Feat/rerank model (#2137)

* feat(provider): add rerank model management as a core model type * feat(provider): add rerank support to existing requesters and new rerank providers * feat(web): add rerank model management UI and pipeline config * fix(provider): correct rerank support_type after verification - Add rerank to OpenRouter (confirmed /api/v1/rerank endpoint) - Remove rerank from Ollama (no native support, PR #7219 unmerged) - Remove rerank from JiekouAI (no rerank docs found, URL path mismatch) * fix(provider): remove alru_cache from model getters and add rerank param hints * fix: resolve lint errors - Remove unused alru_cache import from modelmgr.py - Remove unused error_message variable in invoke_rerank - Fix prettier formatting in frontend files Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix: remove unused exception variable - Change `except Exception as e:` to `except Exception:` since e is not used - Fix prettier formatting in ProviderCard.tsx Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix: apply ruff format Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat(template): add rerank config fields to default pipeline config Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * chore: remove PR.md Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix(ui): remove duplicate rerank model form in AddModelPopover The form was being rendered twice: once in TabsContent manual mode and again in a separate conditional block for rerank tab. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-07-17 09:56:06 +00:00 · 2026-04-20 23:32:36 +08:00
parent 5a5c4295b1
commit 323481d69b
41 changed files with 950 additions and 41 deletions
@@ -247,6 +247,40 @@ class RuntimeProvider:
            except Exception as monitor_err:
                self.requester.ap.logger.error(f'[Monitoring] Failed to record embedding call: {monitor_err}')

+    async def invoke_rerank(
+        self,
+        model: RuntimeRerankModel,
+        query: str,
+        documents: typing.List[str],
+        extra_args: dict[str, typing.Any] = {},
+    ) -> typing.List[dict]:
+        """Bridge method for invoking rerank with monitoring"""
+        start_time = time.time()
+        status = 'success'
+
+        try:
+            result = await self.requester.invoke_rerank(
+                model=model,
+                query=query,
+                documents=documents,
+                extra_args=extra_args,
+            )
+            return result
+
+        except Exception:
+            status = 'error'
+            raise
+        finally:
+            duration_ms = int((time.time() - start_time) * 1000)
+
+            try:
+                self.requester.ap.logger.debug(
+                    f'[Rerank] model={model.model_entity.name} docs={len(documents)} '
+                    f'duration={duration_ms}ms status={status}'
+                )
+            except Exception as monitor_err:
+                self.requester.ap.logger.error(f'[Monitoring] Failed to record rerank call: {monitor_err}')
+

 class RuntimeLLMModel:
    """运行时模型"""
@@ -284,6 +318,24 @@ class RuntimeEmbeddingModel:
        self.provider = provider


+class RuntimeRerankModel:
+    """运行时 Rerank 模型"""
+
+    model_entity: persistence_model.RerankModel
+    """模型数据"""
+
+    provider: RuntimeProvider
+    """提供商实例"""
+
+    def __init__(
+        self,
+        model_entity: persistence_model.RerankModel,
+        provider: RuntimeProvider,
+    ):
+        self.model_entity = model_entity
+        self.provider = provider
+
+
 class ProviderAPIRequester(metaclass=abc.ABCMeta):
    """Provider API请求器"""

@@ -376,3 +428,23 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
            或者 tuple[typing.List[typing.List[float]], dict]: 返回 (embedding 向量, usage_info)
        """
        pass
+
+    async def invoke_rerank(
+        self,
+        model: RuntimeRerankModel,
+        query: str,
+        documents: typing.List[str],
+        extra_args: dict[str, typing.Any] = {},
+    ) -> typing.List[dict]:
+        """调用 Rerank API
+
+        Args:
+            model (RuntimeRerankModel): 使用的模型信息
+            query (str): 查询文本
+            documents (typing.List[str]): 待重排序的文档列表
+            extra_args (dict[str, typing.Any], optional): 额外的参数. Defaults to {}.
+
+        Returns:
+            typing.List[dict]: [{"index": int, "relevance_score": float}, ...]
+        """
+        raise NotImplementedError('This requester does not support rerank')