Merge branch 'refs/heads/feat/knowledge-admin-role' into deploy/dev

* refs/heads/feat/knowledge-admin-role: (26 commits) fix: do not remove (#5682) Feature/add qwen llm (#5659) Fix docker command (#5681) feature: Add presence_penalty and frequency_penalty parameters to the … (#5637) Feat/fix ops trace (#5672) feat: xxo enhancement. (#5671) chore: rearrange python dependencies in groups (#5603) chore: delete unused resource (#5667) feat: get datasets when permission is partial_members feat: update migrate file feat: add account is_non_owner_role add role feat: get dataset info add partial_member_list feat: update field name feat: add tenant account role DATASET_OPERATOR feat: add create and get part_users_list api feat: add dataset permission service feat: add table dataset_permissions feat: add dataset_operator_enabled env feat: add features dataset_operator_enabled ... # Conflicts: # api/core/ops/ops_trace_manager.py # api/tasks/ops_trace_task.py
langgenius · Jun 28, 2024 · 463a943 · 463a943
2 parents 96d250b + 2ccb4e0
commit 463a943
Show file tree

Hide file tree

Showing 53 changed files with 1,086 additions and 377 deletions.
diff --git a/ArrowUturnLeft.svg b/ArrowUturnLeft.svg
diff --git a/api/README.md b/api/README.md
@@ -11,7 +11,7 @@
 
    ```bash
    cd ../docker
-   docker-compose -f docker-compose.middleware.yaml -p dify up -d
+   docker compose -f docker-compose.middleware.yaml -p dify up -d
    cd ../api
    ```
 

diff --git a/api/controllers/console/datasets/datasets.py b/api/controllers/console/datasets/datasets.py
@@ -25,7 +25,7 @@
 from libs.login import login_required
 from models.dataset import Dataset, Document, DocumentSegment
 from models.model import ApiToken, UploadFile
-from services.dataset_service import DatasetService, DocumentService
+from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 
 
 def _validate_name(name):
@@ -163,6 +163,11 @@ def get(self, dataset_id):
                 data['embedding_available'] = False
         else:
             data['embedding_available'] = True
+
+        if data.get('permission') == 'partial_members':
+            part_users_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
+            data.update({'partial_member_list': part_users_list})
+
         return data, 200
 
     @setup_required
@@ -188,16 +193,18 @@ def patch(self, dataset_id):
                             nullable=True,
                             help='Invalid indexing technique.')
         parser.add_argument('permission', type=str, location='json', choices=(
-            'only_me', 'all_team_members'), help='Invalid permission.')
+            'only_me', 'all_team_members', 'partial_members'), help='Invalid permission.'
+                            )
         parser.add_argument('embedding_model', type=str,
                             location='json', help='Invalid embedding model.')
         parser.add_argument('embedding_model_provider', type=str,
                             location='json', help='Invalid embedding model provider.')
         parser.add_argument('retrieval_model', type=dict, location='json', help='Invalid retrieval model.')
+        parser.add_argument('partial_member_list', type=list, location='json', help='Invalid parent user list.')
         args = parser.parse_args()
-
+        data = request.get_json()
         # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
+        if not current_user.is_dataset_editing_role:
             raise Forbidden()
 
         dataset = DatasetService.update_dataset(
@@ -206,7 +213,14 @@ def patch(self, dataset_id):
         if dataset is None:
             raise NotFound("Dataset not found.")
 
-        return marshal(dataset, dataset_detail_fields), 200
+        result_data = marshal(dataset, dataset_detail_fields)
+
+        if data.get('partial_member_list') and data.get('permission') == 'partial_members':
+            DatasetPermissionService.update_partial_member_list(dataset_id_str, data.get('partial_member_list'))
+            part_users_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
+            result_data.update({'partial_member_list': part_users_list})
+
+        return result_data, 200
 
     @setup_required
     @login_required
@@ -560,6 +574,27 @@ def get(self, dataset_id):
         }, 200
 
 
+class DatasetPermissionUserListApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        partial_members_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
+
+        return {
+            'data': partial_members_list,
+        }, 200
+
+
 api.add_resource(DatasetListApi, '/datasets')
 api.add_resource(DatasetApi, '/datasets/<uuid:dataset_id>')
 api.add_resource(DatasetQueryApi, '/datasets/<uuid:dataset_id>/queries')
@@ -572,3 +607,4 @@ def get(self, dataset_id):
 api.add_resource(DatasetApiBaseUrlApi, '/datasets/api-base-info')
 api.add_resource(DatasetRetrievalSettingApi, '/datasets/retrieval-setting')
 api.add_resource(DatasetRetrievalSettingMockApi, '/datasets/retrieval-setting/<string:vector_type>')
+api.add_resource(DatasetPermissionUserListApi, '/datasets/<uuid:dataset_id>/permission-part-users')
diff --git a/api/controllers/console/workspace/members.py b/api/controllers/console/workspace/members.py
@@ -131,7 +131,20 @@ def put(self, member_id):
         return {'result': 'success'}
 
 
+class DatasetOperatorMemberListApi(Resource):
+    """List all members of current tenant."""
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(account_with_role_list_fields)
+    def get(self):
+        members = TenantService.get_dataset_operator_members(current_user.current_tenant)
+        return {'result': 'success', 'accounts': members}, 200
+
+
 api.add_resource(MemberListApi, '/workspaces/current/members')
 api.add_resource(MemberInviteEmailApi, '/workspaces/current/members/invite-email')
 api.add_resource(MemberCancelInviteApi, '/workspaces/current/members/<uuid:member_id>')
 api.add_resource(MemberUpdateRoleApi, '/workspaces/current/members/<uuid:member_id>/update-role')
+api.add_resource(DatasetOperatorMemberListApi, '/workspaces/current/dataset-operators')
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-long.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-long.yaml
@@ -0,0 +1,81 @@
+model: qwen-long
+label:
+  en_US: qwen-long
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 10000000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    type: float
+    default: 0.3
+    min: 0.0
+    max: 2.0
+    help:
+      zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
+      en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 2000
+    min: 1
+    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.
+  - name: top_p
+    use_template: top_p
+    type: float
+    default: 0.8
+    min: 0.1
+    max: 0.9
+    help:
+      zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
+      en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
+  - name: top_k
+    type: int
+    min: 0
+    max: 99
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    help:
+      zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
+      en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
+  - name: seed
+    required: false
+    type: int
+    default: 1234
+    label:
+      zh_Hans: 随机种子
+      en_US: Random seed
+    help:
+      zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。
+      en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.
+  - name: repetition_penalty
+    required: false
+    type: float
+    default: 1.1
+    label:
+      en_US: Repetition penalty
+    help:
+      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
+      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
+  - name: enable_search
+    type: boolean
+    default: false
+    help:
+      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
+      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.0005'
+  output: '0.002'
+  unit: '0.001'
+  currency: RMB
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0403.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0403.yaml
@@ -75,7 +75,7 @@ parameter_rules:
   - name: response_format
     use_template: response_format
 pricing:
-  input: '0.12'
+  input: '0.04'
   output: '0.12'
   unit: '0.001'
   currency: RMB
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0428.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0428.yaml
@@ -0,0 +1,81 @@
+model: qwen-max-0428
+label:
+  en_US: qwen-max-0428
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    type: float
+    default: 0.3
+    min: 0.0
+    max: 2.0
+    help:
+      zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
+      en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 2000
+    min: 1
+    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.
+  - name: top_p
+    use_template: top_p
+    type: float
+    default: 0.8
+    min: 0.1
+    max: 0.9
+    help:
+      zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
+      en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
+  - name: top_k
+    type: int
+    min: 0
+    max: 99
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    help:
+      zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
+      en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
+  - name: seed
+    required: false
+    type: int
+    default: 1234
+    label:
+      zh_Hans: 随机种子
+      en_US: Random seed
+    help:
+      zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。
+      en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.
+  - name: repetition_penalty
+    required: false
+    type: float
+    default: 1.1
+    label:
+      en_US: Repetition penalty
+    help:
+      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
+      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
+  - name: enable_search
+    type: boolean
+    default: false
+    help:
+      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
+      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.04'
+  output: '0.12'
+  unit: '0.001'
+  currency: RMB
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-1201.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-1201.yaml
@@ -75,7 +75,7 @@ parameter_rules:
   - name: response_format
     use_template: response_format
 pricing:
-  input: '0.12'
+  input: '0.04'
   output: '0.12'
   unit: '0.001'
   currency: RMB
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
@@ -75,7 +75,7 @@ parameter_rules:
   - name: response_format
     use_template: response_format
 pricing:
-  input: '0.12'
+  input: '0.04'
   output: '0.12'
   unit: '0.001'
   currency: RMB
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
@@ -75,7 +75,7 @@ parameter_rules:
   - name: response_format
     use_template: response_format
 pricing:
-  input: '0.12'
+  input: '0.04'
   output: '0.12'
   unit: '0.001'
   currency: RMB
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
@@ -75,7 +75,7 @@ parameter_rules:
   - name: response_format
     use_template: response_format
 pricing:
-  input: '0.02'
-  output: '0.02'
+  input: '0.004'
+  output: '0.012'
   unit: '0.001'
   currency: RMB
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
@@ -73,7 +73,7 @@ parameter_rules:
   - name: response_format
     use_template: response_format
 pricing:
-  input: '0.02'
-  output: '0.02'
+  input: '0.004'
+  output: '0.012'
   unit: '0.001'
   currency: RMB
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-chat.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-chat.yaml
@@ -75,7 +75,7 @@ parameter_rules:
   - name: response_format
     use_template: response_format
 pricing:
-  input: '0.008'
-  output: '0.008'
+  input: '0.002'
+  output: '0.006'
   unit: '0.001'
   currency: RMB
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
@@ -73,7 +73,7 @@ parameter_rules:
   - name: response_format
     use_template: response_format
 pricing:
-  input: '0.008'
-  output: '0.008'
+  input: '0.002'
+  output: '0.006'
   unit: '0.001'
   currency: RMB