feat: add embeddings model management (#1461)

* feat: add embeddings model management backend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add embeddings model management frontend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* chore: revert HttpClient URL to production setting

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* refactor: integrate embeddings models into models page with tabs

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* perf: move files

* perf: remove `s`

* feat: allow requester to declare supported types in manifest

* feat(embedding): delete dimension and encoding format

* feat: add extra_args for embedding moels

* perf: i18n ref

* fix: linter err

* fix: lint err

* fix: linter err

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin> <rockchinq@gmail.com>

pkg/provider/modelmgr/requesters/anthropicmsgs.py

@@ -15,7 +15,7 @@ from ...tools import entities as tools_entities
 from ....utils import image
 
 
-class AnthropicMessages(requester.LLMAPIRequester):
+class AnthropicMessages(requester.ProviderAPIRequester):
     """Anthropic Messages API 请求器"""
 
     client: anthropic.AsyncAnthropic

pkg/provider/modelmgr/requesters/anthropicmsgs.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./anthropicmsgs.py

pkg/provider/modelmgr/requesters/bailianchatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./bailianchatcmpl.py

pkg/provider/modelmgr/requesters/chatcmpl.py

@@ -13,7 +13,7 @@ from ... import entities as llm_entities
 from ...tools import entities as tools_entities
 
 
-class OpenAIChatCompletions(requester.LLMAPIRequester):
+class OpenAIChatCompletions(requester.ProviderAPIRequester):
     """OpenAI ChatCompletion API 请求器"""
 
     client: openai.AsyncClient
@@ -141,3 +141,39 @@ class OpenAIChatCompletions(requester.LLMAPIRequester):
             raise errors.RequesterError(f'请求过于频繁或余额不足: {e.message}')
         except openai.APIError as e:
             raise errors.RequesterError(f'请求错误: {e.message}')
+
+    async def invoke_embedding(
+        self,
+        query: core_entities.Query,
+        model: requester.RuntimeEmbeddingModel,
+        input_text: str,
+        extra_args: dict[str, typing.Any] = {},
+    ) -> list[float]:
+        """调用 Embedding API"""
+        self.client.api_key = model.token_mgr.get_token()
+
+        args = {
+            'model': model.model_entity.name,
+            'input': input_text,
+        }
+
+        if model.model_entity.extra_args:
+            args.update(model.model_entity.extra_args)
+
+        args.update(extra_args)
+
+        try:
+            resp = await self.client.embeddings.create(**args)
+            return resp.data[0].embedding
+        except asyncio.TimeoutError:
+            raise errors.RequesterError('请求超时')
+        except openai.BadRequestError as e:
+            raise errors.RequesterError(f'请求参数错误: {e.message}')
+        except openai.AuthenticationError as e:
+            raise errors.RequesterError(f'无效的 api-key: {e.message}')
+        except openai.NotFoundError as e:
+            raise errors.RequesterError(f'请求路径错误: {e.message}')
+        except openai.RateLimitError as e:
+            raise errors.RequesterError(f'请求过于频繁或余额不足: {e.message}')
+        except openai.APIError as e:
+            raise errors.RequesterError(f'请求错误: {e.message}')

pkg/provider/modelmgr/requesters/chatcmpl.yaml

@@ -22,6 +22,9 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
+    - text-embedding
 execution:
   python:
     path: ./chatcmpl.py

pkg/provider/modelmgr/requesters/deepseekchatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./deepseekchatcmpl.py

pkg/provider/modelmgr/requesters/geminichatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./geminichatcmpl.py

pkg/provider/modelmgr/requesters/giteeaichatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./giteeaichatcmpl.py

pkg/provider/modelmgr/requesters/lmstudiochatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./lmstudiochatcmpl.py

pkg/provider/modelmgr/requesters/modelscopechatcmpl.py

@@ -14,7 +14,7 @@ from ... import entities as llm_entities
 from ...tools import entities as tools_entities
 
 
-class ModelScopeChatCompletions(requester.LLMAPIRequester):
+class ModelScopeChatCompletions(requester.ProviderAPIRequester):
     """ModelScope ChatCompletion API 请求器"""
 
     client: openai.AsyncClient

pkg/provider/modelmgr/requesters/modelscopechatcmpl.yaml

@@ -29,6 +29,8 @@ spec:
       type: int
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./modelscopechatcmpl.py

pkg/provider/modelmgr/requesters/moonshotchatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./moonshotchatcmpl.py

pkg/provider/modelmgr/requesters/ollamachat.py

@@ -17,7 +17,7 @@ from ....core import entities as core_entities
 REQUESTER_NAME: str = 'ollama-chat'
 
 
-class OllamaChatCompletions(requester.LLMAPIRequester):
+class OllamaChatCompletions(requester.ProviderAPIRequester):
     """Ollama平台 ChatCompletion API请求器"""
 
     client: ollama.AsyncClient

pkg/provider/modelmgr/requesters/ollamachat.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./ollamachat.py

pkg/provider/modelmgr/requesters/openrouterchatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./openrouterchatcmpl.py

pkg/provider/modelmgr/requesters/ppiochatcmpl.yaml

@@ -29,6 +29,8 @@ spec:
       type: int
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./ppiochatcmpl.py

pkg/provider/modelmgr/requesters/siliconflowchatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./siliconflowchatcmpl.py

pkg/provider/modelmgr/requesters/volcarkchatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./volcarkchatcmpl.py

pkg/provider/modelmgr/requesters/xaichatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./xaichatcmpl.py

pkg/provider/modelmgr/requesters/zhipuaichatcmpl.yaml

@@ -22,6 +22,8 @@ spec:
       type: integer
       required: true
       default: 120
+  support_type:
+    - llm
 execution:
   python:
     path: ./zhipuaichatcmpl.py