Merge branch 'refs/heads/main' into poetry-docker

langgenius · Jun 21, 2024 · 8ca0136 · 8ca0136
2 parents 4e4c4f0 + 91d38a5
commit 8ca0136
Show file tree

Hide file tree

Showing 168 changed files with 1,068 additions and 329 deletions.
diff --git a/api/app.py b/api/app.py
@@ -2,7 +2,7 @@
 
 from configs.app_configs import DifyConfigs
 
-if not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != 'true':
+if not os.environ.get("DEBUG") or os.environ.get("DEBUG", "false").lower() != 'true':
     from gevent import monkey
 
     monkey.patch_all()
@@ -152,27 +152,26 @@ def initialize_extensions(app):
 @login_manager.request_loader
 def load_user_from_request(request_from_flask_login):
     """Load user based on the request."""
-    if request.blueprint in ['console', 'inner_api']:
-        # Check if the user_id contains a dot, indicating the old format
-        auth_header = request.headers.get('Authorization', '')
-        if not auth_header:
-            auth_token = request.args.get('_token')
-            if not auth_token:
-                raise Unauthorized('Invalid Authorization token.')
-        else:
-            if ' ' not in auth_header:
-                raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
-            auth_scheme, auth_token = auth_header.split(None, 1)
-            auth_scheme = auth_scheme.lower()
-            if auth_scheme != 'bearer':
-                raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
-
-        decoded = PassportService().verify(auth_token)
-        user_id = decoded.get('user_id')
-
-        return AccountService.load_user(user_id)
-    else:
+    if request.blueprint not in ['console', 'inner_api']:
         return None
+    # Check if the user_id contains a dot, indicating the old format
+    auth_header = request.headers.get('Authorization', '')
+    if not auth_header:
+        auth_token = request.args.get('_token')
+        if not auth_token:
+            raise Unauthorized('Invalid Authorization token.')
+    else:
+        if ' ' not in auth_header:
+            raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
+        auth_scheme, auth_token = auth_header.split(None, 1)
+        auth_scheme = auth_scheme.lower()
+        if auth_scheme != 'bearer':
+            raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
+
+    decoded = PassportService().verify(auth_token)
+    user_id = decoded.get('user_id')
+
+    return AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
 
 
 @login_manager.unauthorized_handler

diff --git a/api/controllers/console/app/site.py b/api/controllers/console/app/site.py
@@ -28,6 +28,7 @@ def parse_app_site_args():
                         required=False,
                         location='json')
     parser.add_argument('prompt_public', type=bool, required=False, location='json')
+    parser.add_argument('show_workflow_steps', type=bool, required=False, location='json')
     return parser.parse_args()
 
 
@@ -59,7 +60,8 @@ def post(self, app_model):
             'privacy_policy',
             'custom_disclaimer',
             'customize_token_strategy',
-            'prompt_public'
+            'prompt_public',
+            'show_workflow_steps'
         ]:
             value = args.get(attr_name)
             if value is not None:

diff --git a/api/controllers/console/auth/login.py b/api/controllers/console/auth/login.py
@@ -1,12 +1,15 @@
+from typing import cast
+
 import flask_login
 from flask import current_app, request
 from flask_restful import Resource, reqparse
 
 import services
 from controllers.console import api
 from controllers.console.setup import setup_required
-from libs.helper import email
+from libs.helper import email, get_remote_ip
 from libs.password import valid_password
+from models.account import Account
 from services.account_service import AccountService, TenantService
 
 
@@ -34,10 +37,7 @@ def post(self):
         if len(tenants) == 0:
             return {'result': 'fail', 'data': 'workspace not found, please contact system admin to invite you to join in a workspace'}
 
-        AccountService.update_last_login(account, request)
-
-        # todo: return the user info
-        token = AccountService.get_account_jwt_token(account)
+        token = AccountService.login(account, ip_address=get_remote_ip(request))
 
         return {'result': 'success', 'data': token}
 
@@ -46,6 +46,9 @@ class LogoutApi(Resource):
 
     @setup_required
     def get(self):
+        account = cast(Account, flask_login.current_user)
+        token = request.headers.get('Authorization', '').split(' ')[1]
+        AccountService.logout(account=account, token=token)
         flask_login.logout_user()
         return {'result': 'success'}
 

diff --git a/api/controllers/console/auth/oauth.py b/api/controllers/console/auth/oauth.py
@@ -8,6 +8,7 @@
 
 from constants.languages import languages
 from extensions.ext_database import db
+from libs.helper import get_remote_ip
 from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
 from models.account import Account, AccountStatus
 from services.account_service import AccountService, RegisterService, TenantService
@@ -78,9 +79,7 @@ def get(self, provider: str):
 
         TenantService.create_owner_tenant_if_not_exist(account)
 
-        AccountService.update_last_login(account, request)
-
-        token = AccountService.get_account_jwt_token(account)
+        token = AccountService.login(account, ip_address=get_remote_ip(request))
 
         return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?console_token={token}')
 

diff --git a/api/controllers/console/setup.py b/api/controllers/console/setup.py
@@ -4,7 +4,7 @@
 from flask_restful import Resource, reqparse
 
 from extensions.ext_database import db
-from libs.helper import email, str_len
+from libs.helper import email, get_remote_ip, str_len
 from libs.password import valid_password
 from models.model import DifySetup
 from services.account_service import AccountService, RegisterService, TenantService
@@ -61,7 +61,7 @@ def post(self):
         TenantService.create_owner_tenant_if_not_exist(account)
 
         setup()
-        AccountService.update_last_login(account, request)
+        AccountService.update_last_login(account, ip_address=get_remote_ip(request))
 
         return {'result': 'success'}, 201
 

diff --git a/api/controllers/web/site.py b/api/controllers/web/site.py
@@ -33,7 +33,8 @@ class AppSiteApi(WebApiResource):
         'privacy_policy': fields.String,
         'custom_disclaimer': fields.String,
         'default_language': fields.String,
-        'prompt_public': fields.Boolean
+        'prompt_public': fields.Boolean,
+        'show_workflow_steps': fields.Boolean,
     }
 
     app_fields = {

diff --git a/api/core/entities/provider_configuration.py b/api/core/entities/provider_configuration.py
@@ -206,8 +206,8 @@ def custom_credentials_validate(self, credentials: dict) -> tuple[Provider, dict
                         credentials[key] = encrypter.decrypt_token(self.tenant_id, original_credentials[key])
 
         credentials = model_provider_factory.provider_credentials_validate(
-            self.provider.provider,
-            credentials
+            provider=self.provider.provider,
+            credentials=credentials
         )
 
         for key, value in credentials.items():

diff --git a/api/core/model_runtime/model_providers/anthropic/llm/_position.yaml b/api/core/model_runtime/model_providers/anthropic/llm/_position.yaml
@@ -1,3 +1,5 @@
+- claude-3-5-sonnet-20240620
+- claude-3-haiku-20240307
 - claude-3-opus-20240229
 - claude-3-sonnet-20240229
 - claude-2.1

diff --git a/api/core/model_runtime/model_providers/anthropic/llm/claude-3-5-sonnet-20240620.yaml b/api/core/model_runtime/model_providers/anthropic/llm/claude-3-5-sonnet-20240620.yaml
@@ -0,0 +1,39 @@
+model: claude-3-5-sonnet-20240620
+label:
+  en_US: claude-3-5-sonnet-20240620
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '3.00'
+  output: '15.00'
+  unit: '0.000001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/bedrock/llm/anthropic.claude-3-sonnet-v1.5.yaml b/api/core/model_runtime/model_providers/bedrock/llm/anthropic.claude-3-sonnet-v1.5.yaml
@@ -0,0 +1,56 @@
+model: anthropic.claude-3-5-sonnet-20240620-v1:0
+label:
+  en_US: Claude 3.5 Sonnet
+model_type: llm
+features:
+  - agent-thought
+  - vision
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    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
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-chat.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-chat.yaml
@@ -22,9 +22,9 @@ parameter_rules:
   - name: max_tokens
     use_template: max_tokens
     type: int
-    default: 1500
+    default: 2000
     min: 1
-    max: 1500
+    max: 2000
     help:
       zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
       en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.

diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
@@ -20,9 +20,9 @@ parameter_rules:
   - name: max_tokens
     use_template: max_tokens
     type: int
-    default: 1500
+    default: 2000
     min: 1
-    max: 1500
+    max: 2000
     help:
       zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
       en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.

diff --git a/api/core/model_runtime/model_providers/vertex_ai/llm/anthropic.claude-3.5-sonnet.yaml b/api/core/model_runtime/model_providers/vertex_ai/llm/anthropic.claude-3.5-sonnet.yaml
@@ -0,0 +1,55 @@
+model: claude-3-5-sonnet@20240620
+label:
+  en_US: Claude 3.5 Sonnet
+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: 4096
+    min: 1
+    max: 4096
+    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
diff --git a/api/core/model_runtime/model_providers/vertex_ai/llm/llm.py b/api/core/model_runtime/model_providers/vertex_ai/llm/llm.py
@@ -100,7 +100,7 @@ def _generate_anthropic(self, model: str, credentials: dict, prompt_messages: li
             token = credentials.token
 
         # Vertex AI Anthropic Claude3 Opus model available in us-east5 region, Sonnet and Haiku available in us-central1 region
-        if 'opus' in model:
+        if 'opus' or 'claude-3-5-sonnet' in model:
             location = 'us-east5'
         else:
             location = 'us-central1'

diff --git a/api/fields/app_fields.py b/api/fields/app_fields.py
@@ -117,6 +117,7 @@
     'customize_token_strategy': fields.String,
     'prompt_public': fields.Boolean,
     'app_base_url': fields.String,
+    'show_workflow_steps': fields.Boolean,
 }
 
 app_detail_fields_with_site = {
@@ -149,5 +150,6 @@
     'privacy_policy': fields.String,
     'custom_disclaimer': fields.String,
     'customize_token_strategy': fields.String,
-    'prompt_public': fields.Boolean
+    'prompt_public': fields.Boolean,
+    'show_workflow_steps': fields.Boolean,
 }
diff --git a/api/libs/helper.py b/api/libs/helper.py
@@ -140,7 +140,7 @@ def generate_string(n):
     return result
 
 
-def get_remote_ip(request):
+def get_remote_ip(request) -> str:
     if request.headers.get('CF-Connecting-IP'):
         return request.headers.get('Cf-Connecting-Ip')
     elif request.headers.getlist("X-Forwarded-For"):