opensource
/
dify
mirror of https://github.com/langgenius/dify.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/feat/plugins' into dev/plugin-deploy

This commit is contained in:
Yeuoly 2024-11-21 14:35:14 +08:00
parent e05d7637ac 84a3fe85c8
commit 7c74aaabcf
No known key found for this signature in database
GPG Key ID: A66E7E320FB19F61
290 changed files with 3601 additions and 3350 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
api/.env.example
View File

@ -42,6 +42,11 @@ REDIS_SENTINEL_USERNAME=
REDIS_SENTINEL_PASSWORD=
REDIS_SENTINEL_SOCKET_TIMEOUT=0.1
# redis Cluster configuration.
REDIS_USE_CLUSTERS=false
REDIS_CLUSTERS=
REDIS_CLUSTERS_PASSWORD=
# PostgreSQL database configuration
DB_USERNAME=postgres
DB_PASSWORD=difyai123456
@ -234,6 +239,10 @@ ANALYTICDB_ACCOUNT=testaccount
ANALYTICDB_PASSWORD=testpassword
ANALYTICDB_NAMESPACE=dify
ANALYTICDB_NAMESPACE_PASSWORD=difypassword
ANALYTICDB_HOST=gp-test.aliyuncs.com
ANALYTICDB_PORT=5432
ANALYTICDB_MIN_CONNECTION=1
ANALYTICDB_MAX_CONNECTION=5
# OpenSearch configuration
OPENSEARCH_HOST=127.0.0.1

4
api/commands.py
View File

@ -590,7 +590,7 @@ def upgrade_db():
click.echo(click.style("Database migration successful!", fg="green"))
except Exception as e:
logging.exception(f"Database migration failed: {e}")
logging.exception("Failed to execute database migration")
finally:
lock.release()
else:
@ -634,7 +634,7 @@ where sites.id is null limit 1000"""
except Exception as e:
failed_app_ids.append(app_id)
click.echo(click.style("Failed to fix missing site for app {}".format(app_id), fg="red"))
logging.exception(f"Fix app related site missing issue failed, error: {e}")
logging.exception(f"Failed to fix app related site missing issue, app_id: {app_id}")
continue
if not processed_count:

5
api/configs/feature/__init__.py
View File

@ -674,6 +674,11 @@ class DataSetConfig(BaseSettings):
default=False,
)
PLAN_SANDBOX_CLEAN_MESSAGE_DAY_SETTING: PositiveInt = Field(
description="Interval in days for message cleanup operations - plan: sandbox",
default=30,
)
class WorkspaceConfig(BaseSettings):
"""

15
api/configs/middleware/cache/redis_config.py vendored
View File

@ -68,3 +68,18 @@ class RedisConfig(BaseSettings):
description="Socket timeout in seconds for Redis Sentinel connections",
default=0.1,
)
REDIS_USE_CLUSTERS: bool = Field(
description="Enable Redis Clusters mode for high availability",
default=False,
)
REDIS_CLUSTERS: Optional[str] = Field(
description="Comma-separated list of Redis Clusters nodes (host:port)",
default=None,
)
REDIS_CLUSTERS_PASSWORD: Optional[str] = Field(
description="Password for Redis Clusters authentication (if required)",
default=None,
)

10
api/configs/middleware/vdb/analyticdb_config.py
View File

@ -1,6 +1,6 @@
from typing import Optional
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, PositiveInt
class AnalyticdbConfig(BaseModel):
@ -40,3 +40,11 @@ class AnalyticdbConfig(BaseModel):
description="The password for accessing the specified namespace within the AnalyticDB instance"
" (if namespace feature is enabled).",
)
ANALYTICDB_HOST: Optional[str] = Field(
default=None, description="The host of the AnalyticDB instance you want to connect to."
)
ANALYTICDB_PORT: PositiveInt = Field(
default=5432, description="The port of the AnalyticDB instance you want to connect to."
)
ANALYTICDB_MIN_CONNECTION: PositiveInt = Field(default=1, description="Min connection of the AnalyticDB database.")
ANALYTICDB_MAX_CONNECTION: PositiveInt = Field(default=5, description="Max connection of the AnalyticDB database.")

2
api/configs/packaging/__init__.py
View File

@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
CURRENT_VERSION: str = Field(
description="Dify version",
default="0.11.1",
default="0.11.2",
)
COMMIT_SHA: str = Field(

3
api/controllers/console/app/app.py
View File

@ -9,6 +9,7 @@ from controllers.console.app.wraps import get_app_model
from controllers.console.wraps import (
account_initialization_required,
cloud_edition_billing_resource_check,
enterprise_license_required,
setup_required,
)
from core.model_runtime.utils.encoders import jsonable_encoder
@ -29,6 +30,7 @@ class AppListApi(Resource):
@setup_required
@login_required
@account_initialization_required
@enterprise_license_required
def get(self):
"""Get app list"""
@ -188,6 +190,7 @@ class AppApi(Resource):
@setup_required
@login_required
@account_initialization_required
@enterprise_license_required
@get_app_model
@marshal_with(app_detail_fields_with_site)
def get(self, app_model):

6
api/controllers/console/app/audio.py
View File

@ -70,7 +70,7 @@ class ChatMessageAudioApi(Resource):
except ValueError as e:
raise e
except Exception as e:
logging.exception(f"internal server error, {str(e)}.")
logging.exception("Failed to handle post request to ChatMessageAudioApi")
raise InternalServerError()
@ -128,7 +128,7 @@ class ChatMessageTextApi(Resource):
except ValueError as e:
raise e
except Exception as e:
logging.exception(f"internal server error, {str(e)}.")
logging.exception("Failed to handle post request to ChatMessageTextApi")
raise InternalServerError()
@ -170,7 +170,7 @@ class TextModesApi(Resource):
except ValueError as e:
raise e
except Exception as e:
logging.exception(f"internal server error, {str(e)}.")
logging.exception("Failed to handle get request to TextModesApi")
raise InternalServerError()

4
api/controllers/console/auth/forgot_password.py
View File

@ -14,7 +14,7 @@ from controllers.console.auth.error import (
InvalidTokenError,
PasswordMismatchError,
)
from controllers.console.error import EmailSendIpLimitError, NotAllowedRegister
from controllers.console.error import AccountNotFound, EmailSendIpLimitError
from controllers.console.wraps import setup_required
from events.tenant_event import tenant_was_created
from extensions.ext_database import db
@ -51,7 +51,7 @@ class ForgotPasswordSendEmailApi(Resource):
token = AccountService.send_reset_password_email(email=args["email"], language=language)
return {"result": "fail", "data": token, "code": "account_not_found"}
else:
raise NotAllowedRegister()
raise AccountNotFound()
else:
token = AccountService.send_reset_password_email(account=account, email=args["email"], language=language)

8
api/controllers/console/auth/login.py
View File

@ -16,9 +16,9 @@ from controllers.console.auth.error import (
)
from controllers.console.error import (
AccountBannedError,
AccountNotFound,
EmailSendIpLimitError,
NotAllowedCreateWorkspace,
NotAllowedRegister,
)
from controllers.console.wraps import setup_required
from events.tenant_event import tenant_was_created
@ -76,7 +76,7 @@ class LoginApi(Resource):
token = AccountService.send_reset_password_email(email=args["email"], language=language)
return {"result": "fail", "data": token, "code": "account_not_found"}
else:
raise NotAllowedRegister()
raise AccountNotFound()
# SELF_HOSTED only have one workspace
tenants = TenantService.get_join_tenants(account)
if len(tenants) == 0:
@ -119,7 +119,7 @@ class ResetPasswordSendEmailApi(Resource):
if FeatureService.get_system_features().is_allow_register:
token = AccountService.send_reset_password_email(email=args["email"], language=language)
else:
raise NotAllowedRegister()
raise AccountNotFound()
else:
token = AccountService.send_reset_password_email(account=account, language=language)
@ -148,7 +148,7 @@ class EmailCodeLoginSendEmailApi(Resource):
if FeatureService.get_system_features().is_allow_register:
token = AccountService.send_email_code_login_email(email=args["email"], language=language)
else:
raise NotAllowedRegister()
raise AccountNotFound()
else:
token = AccountService.send_email_code_login_email(account=account, language=language)

3
api/controllers/console/datasets/datasets.py
View File

@ -10,7 +10,7 @@ from controllers.console import api
from controllers.console.apikey import api_key_fields, api_key_list
from controllers.console.app.error import ProviderNotInitializeError
from controllers.console.datasets.error import DatasetInUseError, DatasetNameDuplicateError, IndexingEstimateError
from controllers.console.wraps import account_initialization_required, setup_required
from controllers.console.wraps import account_initialization_required, enterprise_license_required, setup_required
from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
from core.indexing_runner import IndexingRunner
from core.model_runtime.entities.model_entities import ModelType
@ -44,6 +44,7 @@ class DatasetListApi(Resource):
@setup_required
@login_required
@account_initialization_required
@enterprise_license_required
def get(self):
page = request.args.get("page", default=1, type=int)
limit = request.args.get("limit", default=20, type=int)

2
api/controllers/console/datasets/datasets_document.py
View File

@ -959,7 +959,7 @@ class DocumentRetryApi(DocumentResource):
raise DocumentAlreadyFinishedError()
retry_documents.append(document)
except Exception as e:
logging.exception(f"Document {document_id} retry failed: {str(e)}")
logging.exception(f"Failed to retry document, document id: {document_id}")
continue
# retry document
DocumentService.retry_document(dataset_id, retry_documents)

10
api/controllers/console/error.py
View File

@ -52,8 +52,8 @@ class AccountBannedError(BaseHTTPException):
code = 400
class NotAllowedRegister(BaseHTTPException):
error_code = "unauthorized"
class AccountNotFound(BaseHTTPException):
error_code = "account_not_found"
description = "Account not found."
code = 400
@ -86,3 +86,9 @@ class NoFileUploadedError(BaseHTTPException):
error_code = "no_file_uploaded"
description = "Please upload your file."
code = 400
class UnauthorizedAndForceLogout(BaseHTTPException):
error_code = "unauthorized_and_force_logout"
description = "Unauthorized and force logout."
code = 401

2
api/controllers/console/remote_files.py
View File

@ -45,7 +45,7 @@ class RemoteFileUploadApi(Resource):
resp = ssrf_proxy.head(url=url)
if resp.status_code != httpx.codes.OK:
resp = ssrf_proxy.get(url=url, timeout=3)
resp = ssrf_proxy.get(url=url, timeout=3, follow_redirects=True)
resp.raise_for_status()
file_info = helpers.guess_file_info_from_response(resp)

3
api/controllers/console/workspace/account.py
View File

@ -14,7 +14,7 @@ from controllers.console.workspace.error import (
InvalidInvitationCodeError,
RepeatPasswordNotMatchError,
)
from controllers.console.wraps import account_initialization_required, setup_required
from controllers.console.wraps import account_initialization_required, enterprise_license_required, setup_required
from extensions.ext_database import db
from fields.member_fields import account_fields
from libs.helper import TimestampField, timezone
@ -79,6 +79,7 @@ class AccountProfileApi(Resource):
@login_required
@account_initialization_required
@marshal_with(account_fields)
@enterprise_license_required
def get(self):
return current_user

5
api/controllers/console/workspace/members.py
View File

@ -1,3 +1,5 @@
from urllib import parse
from flask_login import current_user
from flask_restful import Resource, abort, marshal_with, reqparse
@ -57,11 +59,12 @@ class MemberInviteEmailApi(Resource):
token = RegisterService.invite_new_member(
inviter.current_tenant, invitee_email, interface_language, role=invitee_role, inviter=inviter
)
encoded_invitee_email = parse.quote(invitee_email)
invitation_results.append(
{
"status": "success",
"email": invitee_email,
"url": f"{console_web_url}/activate?email={invitee_email}&token={token}",
"url": f"{console_web_url}/activate?email={encoded_invitee_email}&token={token}",
}
)
except AccountAlreadyInTenantError:

10
api/controllers/console/workspace/models.py
View File

@ -72,7 +72,10 @@ class DefaultModelApi(Resource):
model=model_setting["model"],
)
except Exception as ex:
logging.exception(f"{model_setting['model_type']} save error: {ex}")
logging.exception(
f"Failed to update default model, model type: {model_setting['model_type']},"
f" model:{model_setting.get('model')}"
)
raise ex
return {"result": "success"}
@ -156,7 +159,10 @@ class ModelProviderModelApi(Resource):
credentials=args["credentials"],
)
except CredentialsValidateFailedError as ex:
logging.exception(f"save model credentials error: {ex}")
logging.exception(
f"Failed to save model credentials, tenant_id: {tenant_id},"
f" model: {args.get('model')}, model_type: {args.get('model_type')}"
)
raise ValueError(str(ex))
return {"result": "success"}, 200

3
api/controllers/console/workspace/tool_providers.py
View File

@ -7,7 +7,7 @@ from werkzeug.exceptions import Forbidden
from configs import dify_config
from controllers.console import api
from controllers.console.wraps import account_initialization_required, setup_required
from controllers.console.wraps import account_initialization_required, enterprise_license_required, setup_required
from core.model_runtime.utils.encoders import jsonable_encoder
from libs.helper import alphanumeric, uuid_value
from libs.login import login_required
@ -608,6 +608,7 @@ class ToolLabelsApi(Resource):
@setup_required
@login_required
@account_initialization_required
@enterprise_license_required
def get(self):
return jsonable_encoder(ToolLabelsService.list_tool_labels())

16
api/controllers/console/wraps.py
View File

@ -9,10 +9,10 @@ from configs import dify_config
from controllers.console.workspace.error import AccountNotInitializedError
from extensions.ext_database import db
from models.model import DifySetup
from services.feature_service import FeatureService
from services.feature_service import FeatureService, LicenseStatus
from services.operation_service import OperationService
from .error import NotInitValidateError, NotSetupError
from .error import NotInitValidateError, NotSetupError, UnauthorizedAndForceLogout
def account_initialization_required(view):
@ -147,3 +147,15 @@ def setup_required(view):
return view(*args, **kwargs)
return decorated
def enterprise_license_required(view):
@wraps(view)
def decorated(*args, **kwargs):
settings = FeatureService.get_system_features()
if settings.license.status in [LicenseStatus.INACTIVE, LicenseStatus.EXPIRED, LicenseStatus.LOST]:
raise UnauthorizedAndForceLogout("Your license is invalid. Please contact your administrator.")
return view(*args, **kwargs)
return decorated

4
api/controllers/web/audio.py
View File

@ -59,7 +59,7 @@ class AudioApi(WebApiResource):
except ValueError as e:
raise e
except Exception as e:
logging.exception(f"internal server error: {str(e)}")
logging.exception("Failed to handle post request to AudioApi")
raise InternalServerError()
@ -117,7 +117,7 @@ class TextApi(WebApiResource):
except ValueError as e:
raise e
except Exception as e:
logging.exception(f"internal server error: {str(e)}")
logging.exception("Failed to handle post request to TextApi")
raise InternalServerError()

4
api/core/app/app_config/features/file_upload/manager.py
View File

@ -16,9 +16,7 @@ class FileUploadConfigManager:
file_upload_dict = config.get("file_upload")
if file_upload_dict:
if file_upload_dict.get("enabled"):
transform_methods = file_upload_dict.get("allowed_file_upload_methods") or file_upload_dict.get(
"allowed_upload_methods", []
)
transform_methods = file_upload_dict.get("allowed_file_upload_methods", [])
data = {
"image_config": {
"number_limits": file_upload_dict["number_limits"],

2
api/core/app/apps/advanced_chat/app_generator.py
View File

@ -373,5 +373,5 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
if e.args[0] == "I/O operation on closed file.": # ignore this error
raise GenerateTaskStoppedError()
else:
logger.exception(e)
logger.exception(f"Failed to process generate task pipeline, conversation_id: {conversation.id}")
raise e

2
api/core/app/apps/advanced_chat/generate_task_pipeline.py
View File

@ -242,7 +242,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
start_listener_time = time.time()
yield MessageAudioStreamResponse(audio=audio_trunk.audio, task_id=task_id)
except Exception as e:
logger.exception(e)
logger.exception(f"Failed to listen audio message, task_id: {task_id}")
break
if tts_publisher:
yield MessageAudioEndStreamResponse(audio="", task_id=task_id)

11
api/core/app/apps/base_app_generator.py
View File

@ -34,8 +34,8 @@ class BaseAppGenerator:
tenant_id=app_config.tenant_id,
config=FileUploadConfig(
allowed_file_types=entity_dictionary[k].allowed_file_types,
allowed_extensions=entity_dictionary[k].allowed_file_extensions,
allowed_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
allowed_file_extensions=entity_dictionary[k].allowed_file_extensions,
allowed_file_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
),
)
for k, v in user_inputs.items()
@ -48,8 +48,8 @@ class BaseAppGenerator:
tenant_id=app_config.tenant_id,
config=FileUploadConfig(
allowed_file_types=entity_dictionary[k].allowed_file_types,
allowed_extensions=entity_dictionary[k].allowed_file_extensions,
allowed_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
allowed_file_extensions=entity_dictionary[k].allowed_file_extensions,
allowed_file_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
),
)
for k, v in user_inputs.items()
@ -92,6 +92,9 @@ class BaseAppGenerator:
)
if variable_entity.type == VariableEntityType.NUMBER and isinstance(value, str):
# handle empty string case
if not value.strip():
return None
# may raise ValueError if user_input_value is not a valid number
try:
if "." in value:

2
api/core/app/apps/message_based_app_generator.py
View File

@ -80,7 +80,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
if e.args[0] == "I/O operation on closed file.": # ignore this error
raise GenerateTaskStoppedError()
else:
logger.exception(e)
logger.exception(f"Failed to handle response, conversation_id: {conversation.id}")
raise e
def _get_conversation_by_user(

4
api/core/app/apps/workflow/app_generator.py
View File

@ -310,5 +310,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
if e.args[0] == "I/O operation on closed file.": # ignore this error
raise GenerateTaskStoppedError()
else:
logger.exception(e)
logger.exception(
f"Fails to process generate task pipeline, task_id: {application_generate_entity.task_id}"
)
raise e

2
api/core/app/apps/workflow/generate_task_pipeline.py
View File

@ -216,7 +216,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
else:
yield MessageAudioStreamResponse(audio=audio_trunk.audio, task_id=task_id)
except Exception as e:
logger.exception(e)
logger.exception(f"Fails to get audio trunk, task_id: {task_id}")
break
if tts_publisher:
yield MessageAudioEndStreamResponse(audio="", task_id=task_id)

2
api/core/app/task_pipeline/message_cycle_manage.py
View File

@ -86,7 +86,7 @@ class MessageCycleManage:
conversation.name = name
except Exception as e:
if dify_config.DEBUG:
logging.exception(f"generate conversation name failed: {e}")
logging.exception(f"generate conversation name failed, conversation_id: {conversation_id}")
pass
db.session.merge(conversation)

4
api/core/file/models.py
View File

@ -28,8 +28,8 @@ class FileUploadConfig(BaseModel):
image_config: Optional[ImageConfig] = None
allowed_file_types: Sequence[FileType] = Field(default_factory=list)
allowed_extensions: Sequence[str] = Field(default_factory=list)
allowed_upload_methods: Sequence[FileTransferMethod] = Field(default_factory=list)
allowed_file_extensions: Sequence[str] = Field(default_factory=list)
allowed_file_upload_methods: Sequence[FileTransferMethod] = Field(default_factory=list)
number_limits: int = 0

2
api/core/helper/moderation.py
View File

@ -55,7 +55,7 @@ def check_moderation(tenant_id: str, model_config: ModelConfigWithCredentialsEnt
if moderation_result is True:
return True
except Exception as ex:
logger.exception(ex)
logger.exception(f"Fails to check moderation, provider_name: {provider_name}")
raise InvokeBadRequestError("Rate limit exceeded, please try again later.")
return False

2
api/core/helper/module_import_helper.py
View File

@ -29,7 +29,7 @@ def import_module_from_source(*, module_name: str, py_file_path: AnyStr, use_laz
spec.loader.exec_module(module)
return module
except Exception as e:
logging.exception(f"Failed to load module {module_name} from {py_file_path}: {str(e)}")
logging.exception(f"Failed to load module {module_name} from script file '{py_file_path}'")
raise e

3
api/core/helper/ssrf_proxy.py
View File

@ -39,6 +39,7 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
)
retries = 0
stream = kwargs.pop("stream", False)
while retries <= max_retries:
try:
if dify_config.SSRF_PROXY_ALL_URL:
@ -52,6 +53,8 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
response = client.request(method=method, url=url, **kwargs)
if response.status_code not in STATUS_FORCELIST:
if stream:
return response.iter_bytes()
return response
else:
logging.warning(

9
api/core/indexing_runner.py
View File

@ -29,6 +29,7 @@ from core.rag.splitter.fixed_text_splitter import (
FixedRecursiveCharacterTextSplitter,
)
from core.rag.splitter.text_splitter import TextSplitter
from core.tools.utils.text_processing_utils import remove_leading_symbols
from extensions.ext_database import db
from extensions.ext_redis import redis_client
from extensions.ext_storage import storage
@ -500,11 +501,7 @@ class IndexingRunner:
document_node.metadata["doc_hash"] = hash
# delete Splitter character
page_content = document_node.page_content
if page_content.startswith(".") or page_content.startswith("。"):
page_content = page_content[1:]
else:
page_content = page_content
document_node.page_content = page_content
document_node.page_content = remove_leading_symbols(page_content)
if document_node.page_content:
split_documents.append(document_node)
@ -554,7 +551,7 @@ class IndexingRunner:
qa_documents.append(qa_document)
format_documents.extend(qa_documents)
except Exception as e:
logging.exception(e)
logging.exception("Failed to format qa document")
all_qa_documents.extend(format_documents)

10
api/core/llm_generator/llm_generator.py
View File

@ -102,7 +102,7 @@ class LLMGenerator:
except InvokeError:
questions = []
except Exception as e:
logging.exception(e)
logging.exception("Failed to generate suggested questions after answer")
questions = []
return questions
@ -148,7 +148,7 @@ class LLMGenerator:
error = str(e)
error_step = "generate rule config"
except Exception as e:
logging.exception(e)
logging.exception(f"Failed to generate rule config, model: {model_config.get('name')}")
rule_config["error"] = str(e)
rule_config["error"] = f"Failed to {error_step}. Error: {error}" if error else ""
@ -234,7 +234,7 @@ class LLMGenerator:
error_step = "generate conversation opener"
except Exception as e:
logging.exception(e)
logging.exception(f"Failed to generate rule config, model: {model_config.get('name')}")
rule_config["error"] = str(e)
rule_config["error"] = f"Failed to {error_step}. Error: {error}" if error else ""
@ -286,7 +286,9 @@ class LLMGenerator:
error = str(e)
return {"code": "", "language": code_language, "error": f"Failed to generate code. Error: {error}"}
except Exception as e:
logging.exception(e)
logging.exception(
f"Failed to invoke LLM model, model: {model_config.get('name')}, language: {code_language}"
)
return {"code": "", "language": code_language, "error": f"An unexpected error occurred: {str(e)}"}
@classmethod

6
api/core/model_runtime/model_providers/gitee_ai/_assets/Gitee-AI-Logo-full.svg
View File

File diff suppressed because one or more lines are too long
Side by Side

Before

Width:  |  Height:  |  Size: 9.8 KiB

3
api/core/model_runtime/model_providers/gitee_ai/_assets/Gitee-AI-Logo.svg
View File

@ -1,3 +0,0 @@
<svg width="40" height="40" viewBox="0 0 40 40" fill="none" xmlns="http://www.w3.org/2000/svg">
<path fill-rule="evenodd" clip-rule="evenodd" d="M25.132 24.3947C25.497 25.7527 25.8984 27.1413 26.3334 28.5834C26.7302 29.8992 25.5459 30.4167 25.0752 29.1758C24.571 27.8466 24.0885 26.523 23.6347 25.1729C21.065 26.4654 18.5025 27.5424 15.5961 28.7541C16.7581 33.0256 17.8309 36.5984 19.4952 39.9935C19.4953 39.9936 19.4953 39.9937 19.4954 39.9938C19.6631 39.9979 19.8313 40 20 40C31.0457 40 40 31.0457 40 20C40 16.0335 38.8453 12.3366 36.8537 9.22729C31.6585 9.69534 27.0513 10.4562 22.8185 11.406C22.8882 12.252 22.9677 13.0739 23.0555 13.855C23.3824 16.7604 23.9112 19.5281 24.6137 22.3836C27.0581 21.2848 29.084 20.3225 30.6816 19.522C32.2154 18.7535 33.6943 18.7062 31.2018 20.6594C29.0388 22.1602 27.0644 23.3566 25.132 24.3947ZM36.1559 8.20846C33.0001 3.89184 28.1561 0.887462 22.5955 0.166882C22.4257 2.86234 22.4785 6.26344 22.681 9.50447C26.7473 8.88859 31.1721 8.46032 36.1559 8.20846ZM19.9369 9.73661e-05C19.7594 2.92694 19.8384 6.65663 20.19 9.91293C17.3748 10.4109 14.7225 11.0064 12.1592 11.7038C12.0486 10.4257 11.9927 9.25764 11.9927 8.24178C11.9927 7.5054 11.3957 6.90844 10.6593 6.90844C9.92296 6.90844 9.32601 7.5054 9.32601 8.24178C9.32601 9.47868 9.42873 10.898 9.61402 12.438C8.33567 12.8278 7.07397 13.2443 5.81918 13.688C5.12493 13.9336 4.76118 14.6954 5.0067 15.3896C5.25223 16.0839 6.01406 16.4476 6.7083 16.2021C7.7931 15.8185 8.88482 15.4388 9.98927 15.0659C10.5222 18.3344 11.3344 21.9428 12.2703 25.4156C12.4336 26.0218 12.6062 26.6262 12.7863 27.2263C9.34168 28.4135 5.82612 29.3782 2.61128 29.8879C0.949407 26.9716 0 23.5967 0 20C0 8.97534 8.92023 0.0341108 19.9369 9.73661e-05ZM4.19152 32.2527C7.45069 36.4516 12.3458 39.3173 17.9204 39.8932C16.5916 37.455 14.9338 33.717 13.5405 29.5901C10.4404 30.7762 7.25883 31.6027 4.19152 32.2527ZM22.9735 23.1135C22.1479 20.41 21.4462 17.5441 20.9225 14.277C20.746 13.5841 20.5918 12.8035 20.4593 11.9636C17.6508 12.6606 14.9992 13.4372 12.4356 14.2598C12.8479 17.4766 13.5448 21.1334 14.5118 24.7218C14.662 25.2792 14.8081 25.8248 14.9514 26.3594L14.9516 26.3603L14.9524 26.3634L14.9526 26.3639L14.973 26.4401C16.1833 25.9872 17.3746 25.5123 18.53 25.0259C20.1235 24.3552 21.6051 23.7165 22.9735 23.1135Z" fill="#141519"/>
</svg>
Side by Side

Before

Width:  |  Height:  |  Size: 2.2 KiB

47
api/core/model_runtime/model_providers/gitee_ai/_common.py
View File

@ -1,47 +0,0 @@
from dashscope.common.error import (
AuthenticationError,
InvalidParameter,
RequestFailure,
ServiceUnavailableError,
UnsupportedHTTPMethod,
UnsupportedModel,
)
from core.model_runtime.errors.invoke import (
InvokeAuthorizationError,
InvokeBadRequestError,
InvokeConnectionError,
InvokeError,
InvokeRateLimitError,
InvokeServerUnavailableError,
)
class _CommonGiteeAI:
@property
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
"""
Map model invoke error to unified error
The key is the error type thrown to the caller
The value is the error type thrown by the model,
which needs to be converted into a unified error type for the caller.
:return: Invoke error mapping
"""
return {
InvokeConnectionError: [
RequestFailure,
],
InvokeServerUnavailableError: [
ServiceUnavailableError,
],
InvokeRateLimitError: [],
InvokeAuthorizationError: [
AuthenticationError,
],
InvokeBadRequestError: [
InvalidParameter,
UnsupportedModel,
UnsupportedHTTPMethod,
],
}

36
api/core/model_runtime/model_providers/gitee_ai/gitee_ai.py
View File

@ -1,36 +0,0 @@
import logging
import requests
from core.model_runtime.errors.validate import CredentialsValidateFailedError
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
logger = logging.getLogger(__name__)
class GiteeAIProvider(ModelProvider):
def validate_provider_credentials(self, credentials: dict) -> None:
"""
Validate provider credentials
if validate failed, raise exception
:param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
"""
try:
api_key = credentials.get("api_key")
if not api_key:
raise CredentialsValidateFailedError("Credentials validation failed: api_key not given")
# send a get request to validate the credentials
headers = {"Authorization": f"Bearer {api_key}"}
response = requests.get("https://ai.gitee.com/api/base/account/me", headers=headers, timeout=(10, 300))
if response.status_code != 200:
raise CredentialsValidateFailedError(
f"Credentials validation failed with status code {response.status_code}"
)
except CredentialsValidateFailedError as ex:
raise ex
except Exception as ex:
logger.exception(f"{self.get_provider_schema().provider} credentials validate failed")
raise ex

35
api/core/model_runtime/model_providers/gitee_ai/gitee_ai.yaml
View File

@ -1,35 +0,0 @@
provider: gitee_ai
label:
en_US: Gitee AI
zh_Hans: Gitee AI
description:
en_US: 快速体验大模型，领先探索 AI 开源世界
zh_Hans: 快速体验大模型，领先探索 AI 开源世界
icon_small:
en_US: Gitee-AI-Logo.svg
icon_large:
en_US: Gitee-AI-Logo-full.svg
help:
title:
en_US: Get your token from Gitee AI
zh_Hans: 从 Gitee AI 获取 token
url:
en_US: https://ai.gitee.com/dashboard/settings/tokens
supported_model_types:
- llm
- text-embedding
- rerank
- speech2text
- tts
configurate_methods:
- predefined-model
provider_credential_schema:
credential_form_schemas:
- variable: api_key
label:
en_US: API Key
type: secret-input
required: true
placeholder:
zh_Hans: 在此输入您的 API Key
en_US: Enter your API Key

105
api/core/model_runtime/model_providers/gitee_ai/llm/Qwen2-72B-Instruct.yaml
View File

@ -1,105 +0,0 @@
model: Qwen2-72B-Instruct
label:
zh_Hans: Qwen2-72B-Instruct
en_US: Qwen2-72B-Instruct
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 6400
parameter_rules:
- name: stream
use_template: boolean
label:
en_US: "Stream"
zh_Hans: "流式"
type: boolean
default: true
required: true
help:
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
- name: max_tokens
use_template: max_tokens
label:
en_US: "Max Tokens"
zh_Hans: "最大Token数"
type: int
default: 512
min: 1
required: true
help:
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
- name: temperature
use_template: temperature
label:
en_US: "Temperature"
zh_Hans: "采样温度"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_p
use_template: top_p
label:
en_US: "Top P"
zh_Hans: "Top P"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_k
use_template: top_k
label:
en_US: "Top K"
zh_Hans: "Top K"
type: int
default: 50
min: 0
max: 100
required: true
help:
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
- name: frequency_penalty
use_template: frequency_penalty
label:
en_US: "Frequency Penalty"
zh_Hans: "频率惩罚"
type: float
default: 0
min: -1.0
max: 1.0
precision: 1
required: false
help:
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
- name: user
use_template: text
label:
en_US: "User"
zh_Hans: "用户"
type: string
required: false
help:
en_US: "Used to track and differentiate conversation requests from different users."
zh_Hans: "用于追踪和区分不同用户的对话请求。"

105
api/core/model_runtime/model_providers/gitee_ai/llm/Qwen2-7B-Instruct.yaml
View File

@ -1,105 +0,0 @@
model: Qwen2-7B-Instruct
label:
zh_Hans: Qwen2-7B-Instruct
en_US: Qwen2-7B-Instruct
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 32768
parameter_rules:
- name: stream
use_template: boolean
label:
en_US: "Stream"
zh_Hans: "流式"
type: boolean
default: true
required: true
help:
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
- name: max_tokens
use_template: max_tokens
label:
en_US: "Max Tokens"
zh_Hans: "最大Token数"
type: int
default: 512
min: 1
required: true
help:
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
- name: temperature
use_template: temperature
label:
en_US: "Temperature"
zh_Hans: "采样温度"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_p
use_template: top_p
label:
en_US: "Top P"
zh_Hans: "Top P"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_k
use_template: top_k
label:
en_US: "Top K"
zh_Hans: "Top K"
type: int
default: 50
min: 0
max: 100
required: true
help:
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
- name: frequency_penalty
use_template: frequency_penalty
label:
en_US: "Frequency Penalty"
zh_Hans: "频率惩罚"
type: float
default: 0
min: -1.0
max: 1.0
precision: 1
required: false
help:
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
- name: user
use_template: text
label:
en_US: "User"
zh_Hans: "用户"
type: string
required: false
help:
en_US: "Used to track and differentiate conversation requests from different users."
zh_Hans: "用于追踪和区分不同用户的对话请求。"

95
api/core/model_runtime/model_providers/gitee_ai/llm/Qwen2.5-72B-Instruct.yaml
View File

@ -1,95 +0,0 @@
model: Qwen2.5-72B-Instruct
label:
zh_Hans: Qwen2.5-72B-Instruct
en_US: Qwen2.5-72B-Instruct
model_type: llm
features:
- agent-thought
- tool-call
- stream-tool-call
model_properties:
mode: chat
context_size: 32768
parameter_rules:
- name: max_tokens
use_template: max_tokens
label:
en_US: "Max Tokens"
zh_Hans: "最大Token数"
type: int
default: 512
min: 1
required: true
help:
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
- name: temperature
use_template: temperature
label:
en_US: "Temperature"
zh_Hans: "采样温度"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_p
use_template: top_p
label:
en_US: "Top P"
zh_Hans: "Top P"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_k
use_template: top_k
label:
en_US: "Top K"
zh_Hans: "Top K"
type: int
default: 50
min: 0
max: 100
required: true
help:
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
- name: frequency_penalty
use_template: frequency_penalty
label:
en_US: "Frequency Penalty"
zh_Hans: "频率惩罚"
type: float
default: 0
min: -1.0
max: 1.0
precision: 1
required: false
help:
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
- name: user
use_template: text
label:
en_US: "User"
zh_Hans: "用户"
type: string
required: false
help:
en_US: "Used to track and differentiate conversation requests from different users."
zh_Hans: "用于追踪和区分不同用户的对话请求。"

105
api/core/model_runtime/model_providers/gitee_ai/llm/Yi-1.5-34B-Chat.yaml
View File

@ -1,105 +0,0 @@
model: Yi-1.5-34B-Chat
label:
zh_Hans: Yi-1.5-34B-Chat
en_US: Yi-1.5-34B-Chat
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 4096
parameter_rules:
- name: stream
use_template: boolean
label:
en_US: "Stream"
zh_Hans: "流式"
type: boolean
default: true
required: true
help:
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
- name: max_tokens
use_template: max_tokens
label:
en_US: "Max Tokens"
zh_Hans: "最大Token数"
type: int
default: 512
min: 1
required: true
help:
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
- name: temperature
use_template: temperature
label:
en_US: "Temperature"
zh_Hans: "采样温度"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_p
use_template: top_p
label:
en_US: "Top P"
zh_Hans: "Top P"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_k
use_template: top_k
label:
en_US: "Top K"
zh_Hans: "Top K"
type: int
default: 50
min: 0
max: 100
required: true
help:
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
- name: frequency_penalty
use_template: frequency_penalty
label:
en_US: "Frequency Penalty"
zh_Hans: "频率惩罚"
type: float
default: 0
min: -1.0
max: 1.0
precision: 1
required: false
help:
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
- name: user
use_template: text
label:
en_US: "User"
zh_Hans: "用户"
type: string
required: false
help:
en_US: "Used to track and differentiate conversation requests from different users."
zh_Hans: "用于追踪和区分不同用户的对话请求。"

8
api/core/model_runtime/model_providers/gitee_ai/llm/_position.yaml
View File

@ -1,8 +0,0 @@
- Qwen2.5-72B-Instruct
- Qwen2-7B-Instruct
- Qwen2-72B-Instruct
- Yi-1.5-34B-Chat
- glm-4-9b-chat
- deepseek-coder-33B-instruct-chat
- deepseek-coder-33B-instruct-completions
- codegeex4-all-9b

105
api/core/model_runtime/model_providers/gitee_ai/llm/codegeex4-all-9b.yaml
View File

@ -1,105 +0,0 @@
model: codegeex4-all-9b
label:
zh_Hans: codegeex4-all-9b
en_US: codegeex4-all-9b
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 40960
parameter_rules:
- name: stream
use_template: boolean
label:
en_US: "Stream"
zh_Hans: "流式"
type: boolean
default: true
required: true
help:
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
- name: max_tokens
use_template: max_tokens
label:
en_US: "Max Tokens"
zh_Hans: "最大Token数"
type: int
default: 512
min: 1
required: true
help:
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
- name: temperature
use_template: temperature
label:
en_US: "Temperature"
zh_Hans: "采样温度"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_p
use_template: top_p
label:
en_US: "Top P"
zh_Hans: "Top P"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_k
use_template: top_k
label:
en_US: "Top K"
zh_Hans: "Top K"
type: int
default: 50
min: 0
max: 100
required: true
help:
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
- name: frequency_penalty
use_template: frequency_penalty
label:
en_US: "Frequency Penalty"
zh_Hans: "频率惩罚"
type: float
default: 0
min: -1.0
max: 1.0
precision: 1
required: false
help:
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
- name: user
use_template: text
label:
en_US: "User"
zh_Hans: "用户"
type: string
required: false
help:
en_US: "Used to track and differentiate conversation requests from different users."
zh_Hans: "用于追踪和区分不同用户的对话请求。"

105
api/core/model_runtime/model_providers/gitee_ai/llm/deepseek-coder-33B-instruct-chat.yaml
View File

@ -1,105 +0,0 @@
model: deepseek-coder-33B-instruct-chat
label:
zh_Hans: deepseek-coder-33B-instruct-chat
en_US: deepseek-coder-33B-instruct-chat
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 9000
parameter_rules:
- name: stream
use_template: boolean
label:
en_US: "Stream"
zh_Hans: "流式"
type: boolean
default: true
required: true
help:
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
- name: max_tokens
use_template: max_tokens
label:
en_US: "Max Tokens"
zh_Hans: "最大Token数"
type: int
default: 512
min: 1
required: true
help:
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
- name: temperature
use_template: temperature
label:
en_US: "Temperature"
zh_Hans: "采样温度"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_p
use_template: top_p
label:
en_US: "Top P"
zh_Hans: "Top P"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_k
use_template: top_k
label:
en_US: "Top K"
zh_Hans: "Top K"
type: int
default: 50
min: 0
max: 100
required: true
help:
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
- name: frequency_penalty
use_template: frequency_penalty
label:
en_US: "Frequency Penalty"
zh_Hans: "频率惩罚"
type: float
default: 0
min: -1.0
max: 1.0
precision: 1
required: false
help:
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
- name: user
use_template: text
label:
en_US: "User"
zh_Hans: "用户"
type: string
required: false
help:
en_US: "Used to track and differentiate conversation requests from different users."
zh_Hans: "用于追踪和区分不同用户的对话请求。"

91
api/core/model_runtime/model_providers/gitee_ai/llm/deepseek-coder-33B-instruct-completions.yaml
View File

@ -1,91 +0,0 @@
model: deepseek-coder-33B-instruct-completions
label:
zh_Hans: deepseek-coder-33B-instruct-completions
en_US: deepseek-coder-33B-instruct-completions
model_type: llm
features:
- agent-thought
model_properties:
mode: completion
context_size: 9000
parameter_rules:
- name: stream
use_template: boolean
label:
en_US: "Stream"
zh_Hans: "流式"
type: boolean
default: true
required: true
help:
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
- name: max_tokens
use_template: max_tokens
label:
en_US: "Max Tokens"
zh_Hans: "最大Token数"
type: int
default: 512
min: 1
required: true
help:
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
- name: temperature
use_template: temperature
label:
en_US: "Temperature"
zh_Hans: "采样温度"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_p
use_template: top_p
label:
en_US: "Top P"
zh_Hans: "Top P"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: frequency_penalty
use_template: frequency_penalty
label:
en_US: "Frequency Penalty"
zh_Hans: "频率惩罚"
type: float
default: 0
min: -1.0
max: 1.0
precision: 1
required: false
help:
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
- name: user
use_template: text
label:
en_US: "User"
zh_Hans: "用户"
type: string
required: false
help:
en_US: "Used to track and differentiate conversation requests from different users."
zh_Hans: "用于追踪和区分不同用户的对话请求。"

105
api/core/model_runtime/model_providers/gitee_ai/llm/glm-4-9b-chat.yaml
View File

@ -1,105 +0,0 @@
model: glm-4-9b-chat
label:
zh_Hans: glm-4-9b-chat
en_US: glm-4-9b-chat
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 32768
parameter_rules:
- name: stream
use_template: boolean
label:
en_US: "Stream"
zh_Hans: "流式"
type: boolean
default: true
required: true
help:
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
- name: max_tokens
use_template: max_tokens
label:
en_US: "Max Tokens"
zh_Hans: "最大Token数"
type: int
default: 512
min: 1
required: true
help:
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
- name: temperature
use_template: temperature
label:
en_US: "Temperature"
zh_Hans: "采样温度"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_p
use_template: top_p
label:
en_US: "Top P"
zh_Hans: "Top P"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_k
use_template: top_k
label:
en_US: "Top K"
zh_Hans: "Top K"
type: int
default: 50
min: 0
max: 100
required: true
help:
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
- name: frequency_penalty
use_template: frequency_penalty
label:
en_US: "Frequency Penalty"
zh_Hans: "频率惩罚"
type: float
default: 0
min: -1.0
max: 1.0
precision: 1
required: false
help:
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
- name: user
use_template: text
label:
en_US: "User"
zh_Hans: "用户"
type: string
required: false
help:
en_US: "Used to track and differentiate conversation requests from different users."
zh_Hans: "用于追踪和区分不同用户的对话请求。"

51
api/core/model_runtime/model_providers/gitee_ai/llm/llm.py
View File

@ -1,51 +0,0 @@
from collections.abc import Generator
from typing import Optional, Union
from core.model_runtime.entities.llm_entities import LLMMode, LLMResult
from core.model_runtime.entities.message_entities import (
PromptMessage,
PromptMessageTool,
)
from core.model_runtime.entities.model_entities import ModelFeature
from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
class GiteeAILargeLanguageModel(OAIAPICompatLargeLanguageModel):
MODEL_TO_IDENTITY: dict[str, str] = {
"Yi-1.5-34B-Chat": "Yi-34B-Chat",
"deepseek-coder-33B-instruct-completions": "deepseek-coder-33B-instruct",
"deepseek-coder-33B-instruct-chat": "deepseek-coder-33B-instruct",
}
def _invoke(
self,
model: str,
credentials: dict,
prompt_messages: list[PromptMessage],
model_parameters: dict,
tools: Optional[list[PromptMessageTool]] = None,
stop: Optional[list[str]] = None,
stream: bool = True,
user: Optional[str] = None,
) -> Union[LLMResult, Generator]:
self._add_custom_parameters(credentials, model, model_parameters)
return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)
def validate_credentials(self, model: str, credentials: dict) -> None:
self._add_custom_parameters(credentials, model, None)
super().validate_credentials(model, credentials)
def _add_custom_parameters(self, credentials: dict, model: str, model_parameters: dict) -> None:
if model is None:
model = "bge-large-zh-v1.5"
model_identity = GiteeAILargeLanguageModel.MODEL_TO_IDENTITY.get(model, model)
credentials["endpoint_url"] = f"https://ai.gitee.com/api/serverless/{model_identity}/"
if model.endswith("completions"):
credentials["mode"] = LLMMode.COMPLETION.value
else:
credentials["mode"] = LLMMode.CHAT.value
schema = self.get_model_schema(model, credentials)
if ModelFeature.TOOL_CALL in schema.features or ModelFeature.MULTI_TOOL_CALL in schema.features:
credentials["function_calling_type"] = "tool_call"

0
api/core/model_runtime/model_providers/gitee_ai/rerank/__init__.py
View File

1
api/core/model_runtime/model_providers/gitee_ai/rerank/_position.yaml
View File

@ -1 +0,0 @@
- bge-reranker-v2-m3

4
api/core/model_runtime/model_providers/gitee_ai/rerank/bge-reranker-v2-m3.yaml
View File

@ -1,4 +0,0 @@
model: bge-reranker-v2-m3
model_type: rerank
model_properties:
context_size: 1024

128
api/core/model_runtime/model_providers/gitee_ai/rerank/rerank.py
View File

@ -1,128 +0,0 @@
from typing import Optional
import httpx
from core.model_runtime.entities.common_entities import I18nObject
from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType
from core.model_runtime.entities.rerank_entities import RerankDocument, RerankResult
from core.model_runtime.errors.invoke import (
InvokeAuthorizationError,
InvokeBadRequestError,
InvokeConnectionError,
InvokeError,
InvokeRateLimitError,
InvokeServerUnavailableError,
)
from core.model_runtime.errors.validate import CredentialsValidateFailedError
from core.model_runtime.model_providers.__base.rerank_model import RerankModel
class GiteeAIRerankModel(RerankModel):
"""
Model class for rerank model.
"""
def _invoke(
self,
model: str,
credentials: dict,
query: str,
docs: list[str],
score_threshold: Optional[float] = None,
top_n: Optional[int] = None,
user: Optional[str] = None,
) -> RerankResult:
"""
Invoke rerank model
:param model: model name
:param credentials: model credentials
:param query: search query
:param docs: docs for reranking
:param score_threshold: score threshold
:param top_n: top n documents to return
:param user: unique user id
:return: rerank result
"""
if len(docs) == 0:
return RerankResult(model=model, docs=[])
base_url = credentials.get("base_url", "https://ai.gitee.com/api/serverless")
base_url = base_url.removesuffix("/")
try:
body = {"model": model, "query": query, "documents": docs}
if top_n is not None:
body["top_n"] = top_n
response = httpx.post(
f"{base_url}/{model}/rerank",
json=body,
headers={"Authorization": f"Bearer {credentials.get('api_key')}"},
)
response.raise_for_status()
results = response.json()
rerank_documents = []
for result in results["results"]:
rerank_document = RerankDocument(
index=result["index"],
text=result["document"]["text"],
score=result["relevance_score"],
)
if score_threshold is None or result["relevance_score"] >= score_threshold:
rerank_documents.append(rerank_document)
return RerankResult(model=model, docs=rerank_documents)
except httpx.HTTPStatusError as e:
raise InvokeServerUnavailableError(str(e))
def validate_credentials(self, model: str, credentials: dict) -> None:
"""
Validate model credentials
:param model: model name
:param credentials: model credentials
:return:
"""
try:
self._invoke(
model=model,
credentials=credentials,
query="What is the capital of the United States?",
docs=[
"Carson City is the capital city of the American state of Nevada. At the 2010 United States "
"Census, Carson City had a population of 55,274.",
"The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean that "
"are a political division controlled by the United States. Its capital is Saipan.",
],
score_threshold=0.01,
)
except Exception as ex:
raise CredentialsValidateFailedError(str(ex))
@property
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
"""
Map model invoke error to unified error
"""
return {
InvokeConnectionError: [httpx.ConnectError],
InvokeServerUnavailableError: [httpx.RemoteProtocolError],
InvokeRateLimitError: [],
InvokeAuthorizationError: [httpx.HTTPStatusError],
InvokeBadRequestError: [httpx.RequestError],
}
def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
"""
generate custom model entities from credentials
"""
entity = AIModelEntity(
model=model,
label=I18nObject(en_US=model),
model_type=ModelType.RERANK,
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
)
return entity

0
api/core/model_runtime/model_providers/gitee_ai/speech2text/__init__.py
View File

2
api/core/model_runtime/model_providers/gitee_ai/speech2text/_position.yaml
View File

@ -1,2 +0,0 @@
- whisper-base
- whisper-large

53
api/core/model_runtime/model_providers/gitee_ai/speech2text/speech2text.py
View File

@ -1,53 +0,0 @@
import os
from typing import IO, Optional
import requests
from core.model_runtime.errors.invoke import InvokeBadRequestError
from core.model_runtime.errors.validate import CredentialsValidateFailedError
from core.model_runtime.model_providers.__base.speech2text_model import Speech2TextModel
from core.model_runtime.model_providers.gitee_ai._common import _CommonGiteeAI
class GiteeAISpeech2TextModel(_CommonGiteeAI, Speech2TextModel):
"""
Model class for OpenAI Compatible Speech to text model.
"""
def _invoke(self, model: str, credentials: dict, file: IO[bytes], user: Optional[str] = None) -> str:
"""
Invoke speech2text model
:param model: model name
:param credentials: model credentials
:param file: audio file
:param user: unique user id
:return: text for given audio file
"""
# doc: https://ai.gitee.com/docs/openapi/serverless#tag/serverless/POST/{service}/speech-to-text
endpoint_url = f"https://ai.gitee.com/api/serverless/{model}/speech-to-text"
files = [("file", file)]
_, file_ext = os.path.splitext(file.name)
headers = {"Content-Type": f"audio/{file_ext}", "Authorization": f"Bearer {credentials.get('api_key')}"}
response = requests.post(endpoint_url, headers=headers, files=files)
if response.status_code != 200:
raise InvokeBadRequestError(response.text)
response_data = response.json()
return response_data["text"]
def validate_credentials(self, model: str, credentials: dict) -> None:
"""
Validate model credentials
:param model: model name
:param credentials: model credentials
:return:
"""
try:
audio_file_path = self._get_demo_file_path()
with open(audio_file_path, "rb") as audio_file:
self._invoke(model, credentials, audio_file)
except Exception as ex:
raise CredentialsValidateFailedError(str(ex))

5
api/core/model_runtime/model_providers/gitee_ai/speech2text/whisper-base.yaml
View File

@ -1,5 +0,0 @@
model: whisper-base
model_type: speech2text
model_properties:
file_upload_limit: 1
supported_file_extensions: flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm

5
api/core/model_runtime/model_providers/gitee_ai/speech2text/whisper-large.yaml
View File

@ -1,5 +0,0 @@
model: whisper-large
model_type: speech2text
model_properties:
file_upload_limit: 1
supported_file_extensions: flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm

3
api/core/model_runtime/model_providers/gitee_ai/text_embedding/_position.yaml
View File

@ -1,3 +0,0 @@
- bge-large-zh-v1.5
- bge-small-zh-v1.5
- bge-m3

8
api/core/model_runtime/model_providers/gitee_ai/text_embedding/bge-large-zh-v1.5.yaml
View File

@ -1,8 +0,0 @@
model: bge-large-zh-v1.5
label:
zh_Hans: bge-large-zh-v1.5
en_US: bge-large-zh-v1.5
model_type: text-embedding
model_properties:
context_size: 200000
max_chunks: 20

8
api/core/model_runtime/model_providers/gitee_ai/text_embedding/bge-m3.yaml
View File

@ -1,8 +0,0 @@
model: bge-m3
label:
zh_Hans: bge-m3
en_US: bge-m3
model_type: text-embedding
model_properties:
context_size: 200000
max_chunks: 20

8
api/core/model_runtime/model_providers/gitee_ai/text_embedding/bge-small-zh-v1.5.yaml
View File

@ -1,8 +0,0 @@
model: bge-small-zh-v1.5
label:
zh_Hans: bge-small-zh-v1.5
en_US: bge-small-zh-v1.5
model_type: text-embedding
model_properties:
context_size: 200000
max_chunks: 20

31
api/core/model_runtime/model_providers/gitee_ai/text_embedding/text_embedding.py
View File

@ -1,31 +0,0 @@
from typing import Optional
from core.entities.embedding_type import EmbeddingInputType
from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
from core.model_runtime.model_providers.openai_api_compatible.text_embedding.text_embedding import (
OAICompatEmbeddingModel,
)
class GiteeAIEmbeddingModel(OAICompatEmbeddingModel):
def _invoke(
self,
model: str,
credentials: dict,
texts: list[str],
user: Optional[str] = None,
input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
) -> TextEmbeddingResult:
self._add_custom_parameters(credentials, model)
return super()._invoke(model, credentials, texts, user, input_type)
def validate_credentials(self, model: str, credentials: dict) -> None:
self._add_custom_parameters(credentials, None)
super().validate_credentials(model, credentials)
@staticmethod
def _add_custom_parameters(credentials: dict, model: str) -> None:
if model is None:
model = "bge-m3"
credentials["endpoint_url"] = f"https://ai.gitee.com/api/serverless/{model}/v1/"

11
api/core/model_runtime/model_providers/gitee_ai/tts/ChatTTS.yaml
View File

@ -1,11 +0,0 @@
model: ChatTTS
model_type: tts
model_properties:
default_voice: 'default'
voices:
- mode: 'default'
name: 'Default'
language: [ 'zh-Hans', 'en-US', 'de-DE', 'fr-FR', 'es-ES', 'it-IT', 'th-TH', 'id-ID' ]
word_limit: 3500
audio_type: 'mp3'
max_workers: 5

11
api/core/model_runtime/model_providers/gitee_ai/tts/FunAudioLLM-CosyVoice-300M.yaml
View File

@ -1,11 +0,0 @@
model: FunAudioLLM-CosyVoice-300M
model_type: tts
model_properties:
default_voice: 'default'
voices:
- mode: 'default'
name: 'Default'
language: [ 'zh-Hans', 'en-US', 'de-DE', 'fr-FR', 'es-ES', 'it-IT', 'th-TH', 'id-ID' ]
word_limit: 3500
audio_type: 'mp3'
max_workers: 5

0
api/core/model_runtime/model_providers/gitee_ai/tts/__init__.py
View File

4
api/core/model_runtime/model_providers/gitee_ai/tts/_position.yaml
View File

@ -1,4 +0,0 @@
- speecht5_tts
- ChatTTS
- fish-speech-1.2-sft
- FunAudioLLM-CosyVoice-300M

11
api/core/model_runtime/model_providers/gitee_ai/tts/fish-speech-1.2-sft.yaml
View File

@ -1,11 +0,0 @@
model: fish-speech-1.2-sft
model_type: tts
model_properties:
default_voice: 'default'
voices:
- mode: 'default'
name: 'Default'
language: [ 'zh-Hans', 'en-US', 'de-DE', 'fr-FR', 'es-ES', 'it-IT', 'th-TH', 'id-ID' ]
word_limit: 3500
audio_type: 'mp3'
max_workers: 5

11
api/core/model_runtime/model_providers/gitee_ai/tts/speecht5_tts.yaml
View File

@ -1,11 +0,0 @@
model: speecht5_tts
model_type: tts
model_properties:
default_voice: 'default'
voices:
- mode: 'default'
name: 'Default'
language: [ 'zh-Hans', 'en-US', 'de-DE', 'fr-FR', 'es-ES', 'it-IT', 'th-TH', 'id-ID' ]
word_limit: 3500
audio_type: 'mp3'
max_workers: 5

79
api/core/model_runtime/model_providers/gitee_ai/tts/tts.py
View File

@ -1,79 +0,0 @@
from typing import Optional
import requests
from core.model_runtime.errors.invoke import InvokeBadRequestError
from core.model_runtime.errors.validate import CredentialsValidateFailedError
from core.model_runtime.model_providers.__base.tts_model import TTSModel
from core.model_runtime.model_providers.gitee_ai._common import _CommonGiteeAI
class GiteeAIText2SpeechModel(_CommonGiteeAI, TTSModel):
"""
Model class for OpenAI Speech to text model.
"""
def _invoke(
self, model: str, tenant_id: str, credentials: dict, content_text: str, voice: str, user: Optional[str] = None
) -> any:
"""
_invoke text2speech model
:param model: model name
:param tenant_id: user tenant id
:param credentials: model credentials
:param content_text: text content to be translated
:param voice: model timbre
:param user: unique user id
:return: text translated to audio file
"""
return self._tts_invoke_streaming(model=model, credentials=credentials, content_text=content_text, voice=voice)
def validate_credentials(self, model: str, credentials: dict) -> None:
"""
validate credentials text2speech model
:param model: model name
:param credentials: model credentials
:return: text translated to audio file
"""
try:
self._tts_invoke_streaming(
model=model,
credentials=credentials,
content_text="Hello Dify!",
voice=self._get_model_default_voice(model, credentials),
)
except Exception as ex:
raise CredentialsValidateFailedError(str(ex))
def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> any:
"""
_tts_invoke_streaming text2speech model
:param model: model name
:param credentials: model credentials
:param content_text: text content to be translated
:param voice: model timbre
:return: text translated to audio file
"""
try:
# doc: https://ai.gitee.com/docs/openapi/serverless#tag/serverless/POST/{service}/text-to-speech
endpoint_url = "https://ai.gitee.com/api/serverless/" + model + "/text-to-speech"
headers = {"Content-Type": "application/json"}
api_key = credentials.get("api_key")
if api_key:
headers["Authorization"] = f"Bearer {api_key}"
payload = {"inputs": content_text}
response = requests.post(endpoint_url, headers=headers, json=payload)
if response.status_code != 200:
raise InvokeBadRequestError(response.text)
data = response.content
for i in range(0, len(data), 1024):
yield data[i : i + 1024]
except Exception as ex:
raise InvokeBadRequestError(str(ex))

BIN
api/core/model_runtime/model_providers/gpustack/_assets/icon_l_en.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 277 KiB

15
api/core/model_runtime/model_providers/gpustack/_assets/icon_l_en.svg
View File

@ -1,15 +0,0 @@
<svg width="68" height="24" viewBox="0 0 68 24" fill="none" xmlns="http://www.w3.org/2000/svg">
<g id="Gemini">
<path id="Union" fill-rule="evenodd" clip-rule="evenodd" d="M50.6875 4.37014C48.3498 4.59292 46.5349 6.41319 46.3337 8.72764C46.1446 6.44662 44.2677 4.56074 41.9805 4.3737C44.2762 4.1997 46.152 2.28299 46.3373 0C46.4882 2.28911 48.405 4.20047 50.6875 4.37014ZM15.4567 9.41141L13.9579 10.9076C9.92941 6.64892 2.69298 9.97287 3.17317 15.8112C3.22394 23.108 14.5012 24.4317 15.3628 16.8809H9.52096L9.50061 14.9149H17.3595C18.8163 23.1364 8.44367 27.0292 3.19453 21.238C0.847044 18.7556 0.363651 14.7682 1.83717 11.7212C4.1129 6.62089 11.6505 5.29845 15.4567 9.41141ZM45.5915 23.5989H47.6945C47.6944 22.9155 47.6945 22.2307 47.6946 21.5452V21.5325C47.6948 19.8907 47.695 18.2453 47.6924 16.6072C47.6914 15.9407 47.6161 15.2823 47.4024 14.647C46.4188 11.2828 41.4255 11.4067 39.8332 14.214C38.5637 11.4171 34.4009 11.5236 32.8538 14.0084L32.8082 13.9976V12.4806L32.4233 12.4804H32.4224C31.8687 12.4801 31.3324 12.4798 30.7949 12.4811V23.5848L32.8977 23.5672C32.8981 22.9411 32.8979 22.3122 32.8977 21.6822V21.6812V21.6802V21.6791V21.6781V21.6771V21.676V21.676V21.6759V21.6758V21.6757V21.6757V21.6756C32.8973 20.204 32.8969 18.7261 32.904 17.2614C32.8889 15.3646 34.5674 13.5687 36.5358 14.124C37.7794 14.3298 38.1851 15.6148 38.1761 16.7257C38.1821 17.7019 38.18 18.6824 38.178 19.6633V19.6638C38.1752 20.9756 38.1724 22.2881 38.1891 23.5919L40.2846 23.5731C40.2929 22.7511 40.2881 21.9245 40.2832 21.0966C40.2753 19.7402 40.2674 18.3805 40.317 17.0328C40.4418 15.2122 42.0141 13.6186 43.9064 14.1168C45.2685 14.3231 45.6136 15.7748 45.5882 16.9545C45.5938 18.4959 45.5929 20.0492 45.5921 21.5968V21.5991V21.6014V21.6037V21.606V21.6083V21.6106C45.5917 22.2749 45.5913 22.9382 45.5915 23.5989ZM20.6167 18.4408C20.5625 21.9486 25.2121 23.6996 27.2993 20.0558L29.1566 20.9592C27.8157 23.7067 24.2337 24.7424 21.5381 23.4213C18.0052 21.7253 17.41 16.5007 20.0334 13.7517C21.4609 12.1752 23.7291 11.7901 25.7206 12.3653C28.3408 13.1257 29.4974 15.8937 29.326 18.4399C27.5547 18.4415 25.7971 18.4412 24.0364 18.4409C22.8993 18.4407 21.7609 18.4405 20.6167 18.4408ZM27.1041 16.6957C26.7048 13.1033 21.2867 13.2256 20.7494 16.6957H27.1041ZM53.543 23.5999H55.6206L55.6206 22.4361C55.6205 20.7877 55.6205 19.1443 55.6207 17.4939C55.6208 16.8853 55.7234 16.297 56.0063 15.7531C56.6115 14.3862 58.1745 13.7002 59.5927 14.1774C60.7512 14.4455 61.2852 15.6069 61.2762 16.7154C61.2774 18.3497 61.2771 19.9826 61.2769 21.6162V21.6166V21.617V21.6174V21.6179L61.2766 23.6007H63.3698C63.3913 22.0924 63.3869 20.584 63.3826 19.0755V19.0754V19.0753V19.0753V19.0752C63.3799 18.1682 63.3773 17.2612 63.3803 16.3541C63.3796 15.8622 63.3103 15.3765 63.1698 14.9052C62.3248 11.5142 57.3558 11.2385 55.5828 14.0038L55.5336 13.9905V12.4917H53.539C53.4898 12.7313 53.4934 23.4113 53.543 23.5999ZM49.6211 12.4944H51.7065V23.5994H49.6211V12.4944ZM65.1035 23.5991H67.1831C67.2367 23.2198 67.2133 12.6566 67.1634 12.4983H65.1035V23.5991ZM52.1504 8.67829C52.1709 10.4847 49.2418 10.7058 49.1816 8.65714C49.2189 6.5948 52.2437 6.81331 52.1504 8.67829ZM66.1387 10.1324C64.2712 10.1609 64.1316 7.19881 66.1559 7.17114C68.1709 7.19817 68.0215 10.2087 66.1387 10.1324Z" fill="url(#paint0_linear_14286_118464)"/>
</g>
<defs>
<linearGradient id="paint0_linear_14286_118464" x1="-2" y1="0.999998" x2="67.9999" y2="27.5002" gradientUnits="userSpaceOnUse">
<stop stop-color="#7798E0"/>
<stop offset="0.210002" stop-color="#086FFF"/>
<stop offset="0.345945" stop-color="#086FFF"/>
<stop offset="0.591777" stop-color="#479AFF"/>
<stop offset="0.895892" stop-color="#B7C4FA"/>
<stop offset="1" stop-color="#B5C5F9"/>
</linearGradient>
</defs>
</svg>
Side by Side

Before

Width:  |  Height:  |  Size: 3.6 KiB

BIN
api/core/model_runtime/model_providers/gpustack/_assets/icon_s_en.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 57 KiB

11
api/core/model_runtime/model_providers/gpustack/_assets/icon_s_en.svg
View File

@ -1,11 +0,0 @@
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
<rect width="24" height="24" rx="6" fill="url(#paint0_linear_7301_16076)"/>
<path d="M20 12.0116C15.7043 12.42 12.3692 15.757 11.9995 20C11.652 15.8183 8.20301 12.361 4 12.0181C8.21855 11.6991 11.6656 8.1853 12.006 4C12.2833 8.19653 15.8057 11.7005 20 12.0116Z" fill="white" fill-opacity="0.88"/>
<defs>
<linearGradient id="paint0_linear_7301_16076" x1="-9" y1="29.5" x2="19.4387" y2="1.43791" gradientUnits="userSpaceOnUse">
<stop offset="0.192878" stop-color="#1C7DFF"/>
<stop offset="0.520213" stop-color="#1C69FF"/>
<stop offset="1" stop-color="#F0DCD6"/>
</linearGradient>
</defs>
</svg>
Side by Side

Before

Width:  |  Height:  |  Size: 689 B

10
api/core/model_runtime/model_providers/gpustack/gpustack.py
View File

@ -1,10 +0,0 @@
import logging
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
logger = logging.getLogger(__name__)
class GPUStackProvider(ModelProvider):
def validate_provider_credentials(self, credentials: dict) -> None:
pass

120
api/core/model_runtime/model_providers/gpustack/gpustack.yaml
View File

@ -1,120 +0,0 @@
provider: gpustack
label:
en_US: GPUStack
icon_small:
en_US: icon_s_en.png
icon_large:
en_US: icon_l_en.png
supported_model_types:
- llm
- text-embedding
- rerank
configurate_methods:
- customizable-model
model_credential_schema:
model:
label:
en_US: Model Name
zh_Hans: 模型名称
placeholder:
en_US: Enter your model name
zh_Hans: 输入模型名称
credential_form_schemas:
- variable: endpoint_url
label:
zh_Hans: 服务器地址
en_US: Server URL
type: text-input
required: true
placeholder:
zh_Hans: 输入 GPUStack 的服务器地址，如 http://192.168.1.100
en_US: Enter the GPUStack server URL, e.g. http://192.168.1.100
- variable: api_key
label:
en_US: API Key
type: secret-input
required: true
placeholder:
zh_Hans: 输入您的 API Key
en_US: Enter your API Key
- variable: mode
show_on:
- variable: __model_type
value: llm
label:
en_US: Completion mode
type: select
required: false
default: chat
placeholder:
zh_Hans: 选择补全类型
en_US: Select completion type
options:
- value: completion
label:
en_US: Completion
zh_Hans: 补全
- value: chat
label:
en_US: Chat
zh_Hans: 对话
- variable: context_size
label:
zh_Hans: 模型上下文长度
en_US: Model context size
required: true
type: text-input
default: "8192"
placeholder:
zh_Hans: 输入您的模型上下文长度
en_US: Enter your Model context size
- variable: max_tokens_to_sample
label:
zh_Hans: 最大 token 上限
en_US: Upper bound for max tokens
show_on:
- variable: __model_type
value: llm
default: "8192"
type: text-input
- variable: function_calling_type
show_on:
- variable: __model_type
value: llm
label:
en_US: Function calling
type: select
required: false
default: no_call
options:
- value: function_call
label:
en_US: Function Call
zh_Hans: Function Call
- value: tool_call
label:
en_US: Tool Call
zh_Hans: Tool Call
- value: no_call
label:
en_US: Not Support
zh_Hans: 不支持
- variable: vision_support
show_on:
- variable: __model_type
value: llm
label:
zh_Hans: Vision 支持
en_US: Vision Support
type: select
required: false
default: no_support
options:
- value: support
label:
en_US: Support
zh_Hans: 支持
- value: no_support
label:
en_US: Not Support
zh_Hans: 不支持

0
api/core/model_runtime/model_providers/gpustack/llm/__init__.py
View File

45
api/core/model_runtime/model_providers/gpustack/llm/llm.py
View File

@ -1,45 +0,0 @@
from collections.abc import Generator
from yarl import URL
from core.model_runtime.entities.llm_entities import LLMResult
from core.model_runtime.entities.message_entities import (
PromptMessage,
PromptMessageTool,
)
from core.model_runtime.model_providers.openai_api_compatible.llm.llm import (
OAIAPICompatLargeLanguageModel,
)
class GPUStackLanguageModel(OAIAPICompatLargeLanguageModel):
def _invoke(
self,
model: str,
credentials: dict,
prompt_messages: list[PromptMessage],
model_parameters: dict,
tools: list[PromptMessageTool] | None = None,
stop: list[str] | None = None,
stream: bool = True,
user: str | None = None,
) -> LLMResult | Generator:
return super()._invoke(
model,
credentials,
prompt_messages,
model_parameters,
tools,
stop,
stream,
user,
)
def validate_credentials(self, model: str, credentials: dict) -> None:
self._add_custom_parameters(credentials)
super().validate_credentials(model, credentials)
@staticmethod
def _add_custom_parameters(credentials: dict) -> None:
credentials["endpoint_url"] = str(URL(credentials["endpoint_url"]) / "v1-openai")
credentials["mode"] = "chat"

0
api/core/model_runtime/model_providers/gpustack/rerank/__init__.py
View File

146
api/core/model_runtime/model_providers/gpustack/rerank/rerank.py
View File

@ -1,146 +0,0 @@
from json import dumps
from typing import Optional
import httpx
from requests import post
from yarl import URL
from core.model_runtime.entities.common_entities import I18nObject
from core.model_runtime.entities.model_entities import (
AIModelEntity,
FetchFrom,
ModelPropertyKey,
ModelType,
)
from core.model_runtime.entities.rerank_entities import RerankDocument, RerankResult
from core.model_runtime.errors.invoke import (
InvokeAuthorizationError,
InvokeBadRequestError,
InvokeConnectionError,
InvokeError,
InvokeRateLimitError,
InvokeServerUnavailableError,
)
from core.model_runtime.errors.validate import CredentialsValidateFailedError
from core.model_runtime.model_providers.__base.rerank_model import RerankModel
class GPUStackRerankModel(RerankModel):
"""
Model class for GPUStack rerank model.
"""
def _invoke(
self,
model: str,
credentials: dict,
query: str,
docs: list[str],
score_threshold: Optional[float] = None,
top_n: Optional[int] = None,
user: Optional[str] = None,
) -> RerankResult:
"""
Invoke rerank model
:param model: model name
:param credentials: model credentials
:param query: search query
:param docs: docs for reranking
:param score_threshold: score threshold
:param top_n: top n documents to return
:param user: unique user id
:return: rerank result
"""
if len(docs) == 0:
return RerankResult(model=model, docs=[])
endpoint_url = credentials["endpoint_url"]
headers = {
"Authorization": f"Bearer {credentials.get('api_key')}",
"Content-Type": "application/json",
}
data = {"model": model, "query": query, "documents": docs, "top_n": top_n}
try:
response = post(
str(URL(endpoint_url) / "v1" / "rerank"),
headers=headers,
data=dumps(data),
timeout=10,
)
response.raise_for_status()
results = response.json()
rerank_documents = []
for result in results["results"]:
index = result["index"]
if "document" in result:
text = result["document"]["text"]
else:
text = docs[index]
rerank_document = RerankDocument(
index=index,
text=text,
score=result["relevance_score"],
)
if score_threshold is None or result["relevance_score"] >= score_threshold:
rerank_documents.append(rerank_document)
return RerankResult(model=model, docs=rerank_documents)
except httpx.HTTPStatusError as e:
raise InvokeServerUnavailableError(str(e))
def validate_credentials(self, model: str, credentials: dict) -> None:
"""
Validate model credentials
:param model: model name
:param credentials: model credentials
:return:
"""
try:
self._invoke(
model=model,
credentials=credentials,
query="What is the capital of the United States?",
docs=[
"Carson City is the capital city of the American state of Nevada. At the 2010 United States "
"Census, Carson City had a population of 55,274.",
"The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean that "
"are a political division controlled by the United States. Its capital is Saipan.",
],
score_threshold=0.8,
)
except Exception as ex:
raise CredentialsValidateFailedError(str(ex))
@property
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
"""
Map model invoke error to unified error
"""
return {
InvokeConnectionError: [httpx.ConnectError],
InvokeServerUnavailableError: [httpx.RemoteProtocolError],
InvokeRateLimitError: [],
InvokeAuthorizationError: [httpx.HTTPStatusError],
InvokeBadRequestError: [httpx.RequestError],
}
def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
"""
generate custom model entities from credentials
"""
entity = AIModelEntity(
model=model,
label=I18nObject(en_US=model),
model_type=ModelType.RERANK,
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
)
return entity

0
api/core/model_runtime/model_providers/gpustack/text_embedding/__init__.py
View File

35
api/core/model_runtime/model_providers/gpustack/text_embedding/text_embedding.py
View File

@ -1,35 +0,0 @@
from typing import Optional
from yarl import URL
from core.entities.embedding_type import EmbeddingInputType
from core.model_runtime.entities.text_embedding_entities import (
TextEmbeddingResult,
)
from core.model_runtime.model_providers.openai_api_compatible.text_embedding.text_embedding import (
OAICompatEmbeddingModel,
)
class GPUStackTextEmbeddingModel(OAICompatEmbeddingModel):
"""
Model class for GPUStack text embedding model.
"""
def _invoke(
self,
model: str,
credentials: dict,
texts: list[str],
user: Optional[str] = None,
input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
) -> TextEmbeddingResult:
return super()._invoke(model, credentials, texts, user, input_type)
def validate_credentials(self, model: str, credentials: dict) -> None:
self._add_custom_parameters(credentials)
super().validate_credentials(model, credentials)
@staticmethod
def _add_custom_parameters(credentials: dict) -> None:
credentials["endpoint_url"] = str(URL(credentials["endpoint_url"]) / "v1-openai")

55
api/core/model_runtime/model_providers/vertex_ai/llm/anthropic.claude-3.5-sonnet-v2.yaml
View File

@ -1,55 +0,0 @@
model: claude-3-5-sonnet-v2@20241022
label:
en_US: Claude 3.5 Sonnet v2
model_type: llm
features:
- agent-thought
- vision
model_properties:
mode: chat
context_size: 200000
parameter_rules:
- name: max_tokens
use_template: max_tokens
required: true
type: int
default: 8192
min: 1
max: 8192
help:
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
- name: temperature
use_template: temperature
required: false
type: float
default: 1
min: 0.0
max: 1.0
help:
zh_Hans: 生成内容的随机性。
en_US: The amount of randomness injected into the response.
- name: top_p
required: false
type: float
default: 0.999
min: 0.000
max: 1.000
help:
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
- name: top_k
required: false
type: int
default: 0
min: 0
# tip docs from aws has error, max value is 500
max: 500
help:
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
pricing:
input: '0.003'
output: '0.015'
unit: '0.001'
currency: USD

0
api/core/model_runtime/model_providers/vessl_ai/__init__.py
View File

BIN
api/core/model_runtime/model_providers/vessl_ai/_assets/icon_l_en.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 11 KiB

3
api/core/model_runtime/model_providers/vessl_ai/_assets/icon_s_en.svg
View File

@ -1,3 +0,0 @@
<svg width="1200" height="925" viewBox="0 0 1200 925" fill="none" xmlns="http://www.w3.org/2000/svg">
<path d="M780.152 250.999L907.882 462.174C907.882 462.174 880.925 510.854 867.43 535.21C834.845 594.039 764.171 612.49 710.442 508.333L420.376 0H0L459.926 803.307C552.303 964.663 787.366 964.663 879.743 803.307C989.874 610.952 1089.87 441.97 1200 249.646L1052.28 0H639.519L780.152 250.999Z" fill="#3366FF"/>
</svg>
Side by Side

Before

Width:  |  Height:  |  Size: 417 B

0
api/core/model_runtime/model_providers/vessl_ai/llm/__init__.py
View File

83
api/core/model_runtime/model_providers/vessl_ai/llm/llm.py
View File

@ -1,83 +0,0 @@
from decimal import Decimal
from core.model_runtime.entities.common_entities import I18nObject
from core.model_runtime.entities.llm_entities import LLMMode
from core.model_runtime.entities.model_entities import (
AIModelEntity,
DefaultParameterName,
FetchFrom,
ModelPropertyKey,
ModelType,
ParameterRule,
ParameterType,
PriceConfig,
)
from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
class VesslAILargeLanguageModel(OAIAPICompatLargeLanguageModel):
def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
features = []
entity = AIModelEntity(
model=model,
label=I18nObject(en_US=model),
model_type=ModelType.LLM,
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
features=features,
model_properties={
ModelPropertyKey.MODE: credentials.get("mode"),
},
parameter_rules=[
ParameterRule(
name=DefaultParameterName.TEMPERATURE.value,
label=I18nObject(en_US="Temperature"),
type=ParameterType.FLOAT,
default=float(credentials.get("temperature", 0.7)),
min=0,
max=2,
precision=2,
),
ParameterRule(
name=DefaultParameterName.TOP_P.value,
label=I18nObject(en_US="Top P"),
type=ParameterType.FLOAT,
default=float(credentials.get("top_p", 1)),
min=0,
max=1,
precision=2,
),
ParameterRule(
name=DefaultParameterName.TOP_K.value,
label=I18nObject(en_US="Top K"),
type=ParameterType.INT,
default=int(credentials.get("top_k", 50)),
min=-2147483647,
max=2147483647,
precision=0,
),
ParameterRule(
name=DefaultParameterName.MAX_TOKENS.value,
label=I18nObject(en_US="Max Tokens"),
type=ParameterType.INT,
default=512,
min=1,
max=int(credentials.get("max_tokens_to_sample", 4096)),
),
],
pricing=PriceConfig(
input=Decimal(credentials.get("input_price", 0)),
output=Decimal(credentials.get("output_price", 0)),
unit=Decimal(credentials.get("unit", 0)),
currency=credentials.get("currency", "USD"),
),
)
if credentials["mode"] == "chat":
entity.model_properties[ModelPropertyKey.MODE] = LLMMode.CHAT.value
elif credentials["mode"] == "completion":
entity.model_properties[ModelPropertyKey.MODE] = LLMMode.COMPLETION.value
else:
raise ValueError(f"Unknown completion type {credentials['completion_type']}")
return entity

10
api/core/model_runtime/model_providers/vessl_ai/vessl_ai.py
View File

@ -1,10 +0,0 @@
import logging
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
logger = logging.getLogger(__name__)
class VesslAIProvider(ModelProvider):
def validate_provider_credentials(self, credentials: dict) -> None:
pass

56
api/core/model_runtime/model_providers/vessl_ai/vessl_ai.yaml
View File

@ -1,56 +0,0 @@
provider: vessl_ai
label:
en_US: VESSL AI
icon_small:
en_US: icon_s_en.svg
icon_large:
en_US: icon_l_en.png
background: "#F1EFED"
help:
title:
en_US: How to deploy VESSL AI LLM Model Endpoint
url:
en_US: https://docs.vessl.ai/guides/get-started/llama3-deployment
supported_model_types:
- llm
configurate_methods:
- customizable-model
model_credential_schema:
model:
label:
en_US: Model Name
placeholder:
en_US: Enter model name
credential_form_schemas:
- variable: endpoint_url
label:
en_US: Endpoint Url
type: text-input
required: true
placeholder:
en_US: Enter VESSL AI service endpoint url
- variable: api_key
required: true
label:
en_US: API Key
type: secret-input
placeholder:
en_US: Enter VESSL AI secret key
- variable: mode
show_on:
- variable: __model_type
value: llm
label:
en_US: Completion Mode
type: select
required: false
default: chat
placeholder:
en_US: Select completion mode
options:
- value: completion
label:
en_US: Completion
- value: chat
label:
en_US: Chat

0
api/core/model_runtime/model_providers/x/__init__.py
View File

1
api/core/model_runtime/model_providers/x/_assets/x-ai-logo.svg
View File

@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" fill="currentColor" viewBox="0 0 24 24" aria-hidden="true" class="" focusable="false" style="fill:currentColor;height:28px;width:28px"><path d="m3.005 8.858 8.783 12.544h3.904L6.908 8.858zM6.905 15.825 3 21.402h3.907l1.951-2.788zM16.585 2l-6.75 9.64 1.953 2.79L20.492 2zM17.292 7.965v13.437h3.2V3.395z"></path></svg>
Side by Side

Before

Width:  |  Height:  |  Size: 356 B

0
api/core/model_runtime/model_providers/x/llm/__init__.py
View File

63
api/core/model_runtime/model_providers/x/llm/grok-beta.yaml
View File

@ -1,63 +0,0 @@
model: grok-beta
label:
en_US: Grok beta
model_type: llm
features:
- multi-tool-call
model_properties:
mode: chat
context_size: 131072
parameter_rules:
- name: temperature
label:
en_US: "Temperature"
zh_Hans: "采样温度"
type: float
default: 0.7
min: 0.0
max: 2.0
precision: 1
required: true
help:
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: top_p
label:
en_US: "Top P"
zh_Hans: "Top P"
type: float
default: 0.7
min: 0.0
max: 1.0
precision: 1
required: true
help:
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
- name: frequency_penalty
use_template: frequency_penalty
label:
en_US: "Frequency Penalty"
zh_Hans: "频率惩罚"
type: float
default: 0
min: 0
max: 2.0
precision: 1
required: false
help:
en_US: "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim."
zh_Hans: "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
- name: user
use_template: text
label:
en_US: "User"
zh_Hans: "用户"
type: string
required: false
help:
en_US: "Used to track and differentiate conversation requests from different users."
zh_Hans: "用于追踪和区分不同用户的对话请求。"

37
api/core/model_runtime/model_providers/x/llm/llm.py
View File

@ -1,37 +0,0 @@
from collections.abc import Generator
from typing import Optional, Union
from yarl import URL
from core.model_runtime.entities.llm_entities import LLMMode, LLMResult
from core.model_runtime.entities.message_entities import (
PromptMessage,
PromptMessageTool,
)
from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
class XAILargeLanguageModel(OAIAPICompatLargeLanguageModel):
def _invoke(
self,
model: str,
credentials: dict,
prompt_messages: list[PromptMessage],
model_parameters: dict,
tools: Optional[list[PromptMessageTool]] = None,
stop: Optional[list[str]] = None,
stream: bool = True,
user: Optional[str] = None,
) -> Union[LLMResult, Generator]:
self._add_custom_parameters(credentials)
return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream)
def validate_credentials(self, model: str, credentials: dict) -> None:
self._add_custom_parameters(credentials)
super().validate_credentials(model, credentials)
@staticmethod
def _add_custom_parameters(credentials) -> None:
credentials["endpoint_url"] = str(URL(credentials["endpoint_url"])) or "https://api.x.ai/v1"
credentials["mode"] = LLMMode.CHAT.value
credentials["function_calling_type"] = "tool_call"

25
api/core/model_runtime/model_providers/x/x.py
View File

@ -1,25 +0,0 @@
import logging
from core.model_runtime.entities.model_entities import ModelType
from core.model_runtime.errors.validate import CredentialsValidateFailedError
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
logger = logging.getLogger(__name__)
class XAIProvider(ModelProvider):
def validate_provider_credentials(self, credentials: dict) -> None:
"""
Validate provider credentials
if validate failed, raise exception
:param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
"""
try:
model_instance = self.get_model_instance(ModelType.LLM)
model_instance.validate_credentials(model="grok-beta", credentials=credentials)
except CredentialsValidateFailedError as ex:
raise ex
except Exception as ex:
logger.exception(f"{self.get_provider_schema().provider} credentials validate failed")
raise ex

38
api/core/model_runtime/model_providers/x/x.yaml
View File

@ -1,38 +0,0 @@
provider: x
label:
en_US: xAI
description:
en_US: xAI is a company working on building artificial intelligence to accelerate human scientific discovery. We are guided by our mission to advance our collective understanding of the universe.
icon_small:
en_US: x-ai-logo.svg
icon_large:
en_US: x-ai-logo.svg
help:
title:
en_US: Get your token from xAI
zh_Hans: 从 xAI 获取 token
url:
en_US: https://x.ai/api
supported_model_types:
- llm
configurate_methods:
- predefined-model
provider_credential_schema:
credential_form_schemas:
- variable: api_key
label:
en_US: API Key
type: secret-input
required: true
placeholder:
zh_Hans: 在此输入您的 API Key
en_US: Enter your API Key
- variable: endpoint_url
label:
en_US: API Base
type: text-input
required: false
default: https://api.x.ai/v1
placeholder:
zh_Hans: 在此输入您的 API Base
en_US: Enter your API Base

7
api/core/moderation/keywords/keywords.py
View File

@ -1,3 +1,6 @@
from collections.abc import Sequence
from typing import Any
from core.moderation.base import Moderation, ModerationAction, ModerationInputsResult, ModerationOutputsResult
@ -62,5 +65,5 @@ class KeywordsModeration(Moderation):
def _is_violated(self, inputs: dict, keywords_list: list) -> bool:
return any(self._check_keywords_in_value(keywords_list, value) for value in inputs.values())
def _check_keywords_in_value(self, keywords_list, value) -> bool:
return any(keyword.lower() in value.lower() for keyword in keywords_list)
def _check_keywords_in_value(self, keywords_list: Sequence[str], value: Any) -> bool:
return any(keyword.lower() in str(value).lower() for keyword in keywords_list)

2
api/core/moderation/output_moderation.py
View File

@ -126,6 +126,6 @@ class OutputModeration(BaseModel):
result: ModerationOutputsResult = moderation_factory.moderation_for_outputs(moderation_buffer)
return result
except Exception as e:
logger.exception("Moderation Output error: %s", e)
logger.exception(f"Moderation Output error, app_id: {app_id}")
return None

1
api/core/ops/langsmith_trace/entities/langsmith_trace_entity.py
View File

@ -49,6 +49,7 @@ class LangSmithRunModel(LangSmithTokenUsage, LangSmithMultiModel):
reference_example_id: Optional[str] = Field(None, description="Reference example ID associated with the run")
input_attachments: Optional[dict[str, Any]] = Field(None, description="Input attachments of the run")
output_attachments: Optional[dict[str, Any]] = Field(None, description="Output attachments of the run")
dotted_order: Optional[str] = Field(None, description="Dotted order of the run")
@field_validator("inputs", "outputs")
@classmethod

Some files were not shown because too many files have changed in this diff Show More