mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-09 04:40:57 +00:00
feat(cloud): provision workspace model catalog (#2376)
* feat(cloud): provision workspace model catalog * ci(cloud): pin model catalog adapter source * fix: make cloud model catalog sync recoverable * ci: pin cloud adapter source for release --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>
This commit is contained in:
@@ -5,6 +5,7 @@ import uuid
|
||||
import sqlalchemy
|
||||
from langbot_plugin.api.entities.builtin.provider import message as provider_message
|
||||
|
||||
from ....cloud.model_catalog import LANGBOT_MODELS_PROVIDER_REQUESTER
|
||||
from ....core import app
|
||||
from ....entity.persistence import model as persistence_model
|
||||
from ....entity.persistence import pipeline as persistence_pipeline
|
||||
@@ -113,6 +114,23 @@ async def _require_workspace_provider(
|
||||
return provider
|
||||
|
||||
|
||||
def _is_cloud_runtime(ap: app.Application) -> bool:
|
||||
mode = getattr(ap.persistence_mgr, 'mode', None)
|
||||
return getattr(mode, 'value', None) == 'cloud_runtime'
|
||||
|
||||
|
||||
async def _assert_cloud_managed_provider_mutable(
|
||||
ap: app.Application,
|
||||
context: TenantContext,
|
||||
provider_uuid: str,
|
||||
) -> None:
|
||||
if not _is_cloud_runtime(ap):
|
||||
return
|
||||
provider = await _require_workspace_provider(ap, context, provider_uuid)
|
||||
if provider.get('requester') == LANGBOT_MODELS_PROVIDER_REQUESTER:
|
||||
raise ValueError('LangBot Models is managed by Cloud and cannot be modified')
|
||||
|
||||
|
||||
async def _require_runtime_provider(
|
||||
ap: app.Application,
|
||||
context: TenantContext,
|
||||
@@ -213,6 +231,7 @@ class LLMModelsService:
|
||||
model_data['provider_uuid'] = provider_uuid
|
||||
|
||||
await _require_workspace_provider(self.ap, context, model_data['provider_uuid'])
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, model_data['provider_uuid'])
|
||||
await _validate_provider_supports(self.ap, context, model_data['provider_uuid'], 'llm')
|
||||
|
||||
await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_model.LLMModel).values(**model_data))
|
||||
@@ -291,11 +310,17 @@ class LLMModelsService:
|
||||
|
||||
return model_dict
|
||||
|
||||
async def update_llm_model(self, context: TenantContext, model_uuid: str, model_data: dict) -> None:
|
||||
async def update_llm_model(
|
||||
self,
|
||||
context: TenantContext,
|
||||
model_uuid: str,
|
||||
model_data: dict,
|
||||
) -> None:
|
||||
"""Update an existing LLM model"""
|
||||
existing_model = await self.get_llm_model(context, model_uuid, include_secret=True)
|
||||
if existing_model is None:
|
||||
raise WorkspaceNotFoundError('Model not found')
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, existing_model['provider_uuid'])
|
||||
model_data = model_data.copy()
|
||||
model_data.pop('uuid', None)
|
||||
model_data.pop('workspace_uuid', None)
|
||||
@@ -321,6 +346,7 @@ class LLMModelsService:
|
||||
|
||||
provider_uuid = model_data.get('provider_uuid', existing_model['provider_uuid'])
|
||||
await _require_workspace_provider(self.ap, context, provider_uuid)
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, provider_uuid)
|
||||
await _validate_provider_supports(self.ap, context, provider_uuid, 'llm')
|
||||
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
@@ -355,6 +381,11 @@ class LLMModelsService:
|
||||
|
||||
async def delete_llm_model(self, context: TenantContext, model_uuid: str) -> None:
|
||||
"""Delete an LLM model"""
|
||||
if _is_cloud_runtime(self.ap):
|
||||
existing_model = await self.get_llm_model(context, model_uuid, include_secret=True)
|
||||
if existing_model is None:
|
||||
raise WorkspaceNotFoundError('Model not found')
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, existing_model['provider_uuid'])
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.delete(persistence_model.LLMModel).where(persistence_model.LLMModel.uuid == model_uuid),
|
||||
@@ -448,7 +479,10 @@ class EmbeddingModelsService:
|
||||
return serialized if include_secret else [_redact_model_secrets(model) for model in serialized]
|
||||
|
||||
async def create_embedding_model(
|
||||
self, context: TenantContext, model_data: dict, preserve_uuid: bool = False
|
||||
self,
|
||||
context: TenantContext,
|
||||
model_data: dict,
|
||||
preserve_uuid: bool = False,
|
||||
) -> str:
|
||||
"""Create a new embedding model"""
|
||||
model_data = model_data.copy()
|
||||
@@ -472,6 +506,7 @@ class EmbeddingModelsService:
|
||||
model_data['provider_uuid'] = provider_uuid
|
||||
|
||||
await _require_workspace_provider(self.ap, context, model_data['provider_uuid'])
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, model_data['provider_uuid'])
|
||||
await _validate_provider_supports(self.ap, context, model_data['provider_uuid'], 'text-embedding')
|
||||
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
@@ -530,11 +565,17 @@ class EmbeddingModelsService:
|
||||
|
||||
return model_dict
|
||||
|
||||
async def update_embedding_model(self, context: TenantContext, model_uuid: str, model_data: dict) -> None:
|
||||
async def update_embedding_model(
|
||||
self,
|
||||
context: TenantContext,
|
||||
model_uuid: str,
|
||||
model_data: dict,
|
||||
) -> None:
|
||||
"""Update an existing embedding model"""
|
||||
existing_model = await self.get_embedding_model(context, model_uuid, include_secret=True)
|
||||
if existing_model is None:
|
||||
raise WorkspaceNotFoundError('Model not found')
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, existing_model['provider_uuid'])
|
||||
model_data = model_data.copy()
|
||||
model_data.pop('uuid', None)
|
||||
model_data.pop('workspace_uuid', None)
|
||||
@@ -559,6 +600,7 @@ class EmbeddingModelsService:
|
||||
|
||||
provider_uuid = model_data.get('provider_uuid', existing_model['provider_uuid'])
|
||||
await _require_workspace_provider(self.ap, context, provider_uuid)
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, provider_uuid)
|
||||
await _validate_provider_supports(self.ap, context, provider_uuid, 'text-embedding')
|
||||
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
@@ -593,6 +635,11 @@ class EmbeddingModelsService:
|
||||
|
||||
async def delete_embedding_model(self, context: TenantContext, model_uuid: str) -> None:
|
||||
"""Delete an embedding model"""
|
||||
if _is_cloud_runtime(self.ap):
|
||||
existing_model = await self.get_embedding_model(context, model_uuid, include_secret=True)
|
||||
if existing_model is None:
|
||||
raise WorkspaceNotFoundError('Model not found')
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, existing_model['provider_uuid'])
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.delete(persistence_model.EmbeddingModel).where(
|
||||
@@ -685,7 +732,12 @@ class RerankModelsService:
|
||||
serialized = [self.ap.persistence_mgr.serialize_model(persistence_model.RerankModel, m) for m in models]
|
||||
return serialized if include_secret else [_redact_model_secrets(model) for model in serialized]
|
||||
|
||||
async def create_rerank_model(self, context: TenantContext, model_data: dict, preserve_uuid: bool = False) -> str:
|
||||
async def create_rerank_model(
|
||||
self,
|
||||
context: TenantContext,
|
||||
model_data: dict,
|
||||
preserve_uuid: bool = False,
|
||||
) -> str:
|
||||
"""Create a new rerank model"""
|
||||
model_data = model_data.copy()
|
||||
if not preserve_uuid:
|
||||
@@ -708,6 +760,7 @@ class RerankModelsService:
|
||||
model_data['provider_uuid'] = provider_uuid
|
||||
|
||||
await _require_workspace_provider(self.ap, context, model_data['provider_uuid'])
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, model_data['provider_uuid'])
|
||||
await _validate_provider_supports(self.ap, context, model_data['provider_uuid'], 'rerank')
|
||||
|
||||
await self.ap.persistence_mgr.execute_async(
|
||||
@@ -766,11 +819,17 @@ class RerankModelsService:
|
||||
|
||||
return model_dict
|
||||
|
||||
async def update_rerank_model(self, context: TenantContext, model_uuid: str, model_data: dict) -> None:
|
||||
async def update_rerank_model(
|
||||
self,
|
||||
context: TenantContext,
|
||||
model_uuid: str,
|
||||
model_data: dict,
|
||||
) -> None:
|
||||
"""Update an existing rerank model"""
|
||||
existing_model = await self.get_rerank_model(context, model_uuid, include_secret=True)
|
||||
if existing_model is None:
|
||||
raise WorkspaceNotFoundError('Model not found')
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, existing_model['provider_uuid'])
|
||||
model_data = model_data.copy()
|
||||
model_data.pop('uuid', None)
|
||||
model_data.pop('workspace_uuid', None)
|
||||
@@ -795,6 +854,7 @@ class RerankModelsService:
|
||||
|
||||
provider_uuid = model_data.get('provider_uuid', existing_model['provider_uuid'])
|
||||
await _require_workspace_provider(self.ap, context, provider_uuid)
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, provider_uuid)
|
||||
await _validate_provider_supports(self.ap, context, provider_uuid, 'rerank')
|
||||
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
@@ -829,6 +889,11 @@ class RerankModelsService:
|
||||
|
||||
async def delete_rerank_model(self, context: TenantContext, model_uuid: str) -> None:
|
||||
"""Delete a rerank model"""
|
||||
if _is_cloud_runtime(self.ap):
|
||||
existing_model = await self.get_rerank_model(context, model_uuid, include_secret=True)
|
||||
if existing_model is None:
|
||||
raise WorkspaceNotFoundError('Model not found')
|
||||
await _assert_cloud_managed_provider_mutable(self.ap, context, existing_model['provider_uuid'])
|
||||
result = await self.ap.persistence_mgr.execute_async(
|
||||
scope_statement(
|
||||
sqlalchemy.delete(persistence_model.RerankModel).where(
|
||||
|
||||
@@ -5,6 +5,7 @@ import traceback
|
||||
|
||||
import sqlalchemy
|
||||
|
||||
from ....cloud.model_catalog import LANGBOT_MODELS_PROVIDER_REQUESTER
|
||||
from ....core import app
|
||||
from ....entity.persistence import model as persistence_model
|
||||
from ....workspace.errors import WorkspaceNotFoundError
|
||||
@@ -20,6 +21,20 @@ class ModelProviderService:
|
||||
def __init__(self, ap: app.Application) -> None:
|
||||
self.ap = ap
|
||||
|
||||
def _is_cloud_runtime(self) -> bool:
|
||||
mode = getattr(self.ap.persistence_mgr, 'mode', None)
|
||||
return getattr(mode, 'value', None) == 'cloud_runtime'
|
||||
|
||||
def _system_requester_is_reserved(self, requester: object) -> bool:
|
||||
return self._is_cloud_runtime() and requester == LANGBOT_MODELS_PROVIDER_REQUESTER
|
||||
|
||||
async def _assert_provider_mutable(self, context: TenantContext, provider_uuid: str) -> None:
|
||||
if not self._is_cloud_runtime():
|
||||
return
|
||||
provider = await self.get_provider(context, provider_uuid)
|
||||
if provider is not None and self._system_requester_is_reserved(provider.get('requester')):
|
||||
raise ValueError('LangBot Models is managed by Cloud and cannot be modified')
|
||||
|
||||
@staticmethod
|
||||
def _normalize_api_keys(api_keys: str | list[str] | tuple[str, ...] | None) -> list[str]:
|
||||
if api_keys is None:
|
||||
@@ -99,6 +114,8 @@ class ModelProviderService:
|
||||
async def create_provider(self, context: TenantContext, provider_data: dict) -> str:
|
||||
"""Create a new provider"""
|
||||
provider_data = provider_data.copy()
|
||||
if self._system_requester_is_reserved(provider_data.get('requester')):
|
||||
raise ValueError('space-chat-completions is reserved for the Cloud-managed LangBot Models provider')
|
||||
provider_data['uuid'] = str(uuid.uuid4())
|
||||
provider_data['workspace_uuid'] = require_workspace_uuid(context)
|
||||
provider_data['api_keys'] = self._normalize_api_keys(
|
||||
@@ -115,7 +132,10 @@ class ModelProviderService:
|
||||
|
||||
async def update_provider(self, context: TenantContext, provider_uuid: str, provider_data: dict) -> None:
|
||||
"""Update an existing provider"""
|
||||
await self._assert_provider_mutable(context, provider_uuid)
|
||||
provider_data = provider_data.copy()
|
||||
if self._system_requester_is_reserved(provider_data.get('requester')):
|
||||
raise ValueError('space-chat-completions is reserved for the Cloud-managed LangBot Models provider')
|
||||
provider_data.pop('uuid', None)
|
||||
provider_data.pop('workspace_uuid', None)
|
||||
if 'api_keys' in provider_data:
|
||||
@@ -145,6 +165,7 @@ class ModelProviderService:
|
||||
|
||||
async def delete_provider(self, context: TenantContext, provider_uuid: str) -> None:
|
||||
"""Delete a provider (only if no models reference it)"""
|
||||
await self._assert_provider_mutable(context, provider_uuid)
|
||||
workspace_uuid = require_workspace_uuid(context)
|
||||
# Check if any models use this provider
|
||||
llm_result = await self.ap.persistence_mgr.execute_async(
|
||||
@@ -245,6 +266,8 @@ class ModelProviderService:
|
||||
api_keys: list,
|
||||
) -> str:
|
||||
"""Find existing provider or create new one"""
|
||||
if self._system_requester_is_reserved(requester):
|
||||
raise ValueError('space-chat-completions is reserved for the Cloud-managed LangBot Models provider')
|
||||
workspace_uuid = require_workspace_uuid(context)
|
||||
api_keys = self._normalize_api_keys(restore_secret_placeholders(api_keys, sensitive=True))
|
||||
|
||||
|
||||
Reference in New Issue
Block a user