NZI_LK5W7wHQvH3yGYExX8YnhaHwZipUYbiZKCYJbBQ' \
--header 'X-API-Key: your_api_key' \
--data '{
"name": "linux6200/bge-reranker-v2-m3:latest",
"name": "gte-rerank",
"type": "Rerank",
"source": "local",
"description": "Rerank Model for Knowledge QA",
"source": "remote",
"description": "阿里云 GTE Rerank 模型",
"parameters": {
"base_url": "",
"api_key": ""
},
"is_default": false
"base_url": "https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank",
"api_key": "sk-your-dashscope-api-key",
"provider": "aliyun"
}
}'
```
**远程 API 模型(Jina AI)**:
```curl
curl --location 'http://localhost:8080/api/v1/models' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: your_api_key' \
--data '{
"name": "jina-reranker-v2-base-multilingual",
"type": "Rerank",
"source": "remote",
"description": "Jina AI Rerank 模型",
"parameters": {
"base_url": "https://api.jina.ai/v1",
"api_key": "jina_your_api_key",
"provider": "jina"
}
}'
```
### 创建视觉模型(VLLM)
```curl
curl --location 'http://localhost:8080/api/v1/models' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: your_api_key' \
--data '{
"name": "qwen-vl-plus",
"type": "VLLM",
"source": "remote",
"description": "阿里云通义千问视觉模型",
"parameters": {
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"api_key": "sk-your-dashscope-api-key",
"provider": "aliyun"
}
}'
```
@@ -77,28 +260,29 @@ curl --location 'http://localhost:8080/api/v1/models' \
```json
{
"success": true,
"data": {
"id": "09c5a1d6-ee8b-4657-9a17-d3dcbd5c70cb",
"tenant_id": 1,
"name": "nomic-embed-text:latest3",
"name": "text-embedding-v3",
"type": "Embedding",
"source": "local",
"description": "Embedding Model",
"source": "remote",
"description": "阿里云通义千问 Embedding 模型",
"parameters": {
"base_url": "",
"api_key": "",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"api_key": "sk-***",
"provider": "aliyun",
"embedding_parameters": {
"dimension": 768,
"dimension": 1024,
"truncate_prompt_tokens": 0
}
},
"is_default": false,
"status": "downloading",
"status": "active",
"created_at": "2025-08-12T10:39:01.454591766+08:00",
"updated_at": "2025-08-12T10:39:01.454591766+08:00",
"deleted_at": null
},
"success": true
}
}
```
@@ -109,26 +293,28 @@ curl --location 'http://localhost:8080/api/v1/models' \
```curl
curl --location 'http://localhost:8080/api/v1/models' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: sk-vQHV2NZI_LK5W7wHQvH3yGYExX8YnhaHwZipUYbiZKCYJbBQ'
--header 'X-API-Key: your_api_key'
```
**响应**:
```json
{
"success": true,
"data": [
{
"id": "dff7bc94-7885-4dd1-bfd5-bd96e4df2fc3",
"tenant_id": 1,
"name": "nomic-embed-text:latest",
"name": "text-embedding-v3",
"type": "Embedding",
"source": "local",
"description": "Embedding Model",
"source": "remote",
"description": "阿里云通义千问 Embedding 模型",
"parameters": {
"base_url": "",
"api_key": "",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"api_key": "sk-***",
"provider": "aliyun",
"embedding_parameters": {
"dimension": 768,
"dimension": 1024,
"truncate_prompt_tokens": 0
}
},
@@ -141,13 +327,14 @@ curl --location 'http://localhost:8080/api/v1/models' \
{
"id": "8aea788c-bb30-4898-809e-e40c14ffb48c",
"tenant_id": 1,
"name": "qwen3:8b",
"name": "qwen-plus",
"type": "KnowledgeQA",
"source": "local",
"description": "LLM Model for Knowledge QA",
"source": "remote",
"description": "阿里云 Qwen 大模型",
"parameters": {
"base_url": "",
"api_key": "",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"api_key": "sk-***",
"provider": "aliyun",
"embedding_parameters": {
"dimension": 0,
"truncate_prompt_tokens": 0
@@ -159,8 +346,7 @@ curl --location 'http://localhost:8080/api/v1/models' \
"updated_at": "2025-08-11T20:10:41.825381+08:00",
"deleted_at": null
}
],
"success": true
]
}
```
@@ -171,25 +357,27 @@ curl --location 'http://localhost:8080/api/v1/models' \
```curl
curl --location 'http://localhost:8080/api/v1/models/dff7bc94-7885-4dd1-bfd5-bd96e4df2fc3' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: sk-vQHV2NZI_LK5W7wHQvH3yGYExX8YnhaHwZipUYbiZKCYJbBQ'
--header 'X-API-Key: your_api_key'
```
**响应**:
```json
{
"success": true,
"data": {
"id": "dff7bc94-7885-4dd1-bfd5-bd96e4df2fc3",
"tenant_id": 1,
"name": "nomic-embed-text:latest",
"name": "text-embedding-v3",
"type": "Embedding",
"source": "local",
"description": "Embedding Model",
"source": "remote",
"description": "阿里云通义千问 Embedding 模型",
"parameters": {
"base_url": "",
"api_key": "",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"api_key": "sk-***",
"provider": "aliyun",
"embedding_parameters": {
"dimension": 768,
"dimension": 1024,
"truncate_prompt_tokens": 0
}
},
@@ -198,8 +386,7 @@ curl --location 'http://localhost:8080/api/v1/models/dff7bc94-7885-4dd1-bfd5-bd9
"created_at": "2025-08-11T20:10:41.813832+08:00",
"updated_at": "2025-08-11T20:10:41.822354+08:00",
"deleted_at": null
},
"success": true
}
}
```
@@ -210,15 +397,15 @@ curl --location 'http://localhost:8080/api/v1/models/dff7bc94-7885-4dd1-bfd5-bd9
```curl
curl --location --request PUT 'http://localhost:8080/api/v1/models/8fdc464d-8eaa-44d4-a85b-094b28af5330' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: sk-vQHV2NZI_LK5W7wHQvH3yGYExX8YnhaHwZipUYbiZKCYJbBQ' \
--header 'X-API-Key: your_api_key' \
--data '{
"name": "linux6200/bge-reranker-v2-m3:latest",
"description": "Rerank Model for Knowledge QA new",
"name": "gte-rerank-v2",
"description": "阿里云 GTE Rerank 模型 V2",
"parameters": {
"base_url": "",
"api_key": ""
},
"is_default": false
"base_url": "https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank",
"api_key": "sk-your-new-api-key",
"provider": "aliyun"
}
}'
```
@@ -226,16 +413,18 @@ curl --location --request PUT 'http://localhost:8080/api/v1/models/8fdc464d-8eaa
```json
{
"success": true,
"data": {
"id": "8fdc464d-8eaa-44d4-a85b-094b28af5330",
"tenant_id": 1,
"name": "linux6200/bge-reranker-v2-m3:latest",
"name": "gte-rerank-v2",
"type": "Rerank",
"source": "local",
"description": "Rerank Model for Knowledge QA new",
"source": "remote",
"description": "阿里云 GTE Rerank 模型 V2",
"parameters": {
"base_url": "",
"api_key": "",
"base_url": "https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank",
"api_key": "sk-***",
"provider": "aliyun",
"embedding_parameters": {
"dimension": 0,
"truncate_prompt_tokens": 0
@@ -246,8 +435,7 @@ curl --location --request PUT 'http://localhost:8080/api/v1/models/8fdc464d-8eaa
"created_at": "2025-08-12T10:57:39.512681+08:00",
"updated_at": "2025-08-12T11:00:27.271678+08:00",
"deleted_at": null
},
"success": true
}
}
```
@@ -258,14 +446,49 @@ curl --location --request PUT 'http://localhost:8080/api/v1/models/8fdc464d-8eaa
```curl
curl --location --request DELETE 'http://localhost:8080/api/v1/models/8fdc464d-8eaa-44d4-a85b-094b28af5330' \
--header 'Content-Type: application/json' \
--header 'X-API-Key: sk-vQHV2NZI_LK5W7wHQvH3yGYExX8YnhaHwZipUYbiZKCYJbBQ'
--header 'X-API-Key: your_api_key'
```
**响应**:
```json
{
"message": "Model deleted",
"success": true
"success": true,
"message": "Model deleted"
}
```
## 参数说明
### ModelType (模型类型)
| 值 | 说明 | 用途 |
| ------------ | ------------ | ------------------------------ |
| KnowledgeQA | 对话模型 | 知识库问答、对话生成 |
| Embedding | 嵌入模型 | 文本向量化、知识库检索 |
| Rerank | 排序模型 | 检索结果重排序、相关性优化 |
| VLLM | 视觉语言模型 | 多模态分析、图文理解 |
### ModelSource (模型来源)
| 值 | 说明 | 配置要求 |
| -------- | ---------- | ------------------------------ |
| local | 本地模型 | 需要已安装 Ollama 并拉取模型 |
| remote | 远程 API | 需要提供 `base_url` 和 `api_key` |
### Parameters (模型参数)
| 字段 | 类型 | 说明 |
| -------------------- | ------ | -------------------------------------------- |
| base_url | string | API 服务地址(远程模型必填) |
| api_key | string | API 密钥(远程模型必填) |
| provider | string | 服务商标识(可选,用于选择特定的 API 适配器)|
| embedding_parameters | object | Embedding 模型专用参数 |
| extra_config | object | 服务商特定的额外配置 |
### EmbeddingParameters (嵌入参数)
| 字段 | 类型 | 说明 |
| ---------------------- | ---- | -------------------------- |
| dimension | int | 向量维度(如:768, 1024) |
| truncate_prompt_tokens | int | 截断 Token 数(0 表示不截断)|