admin/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat: add zhipuai (#1188)

Browse Source
This commit is contained in:
takatost
2023-09-18 17:32:31 +08:00
committed by GitHub
parent c8bd76cd66
commit 827c97f0d3
36 changed files with 1087 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
api/core/model_providers/providers/anthropic_provider.py
View File

@@ -69,11 +69,11 @@ class AnthropicProvider(BaseModelProvider):
:return:
"""
return ModelKwargsRules(
temperature=KwargRule[float](min=0, max=1, default=1),
top_p=KwargRule[float](min=0, max=1, default=0.7),
temperature=KwargRule[float](min=0, max=1, default=1, precision=2),
top_p=KwargRule[float](min=0, max=1, default=0.7, precision=2),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](alias="max_tokens_to_sample", min=10, max=100000, default=256),
max_tokens=KwargRule[int](alias="max_tokens_to_sample", min=10, max=100000, default=256, precision=0),
)
@classmethod

10
api/core/model_providers/providers/azure_openai_provider.py
View File

@@ -164,14 +164,14 @@ class AzureOpenAIProvider(BaseModelProvider):
model_credentials = self.get_model_credentials(model_name, model_type)
return ModelKwargsRules(
temperature=KwargRule[float](min=0, max=2, default=1),
top_p=KwargRule[float](min=0, max=1, default=1),
presence_penalty=KwargRule[float](min=-2, max=2, default=0),
frequency_penalty=KwargRule[float](min=-2, max=2, default=0),
temperature=KwargRule[float](min=0, max=2, default=1, precision=2),
top_p=KwargRule[float](min=0, max=1, default=1, precision=2),
presence_penalty=KwargRule[float](min=-2, max=2, default=0, precision=2),
frequency_penalty=KwargRule[float](min=-2, max=2, default=0, precision=2),
max_tokens=KwargRule[int](min=10, max=base_model_max_tokens.get(
model_credentials['base_model_name'],
4097
), default=16),
), default=16, precision=0),
)
@classmethod

6
api/core/model_providers/providers/chatglm_provider.py
View File

@@ -64,11 +64,11 @@ class ChatGLMProvider(BaseModelProvider):
}
return ModelKwargsRules(
temperature=KwargRule[float](min=0, max=2, default=1),
top_p=KwargRule[float](min=0, max=1, default=0.7),
temperature=KwargRule[float](min=0, max=2, default=1, precision=2),
top_p=KwargRule[float](min=0, max=1, default=0.7, precision=2),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](alias='max_token', min=10, max=model_max_tokens.get(model_name), default=2048),
max_tokens=KwargRule[int](alias='max_token', min=10, max=model_max_tokens.get(model_name), default=2048, precision=0),
)
@classmethod

18
api/core/model_providers/providers/hosted.py
View File

@@ -45,6 +45,18 @@ class HostedModelProviders(BaseModel):
hosted_model_providers = HostedModelProviders()
class HostedModerationConfig(BaseModel):
enabled: bool = False
providers: list[str] = []
class HostedConfig(BaseModel):
moderation = HostedModerationConfig()
hosted_config = HostedConfig()
def init_app(app: Flask):
if os.environ.get("DEBUG") and os.environ.get("DEBUG").lower() == 'true':
langchain.verbose = True
@@ -78,3 +90,9 @@ def init_app(app: Flask):
paid_min_quantity=app.config.get("HOSTED_ANTHROPIC_PAID_MIN_QUANTITY"),
paid_max_quantity=app.config.get("HOSTED_ANTHROPIC_PAID_MAX_QUANTITY"),
)
if app.config.get("HOSTED_MODERATION_ENABLED") and app.config.get("HOSTED_MODERATION_PROVIDERS"):
hosted_config.moderation = HostedModerationConfig(
enabled=app.config.get("HOSTED_MODERATION_ENABLED"),
providers=app.config.get("HOSTED_MODERATION_PROVIDERS").split(',')
)

6
api/core/model_providers/providers/huggingface_hub_provider.py
View File

@@ -47,11 +47,11 @@ class HuggingfaceHubProvider(BaseModelProvider):
:return:
"""
return ModelKwargsRules(
temperature=KwargRule[float](min=0, max=2, default=1),
top_p=KwargRule[float](min=0.01, max=0.99, default=0.7),
temperature=KwargRule[float](min=0, max=2, default=1, precision=2),
top_p=KwargRule[float](min=0.01, max=0.99, default=0.7, precision=2),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](alias='max_new_tokens', min=10, max=4000, default=200),
max_tokens=KwargRule[int](alias='max_new_tokens', min=10, max=4000, default=200, precision=0),
)
@classmethod

6
api/core/model_providers/providers/localai_provider.py
View File

@@ -52,9 +52,9 @@ class LocalAIProvider(BaseModelProvider):
:return:
"""
return ModelKwargsRules(
temperature=KwargRule[float](min=0, max=2, default=0.7),
top_p=KwargRule[float](min=0, max=1, default=1),
max_tokens=KwargRule[int](min=10, max=4097, default=16),
temperature=KwargRule[float](min=0, max=2, default=0.7, precision=2),
top_p=KwargRule[float](min=0, max=1, default=1, precision=2),
max_tokens=KwargRule[int](min=10, max=4097, default=16, precision=0),
)
@classmethod

6
api/core/model_providers/providers/minimax_provider.py
View File

@@ -74,11 +74,11 @@ class MinimaxProvider(BaseModelProvider):
}
return ModelKwargsRules(
temperature=KwargRule[float](min=0.01, max=1, default=0.9),
top_p=KwargRule[float](min=0, max=1, default=0.95),
temperature=KwargRule[float](min=0.01, max=1, default=0.9, precision=2),
top_p=KwargRule[float](min=0, max=1, default=0.95, precision=2),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](min=10, max=model_max_tokens.get(model_name, 6144), default=1024),
max_tokens=KwargRule[int](min=10, max=model_max_tokens.get(model_name, 6144), default=1024, precision=0),
)
@classmethod

10
api/core/model_providers/providers/openai_provider.py
View File

@@ -133,11 +133,11 @@ class OpenAIProvider(BaseModelProvider):
}
return ModelKwargsRules(
temperature=KwargRule[float](min=0, max=2, default=1),
top_p=KwargRule[float](min=0, max=1, default=1),
presence_penalty=KwargRule[float](min=-2, max=2, default=0),
frequency_penalty=KwargRule[float](min=-2, max=2, default=0),
max_tokens=KwargRule[int](min=10, max=model_max_tokens.get(model_name, 4097), default=16),
temperature=KwargRule[float](min=0, max=2, default=1, precision=2),
top_p=KwargRule[float](min=0, max=1, default=1, precision=2),
presence_penalty=KwargRule[float](min=-2, max=2, default=0, precision=2),
frequency_penalty=KwargRule[float](min=-2, max=2, default=0, precision=2),
max_tokens=KwargRule[int](min=10, max=model_max_tokens.get(model_name, 4097), default=16, precision=0),
)
@classmethod

10
api/core/model_providers/providers/openllm_provider.py
View File

@@ -45,11 +45,11 @@ class OpenLLMProvider(BaseModelProvider):
:return:
"""
return ModelKwargsRules(
temperature=KwargRule[float](min=0.01, max=2, default=1),
top_p=KwargRule[float](min=0, max=1, default=0.7),
presence_penalty=KwargRule[float](min=-2, max=2, default=0),
frequency_penalty=KwargRule[float](min=-2, max=2, default=0),
max_tokens=KwargRule[int](alias='max_new_tokens', min=10, max=4000, default=128),
temperature=KwargRule[float](min=0.01, max=2, default=1, precision=2),
top_p=KwargRule[float](min=0, max=1, default=0.7, precision=2),
presence_penalty=KwargRule[float](min=-2, max=2, default=0, precision=2),
frequency_penalty=KwargRule[float](min=-2, max=2, default=0, precision=2),
max_tokens=KwargRule[int](alias='max_new_tokens', min=10, max=4000, default=128, precision=0),
)
@classmethod

2
api/core/model_providers/providers/replicate_provider.py
View File

@@ -72,6 +72,7 @@ class ReplicateProvider(BaseModelProvider):
min=float(value.get('minimum')) if value.get('minimum') is not None else None,
max=float(value.get('maximum')) if value.get('maximum') is not None else None,
default=float(value.get('default')) if value.get('default') is not None else None,
precision = 2
)
if key == 'temperature':
model_kwargs_rules.temperature = kwarg_rule
@@ -84,6 +85,7 @@ class ReplicateProvider(BaseModelProvider):
min=int(value.get('minimum')) if value.get('minimum') is not None else 1,
max=int(value.get('maximum')) if value.get('maximum') is not None else 8000,
default=int(value.get('default')) if value.get('default') is not None else 500,
precision = 0
)
return model_kwargs_rules

4
api/core/model_providers/providers/spark_provider.py
View File

@@ -62,11 +62,11 @@ class SparkProvider(BaseModelProvider):
:return:
"""
return ModelKwargsRules(
temperature=KwargRule[float](min=0, max=1, default=0.5),
temperature=KwargRule[float](min=0, max=1, default=0.5, precision=2),
top_p=KwargRule[float](enabled=False),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](min=10, max=4096, default=2048),
max_tokens=KwargRule[int](min=10, max=4096, default=2048, precision=0),
)
@classmethod

4
api/core/model_providers/providers/tongyi_provider.py
View File

@@ -64,10 +64,10 @@ class TongyiProvider(BaseModelProvider):
return ModelKwargsRules(
temperature=KwargRule[float](enabled=False),
top_p=KwargRule[float](min=0, max=1, default=0.8),
top_p=KwargRule[float](min=0, max=1, default=0.8, precision=2),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](min=10, max=model_max_tokens.get(model_name), default=1024),
max_tokens=KwargRule[int](min=10, max=model_max_tokens.get(model_name), default=1024, precision=0),
)
@classmethod

4
api/core/model_providers/providers/wenxin_provider.py
View File

@@ -63,8 +63,8 @@ class WenxinProvider(BaseModelProvider):
"""
if model_name in ['ernie-bot', 'ernie-bot-turbo']:
return ModelKwargsRules(
temperature=KwargRule[float](min=0.01, max=1, default=0.95),
top_p=KwargRule[float](min=0.01, max=1, default=0.8),
temperature=KwargRule[float](min=0.01, max=1, default=0.95, precision=2),
top_p=KwargRule[float](min=0.01, max=1, default=0.8, precision=2),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](enabled=False),

22
api/core/model_providers/providers/xinference_provider.py
View File

@@ -53,27 +53,27 @@ class XinferenceProvider(BaseModelProvider):
credentials = self.get_model_credentials(model_name, model_type)
if credentials['model_format'] == "ggmlv3" and credentials["model_handle_type"] == "chatglm":
return ModelKwargsRules(
temperature=KwargRule[float](min=0.01, max=2, default=1),
top_p=KwargRule[float](min=0, max=1, default=0.7),
temperature=KwargRule[float](min=0.01, max=2, default=1, precision=2),
top_p=KwargRule[float](min=0, max=1, default=0.7, precision=2),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](min=10, max=4000, default=256),
max_tokens=KwargRule[int](min=10, max=4000, default=256, precision=0),
)
elif credentials['model_format'] == "ggmlv3":
return ModelKwargsRules(
temperature=KwargRule[float](min=0.01, max=2, default=1),
top_p=KwargRule[float](min=0, max=1, default=0.7),
presence_penalty=KwargRule[float](min=-2, max=2, default=0),
frequency_penalty=KwargRule[float](min=-2, max=2, default=0),
max_tokens=KwargRule[int](min=10, max=4000, default=256),
temperature=KwargRule[float](min=0.01, max=2, default=1, precision=2),
top_p=KwargRule[float](min=0, max=1, default=0.7, precision=2),
presence_penalty=KwargRule[float](min=-2, max=2, default=0, precision=2),
frequency_penalty=KwargRule[float](min=-2, max=2, default=0, precision=2),
max_tokens=KwargRule[int](min=10, max=4000, default=256, precision=0),
)
else:
return ModelKwargsRules(
temperature=KwargRule[float](min=0.01, max=2, default=1),
top_p=KwargRule[float](min=0, max=1, default=0.7),
temperature=KwargRule[float](min=0.01, max=2, default=1, precision=2),
top_p=KwargRule[float](min=0, max=1, default=0.7, precision=2),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](min=10, max=4000, default=256),
max_tokens=KwargRule[int](min=10, max=4000, default=256, precision=0),
)

176
api/core/model_providers/providers/zhipuai_provider.py Normal file
View File

@@ -0,0 +1,176 @@
import json
from json import JSONDecodeError
from typing import Type
from langchain.schema import HumanMessage
from core.helper import encrypter
from core.model_providers.models.base import BaseProviderModel
from core.model_providers.models.embedding.zhipuai_embedding import ZhipuAIEmbedding
from core.model_providers.models.entity.model_params import ModelKwargsRules, KwargRule, ModelType
from core.model_providers.models.llm.zhipuai_model import ZhipuAIModel
from core.model_providers.providers.base import BaseModelProvider, CredentialsValidateFailedError
from core.third_party.langchain.llms.zhipuai_llm import ZhipuAIChatLLM
from models.provider import ProviderType, ProviderQuotaType
class ZhipuAIProvider(BaseModelProvider):
@property
def provider_name(self):
"""
Returns the name of a provider.
"""
return 'zhipuai'
def _get_fixed_model_list(self, model_type: ModelType) -> list[dict]:
if model_type == ModelType.TEXT_GENERATION:
return [
{
'id': 'chatglm_pro',
'name': 'chatglm_pro',
},
{
'id': 'chatglm_std',
'name': 'chatglm_std',
},
{
'id': 'chatglm_lite',
'name': 'chatglm_lite',
},
{
'id': 'chatglm_lite_32k',
'name': 'chatglm_lite_32k',
}
]
elif model_type == ModelType.EMBEDDINGS:
return [
{
'id': 'text_embedding',
'name': 'text_embedding',
}
]
else:
return []
def get_model_class(self, model_type: ModelType) -> Type[BaseProviderModel]:
"""
Returns the model class.
:param model_type:
:return:
"""
if model_type == ModelType.TEXT_GENERATION:
model_class = ZhipuAIModel
elif model_type == ModelType.EMBEDDINGS:
model_class = ZhipuAIEmbedding
else:
raise NotImplementedError
return model_class
def get_model_parameter_rules(self, model_name: str, model_type: ModelType) -> ModelKwargsRules:
"""
get model parameter rules.
:param model_name:
:param model_type:
:return:
"""
return ModelKwargsRules(
temperature=KwargRule[float](min=0.01, max=1, default=0.95, precision=2),
top_p=KwargRule[float](min=0.1, max=0.9, default=0.8, precision=1),
presence_penalty=KwargRule[float](enabled=False),
frequency_penalty=KwargRule[float](enabled=False),
max_tokens=KwargRule[int](enabled=False),
)
@classmethod
def is_provider_credentials_valid_or_raise(cls, credentials: dict):
"""
Validates the given credentials.
"""
if 'api_key' not in credentials:
raise CredentialsValidateFailedError('ZhipuAI api_key must be provided.')
try:
credential_kwargs = {
'api_key': credentials['api_key']
}
llm = ZhipuAIChatLLM(
temperature=0.01,
**credential_kwargs
)
llm([HumanMessage(content='ping')])
except Exception as ex:
raise CredentialsValidateFailedError(str(ex))
@classmethod
def encrypt_provider_credentials(cls, tenant_id: str, credentials: dict) -> dict:
credentials['api_key'] = encrypter.encrypt_token(tenant_id, credentials['api_key'])
return credentials
def get_provider_credentials(self, obfuscated: bool = False) -> dict:
if self.provider.provider_type == ProviderType.CUSTOM.value \
or (self.provider.provider_type == ProviderType.SYSTEM.value
and self.provider.quota_type == ProviderQuotaType.FREE.value):
try:
credentials = json.loads(self.provider.encrypted_config)
except JSONDecodeError:
credentials = {
'api_key': None,
}
if credentials['api_key']:
credentials['api_key'] = encrypter.decrypt_token(
self.provider.tenant_id,
credentials['api_key']
)
if obfuscated:
credentials['api_key'] = encrypter.obfuscated_token(credentials['api_key'])
return credentials
else:
return {}
def should_deduct_quota(self):
return True
@classmethod
def is_model_credentials_valid_or_raise(cls, model_name: str, model_type: ModelType, credentials: dict):
"""
check model credentials valid.
:param model_name:
:param model_type:
:param credentials:
"""
return
@classmethod
def encrypt_model_credentials(cls, tenant_id: str, model_name: str, model_type: ModelType,
credentials: dict) -> dict:
"""
encrypt model credentials for save.
:param tenant_id:
:param model_name:
:param model_type:
:param credentials:
:return:
"""
return {}
def get_model_credentials(self, model_name: str, model_type: ModelType, obfuscated: bool = False) -> dict:
"""
get credentials for llm use.
:param model_name:
:param model_type:
:param obfuscated:
:return:
"""
return self.get_provider_credentials(obfuscated)