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>
This commit is contained in:
huanghuoguoguo
2026-04-20 23:32:36 +08:00
committed by GitHub
parent 5a5c4295b1
commit 323481d69b
41 changed files with 950 additions and 41 deletions

View File

@@ -97,3 +97,51 @@ class EmbeddingModelsRouterGroup(group.RouterGroup):
await self.ap.embedding_models_service.test_embedding_model(model_uuid, json_data)
return self.success()
@group.group_class('models/rerank', '/api/v1/provider/models/rerank')
class RerankModelsRouterGroup(group.RouterGroup):
async def initialize(self) -> None:
@self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
async def _() -> str:
if quart.request.method == 'GET':
provider_uuid = quart.request.args.get('provider_uuid')
if provider_uuid:
return self.success(
data={
'models': await self.ap.rerank_models_service.get_rerank_models_by_provider(provider_uuid)
}
)
return self.success(data={'models': await self.ap.rerank_models_service.get_rerank_models()})
elif quart.request.method == 'POST':
json_data = await quart.request.json
model_uuid = await self.ap.rerank_models_service.create_rerank_model(json_data)
return self.success(data={'uuid': model_uuid})
@self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
async def _(model_uuid: str) -> str:
if quart.request.method == 'GET':
model = await self.ap.rerank_models_service.get_rerank_model(model_uuid)
if model is None:
return self.http_status(404, -1, 'model not found')
return self.success(data={'model': model})
elif quart.request.method == 'PUT':
json_data = await quart.request.json
await self.ap.rerank_models_service.update_rerank_model(model_uuid, json_data)
return self.success()
elif quart.request.method == 'DELETE':
await self.ap.rerank_models_service.delete_rerank_model(model_uuid)
return self.success()
@self.route('/<model_uuid>/test', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
async def _(model_uuid: str) -> str:
json_data = await quart.request.json
await self.ap.rerank_models_service.test_rerank_model(model_uuid, json_data)
return self.success()

View File

@@ -15,6 +15,7 @@ class ModelProvidersRouterGroup(group.RouterGroup):
counts = await self.ap.provider_service.get_provider_model_counts(provider['uuid'])
provider['llm_count'] = counts['llm_count']
provider['embedding_count'] = counts['embedding_count']
provider['rerank_count'] = counts['rerank_count']
return self.success(data={'providers': providers})
elif quart.request.method == 'POST':
json_data = await quart.request.json
@@ -32,6 +33,7 @@ class ModelProvidersRouterGroup(group.RouterGroup):
counts = await self.ap.provider_service.get_provider_model_counts(provider_uuid)
provider['llm_count'] = counts['llm_count']
provider['embedding_count'] = counts['embedding_count']
provider['rerank_count'] = counts['rerank_count']
return self.success(data={'provider': provider})
elif quart.request.method == 'PUT':
json_data = await quart.request.json

View File

@@ -367,3 +367,162 @@ class EmbeddingModelsService:
input_text=['Hello, world!'],
extra_args={},
)
class RerankModelsService:
ap: app.Application
def __init__(self, ap: app.Application) -> None:
self.ap = ap
async def get_rerank_models(self) -> list[dict]:
"""Get all rerank models with provider info"""
result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.RerankModel))
models = result.all()
providers_result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_model.ModelProvider)
)
providers = {p.uuid: p for p in providers_result.all()}
models_list = []
for model in models:
model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.RerankModel, model)
provider = providers.get(model.provider_uuid)
if provider:
provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
model_dict['provider'] = _parse_provider_api_keys(provider_dict)
models_list.append(model_dict)
return models_list
async def get_rerank_models_by_provider(self, provider_uuid: str) -> list[dict]:
"""Get rerank models by provider UUID"""
result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_model.RerankModel).where(
persistence_model.RerankModel.provider_uuid == provider_uuid
)
)
models = result.all()
return [self.ap.persistence_mgr.serialize_model(persistence_model.RerankModel, m) for m in models]
async def create_rerank_model(self, model_data: dict, preserve_uuid: bool = False) -> str:
"""Create a new rerank model"""
if not preserve_uuid:
model_data['uuid'] = str(uuid.uuid4())
if 'provider' in model_data:
provider_data = model_data.pop('provider')
if provider_data.get('uuid'):
model_data['provider_uuid'] = provider_data['uuid']
else:
provider_uuid = await self.ap.provider_service.find_or_create_provider(
requester=provider_data.get('requester', ''),
base_url=provider_data.get('base_url', ''),
api_keys=provider_data.get('api_keys', []),
)
model_data['provider_uuid'] = provider_uuid
await self.ap.persistence_mgr.execute_async(
sqlalchemy.insert(persistence_model.RerankModel).values(**model_data)
)
runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
if runtime_provider is None:
raise Exception('provider not found')
runtime_rerank_model = await self.ap.model_mgr.load_rerank_model_with_provider(
persistence_model.RerankModel(**model_data),
runtime_provider,
)
self.ap.model_mgr.rerank_models.append(runtime_rerank_model)
return model_data['uuid']
async def get_rerank_model(self, model_uuid: str) -> dict | None:
"""Get a single rerank model with provider info"""
result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_model.RerankModel).where(persistence_model.RerankModel.uuid == model_uuid)
)
model = result.first()
if model is None:
return None
model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.RerankModel, model)
provider_result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_model.ModelProvider).where(
persistence_model.ModelProvider.uuid == model.provider_uuid
)
)
provider = provider_result.first()
if provider:
provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
model_dict['provider'] = _parse_provider_api_keys(provider_dict)
return model_dict
async def update_rerank_model(self, model_uuid: str, model_data: dict) -> None:
"""Update an existing rerank model"""
if 'uuid' in model_data:
del model_data['uuid']
if 'provider' in model_data:
provider_data = model_data.pop('provider')
if provider_data.get('uuid'):
model_data['provider_uuid'] = provider_data['uuid']
else:
provider_uuid = await self.ap.provider_service.find_or_create_provider(
requester=provider_data.get('requester', ''),
base_url=provider_data.get('base_url', ''),
api_keys=provider_data.get('api_keys', []),
)
model_data['provider_uuid'] = provider_uuid
await self.ap.persistence_mgr.execute_async(
sqlalchemy.update(persistence_model.RerankModel)
.where(persistence_model.RerankModel.uuid == model_uuid)
.values(**model_data)
)
await self.ap.model_mgr.remove_rerank_model(model_uuid)
runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
if runtime_provider is None:
raise Exception('provider not found')
runtime_rerank_model = await self.ap.model_mgr.load_rerank_model_with_provider(
persistence_model.RerankModel(**model_data),
runtime_provider,
)
self.ap.model_mgr.rerank_models.append(runtime_rerank_model)
async def delete_rerank_model(self, model_uuid: str) -> None:
"""Delete a rerank model"""
await self.ap.persistence_mgr.execute_async(
sqlalchemy.delete(persistence_model.RerankModel).where(persistence_model.RerankModel.uuid == model_uuid)
)
await self.ap.model_mgr.remove_rerank_model(model_uuid)
async def test_rerank_model(self, model_uuid: str, model_data: dict) -> None:
"""Test a rerank model"""
runtime_rerank_model: model_requester.RuntimeRerankModel | None = None
if model_uuid != '_':
for model in self.ap.model_mgr.rerank_models:
if model.model_entity.uuid == model_uuid:
runtime_rerank_model = model
break
if runtime_rerank_model is None:
raise Exception('model not found')
else:
runtime_rerank_model = await self.ap.model_mgr.init_temporary_runtime_rerank_model(model_data)
await runtime_rerank_model.provider.invoke_rerank(
model=runtime_rerank_model,
query='What is artificial intelligence?',
documents=[
'Artificial intelligence is a branch of computer science.',
'The weather is nice today.',
],
)

View File

@@ -98,6 +98,14 @@ class ModelProviderService:
if embedding_result.first() is not None:
raise ValueError('Cannot delete provider: Embedding models still reference it')
rerank_result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_model.RerankModel).where(
persistence_model.RerankModel.provider_uuid == provider_uuid
)
)
if rerank_result.first() is not None:
raise ValueError('Cannot delete provider: Rerank models still reference it')
await self.ap.persistence_mgr.execute_async(
sqlalchemy.delete(persistence_model.ModelProvider).where(
persistence_model.ModelProvider.uuid == provider_uuid
@@ -122,7 +130,14 @@ class ModelProviderService:
)
embedding_count = embedding_result.scalar() or 0
return {'llm_count': llm_count, 'embedding_count': embedding_count}
rerank_result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(sqlalchemy.func.count())
.select_from(persistence_model.RerankModel)
.where(persistence_model.RerankModel.provider_uuid == provider_uuid)
)
rerank_count = rerank_result.scalar() or 0
return {'llm_count': llm_count, 'embedding_count': embedding_count, 'rerank_count': rerank_count}
async def find_or_create_provider(self, requester: str, base_url: str, api_keys: list) -> str:
"""Find existing provider or create new one"""