Merge 247e1cdcf3 into 4b2abf8ac2

Signed-off-by: yihong0618 <zouzou0208@gmail.com>

api/core/model_runtime/model_providers/siliconflow/llm/Internvl2-26b.yaml

@@ -0,0 +1,84 @@
+model: OpenGVLab/InternVL2-26B
+label:
+  en_US: OpenGVLab/InternVL2-26B
+model_type: llm
+features:
+  - vision
+model_properties:
+  mode: chat
+  context_size: 32768
+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:
+      zh_Hans: 重复惩罚
+      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: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '21'
+  output: '21'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/Internvl2-8b.yaml

@@ -0,0 +1,84 @@
+model: Pro/OpenGVLab/InternVL2-8B
+label:
+  en_US: Pro/OpenGVLab/InternVL2-8B
+model_type: llm
+features:
+  - vision
+model_properties:
+  mode: chat
+  context_size: 32768
+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:
+      zh_Hans: 重复惩罚
+      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: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '21'
+  output: '21'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml

@@ -1,16 +1,18 @@
+- Tencent/Hunyuan-A52B-Instruct
 - Qwen/Qwen2.5-72B-Instruct
 - Qwen/Qwen2.5-32B-Instruct
 - Qwen/Qwen2.5-14B-Instruct
 - Qwen/Qwen2.5-7B-Instruct
+- Qwen/Qwen2.5-Coder-32B-Instruct
 - Qwen/Qwen2.5-Coder-7B-Instruct
 - Qwen/Qwen2.5-Math-72B-Instruct
-- Qwen/Qwen2-72B-Instruct
-- Qwen/Qwen2-57B-A14B-Instruct
-- Qwen/Qwen2-7B-Instruct
+- Qwen/Qwen2-VL-72B-Instruct
 - Qwen/Qwen2-1.5B-Instruct
+- Pro/Qwen/Qwen2-VL-7B-Instruct
+- OpenGVLab/InternVL2-Llama3-76B
+- OpenGVLab/InternVL2-26B
+- Pro/OpenGVLab/InternVL2-8B
 - deepseek-ai/DeepSeek-V2.5
-- deepseek-ai/DeepSeek-V2-Chat
-- deepseek-ai/DeepSeek-Coder-V2-Instruct
 - THUDM/glm-4-9b-chat
 - 01-ai/Yi-1.5-34B-Chat-16K
 - 01-ai/Yi-1.5-9B-Chat-16K
@@ -20,9 +22,6 @@
 - meta-llama/Meta-Llama-3.1-405B-Instruct
 - meta-llama/Meta-Llama-3.1-70B-Instruct
 - meta-llama/Meta-Llama-3.1-8B-Instruct
-- meta-llama/Meta-Llama-3-70B-Instruct
-- meta-llama/Meta-Llama-3-8B-Instruct
 - google/gemma-2-27b-it
 - google/gemma-2-9b-it
-- mistralai/Mistral-7B-Instruct-v0.2
-- mistralai/Mixtral-8x7B-Instruct-v0.1
+- deepseek-ai/DeepSeek-V2-Chat

api/core/model_runtime/model_providers/siliconflow/llm/deepdeek-coder-v2-instruct.yaml

@@ -37,3 +37,4 @@ pricing:
   output: '1.33'
   unit: '0.000001'
   currency: RMB
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2-chat.yaml

@@ -37,3 +37,4 @@ pricing:
   output: '1.33'
   unit: '0.000001'
   currency: RMB
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2.5.yaml

@@ -4,6 +4,8 @@ label:
 model_type: llm
 features:
   - agent-thought
+  - tool-call
+  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 32768

api/core/model_runtime/model_providers/siliconflow/llm/hunyuan-a52b-instruct.yaml

@@ -0,0 +1,84 @@
+model: Tencent/Hunyuan-A52B-Instruct
+label:
+  en_US: Tencent/Hunyuan-A52B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+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:
+      zh_Hans: 重复惩罚
+      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: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '21'
+  output: '21'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/internvl2-llama3-76b.yaml

@@ -0,0 +1,84 @@
+model: OpenGVLab/InternVL2-Llama3-76B
+label:
+  en_US: OpenGVLab/InternVL2-Llama3-76B
+model_type: llm
+features:
+  - vision
+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:
+      zh_Hans: 重复惩罚
+      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: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '21'
+  output: '21'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3-70b-instruct.yaml

@@ -37,3 +37,4 @@ pricing:
   output: '4.13'
   unit: '0.000001'
   currency: RMB
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3-8b-instruct.yaml

@@ -37,3 +37,4 @@ pricing:
   output: '0'
   unit: '0.000001'
   currency: RMB
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3.1-70b-instruct.yaml

@@ -6,7 +6,7 @@ features:
   - agent-thought
 model_properties:
   mode: chat
-  context_size: 32768
+  context_size: 8192
 parameter_rules:
   - name: temperature
     use_template: temperature

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-57b-a14b-instruct.yaml

@@ -37,3 +37,4 @@ pricing:
   output: '1.26'
   unit: '0.000001'
   currency: RMB
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-72b-instruct.yaml

@@ -37,3 +37,4 @@ pricing:
   output: '4.13'
   unit: '0.000001'
   currency: RMB
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-7b-instruct.yaml

@@ -37,3 +37,4 @@ pricing:
   output: '0'
   unit: '0.000001'
   currency: RMB
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-vl-72b-instruct.yaml

@@ -0,0 +1,84 @@
+model: Qwen/Qwen2-VL-72B-Instruct
+label:
+  en_US: Qwen/Qwen2-VL-72B-Instruct
+model_type: llm
+features:
+  - vision
+model_properties:
+  mode: chat
+  context_size: 32768
+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:
+      zh_Hans: 重复惩罚
+      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: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '21'
+  output: '21'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-vl-7b-Instruct.yaml

@@ -0,0 +1,84 @@
+model: Pro/Qwen/Qwen2-VL-7B-Instruct
+label:
+  en_US: Pro/Qwen/Qwen2-VL-7B-Instruct
+model_type: llm
+features:
+  - vision
+model_properties:
+  mode: chat
+  context_size: 32768
+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:
+      zh_Hans: 重复惩罚
+      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: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '21'
+  output: '21'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen2.5-coder-32b-instruct.yaml

@@ -0,0 +1,84 @@
+model: Qwen/Qwen2.5-Coder-32B-Instruct
+label:
+  en_US: Qwen/Qwen2.5-Coder-32B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+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: 8192
+    min: 1
+    max: 8192
+    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:
+      zh_Hans: 重复惩罚
+      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: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '1.26'
+  output: '1.26'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/speech2text/funaudio-sense-voice-small.yaml

@@ -0,0 +1,5 @@
+model: FunAudioLLM/SenseVoiceSmall
+model_type: speech2text
+model_properties:
+  file_upload_limit: 1
+  supported_file_extensions: mp3,wav

api/core/model_runtime/model_providers/siliconflow/speech2text/sense-voice-small.yaml

@@ -3,3 +3,4 @@ model_type: speech2text
 model_properties:
   file_upload_limit: 1
   supported_file_extensions: mp3,wav
+deprecated: true

api/core/model_runtime/model_providers/volcengine_maas/legacy/volc_sdk/common.py

@@ -1,5 +1,6 @@
 import json
 import random
+from collections import UserDict
 from datetime import datetime
 
 
@@ -10,9 +11,9 @@ class ChatRole:
     FUNCTION = "function"
 
 
-class _Dict(dict):
-    __setattr__ = dict.__setitem__
-    __getattr__ = dict.__getitem__
+class _Dict(UserDict):
+    __setattr__ = UserDict.__setitem__
+    __getattr__ = UserDict.__getitem__
 
     def __missing__(self, key):
         return None

api/core/tools/provider/builtin/fal/tools/wizper.py

@@ -0,0 +1,52 @@
+import io
+import os
+from typing import Any
+
+import fal_client
+
+from core.file.enums import FileAttribute, FileType
+from core.file.file_manager import download, get_attr
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+
+class WizperTool(BuiltinTool):
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        audio_file = tool_parameters.get("audio_file")
+        task = tool_parameters.get("task", "transcribe")
+        language = tool_parameters.get("language", "en")
+        chunk_level = tool_parameters.get("chunk_level", "segment")
+        version = tool_parameters.get("version", "3")
+
+        if audio_file.type != FileType.AUDIO:
+            return [self.create_text_message("Not a valid audio file.")]
+
+        api_key = self.runtime.credentials["fal_api_key"]
+
+        os.environ["FAL_KEY"] = api_key
+
+        audio_binary = io.BytesIO(download(audio_file))
+        mime_type = get_attr(file=audio_file, attr=FileAttribute.MIME_TYPE)
+        file_data = audio_binary.getvalue()
+
+        try:
+            audio_url = fal_client.upload(file_data, mime_type)
+
+        except Exception as e:
+            return [self.create_text_message(f"Error uploading audio file: {str(e)}")]
+
+        arguments = {
+            "audio_url": audio_url,
+            "task": task,
+            "language": language,
+            "chunk_level": chunk_level,
+            "version": version,
+        }
+
+        result = fal_client.subscribe(
+            "fal-ai/wizper",
+            arguments=arguments,
+            with_logs=False,
+        )
+
+        return self.create_json_message(result)

api/core/tools/provider/builtin/fal/tools/wizper.yaml

@@ -0,0 +1,489 @@
+identity:
+  name: wizper
+  author: Kalo Chin
+  label:
+    en_US: Wizper
+    zh_Hans: Wizper
+description:
+  human:
+    en_US: Transcribe an audio file using the Whisper model.
+    zh_Hans: 使用 Whisper 模型转录音频文件。
+  llm: Transcribe an audio file using the Whisper model.
+parameters:
+  - name: audio_file
+    type: file
+    required: true
+    label:
+      en_US: Audio File
+      zh_Hans: 音频文件
+    human_description:
+      en_US: "Upload an audio file to transcribe. Supports mp3, mp4, mpeg, mpga, m4a, wav, or webm formats."
+      zh_Hans: "上传要转录的音频文件。支持 mp3、mp4、mpeg、mpga、m4a、wav 或 webm 格式。"
+    llm_description: "Audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm."
+    form: llm
+  - name: task
+    type: select
+    required: true
+    label:
+      en_US: Task
+      zh_Hans: 任务
+    human_description:
+      en_US: "Choose whether to transcribe the audio in its original language or translate it to English"
+      zh_Hans: "选择是以原始语言转录音频还是将其翻译成英语"
+    llm_description: "Task to perform on the audio file. Either transcribe or translate. Default value: 'transcribe'. If 'translate' is selected as the task, the audio will be translated to English, regardless of the language selected."
+    form: form
+    default: transcribe
+    options:
+      - value: transcribe
+        label:
+          en_US: Transcribe
+          zh_Hans: 转录
+      - value: translate
+        label:
+          en_US: Translate
+          zh_Hans: 翻译
+  - name: language
+    type: select
+    required: true
+    label:
+      en_US: Language
+      zh_Hans: 语言
+    human_description:
+      en_US: "Select the primary language spoken in the audio file"
+      zh_Hans: "选择音频文件中使用的主要语言"
+    llm_description: "Language of the audio file."
+    form: form
+    default: en
+    options:
+      - value: af
+        label:
+          en_US: Afrikaans
+          zh_Hans: 南非语
+      - value: am
+        label:
+          en_US: Amharic
+          zh_Hans: 阿姆哈拉语
+      - value: ar
+        label:
+          en_US: Arabic
+          zh_Hans: 阿拉伯语
+      - value: as
+        label:
+          en_US: Assamese
+          zh_Hans: 阿萨姆语
+      - value: az
+        label:
+          en_US: Azerbaijani
+          zh_Hans: 阿塞拜疆语
+      - value: ba
+        label:
+          en_US: Bashkir
+          zh_Hans: 巴什基尔语
+      - value: be
+        label:
+          en_US: Belarusian
+          zh_Hans: 白俄罗斯语
+      - value: bg
+        label:
+          en_US: Bulgarian
+          zh_Hans: 保加利亚语
+      - value: bn
+        label:
+          en_US: Bengali
+          zh_Hans: 孟加拉语
+      - value: bo
+        label:
+          en_US: Tibetan
+          zh_Hans: 藏语
+      - value: br
+        label:
+          en_US: Breton
+          zh_Hans: 布列塔尼语
+      - value: bs
+        label:
+          en_US: Bosnian
+          zh_Hans: 波斯尼亚语
+      - value: ca
+        label:
+          en_US: Catalan
+          zh_Hans: 加泰罗尼亚语
+      - value: cs
+        label:
+          en_US: Czech
+          zh_Hans: 捷克语
+      - value: cy
+        label:
+          en_US: Welsh
+          zh_Hans: 威尔士语
+      - value: da
+        label:
+          en_US: Danish
+          zh_Hans: 丹麦语
+      - value: de
+        label:
+          en_US: German
+          zh_Hans: 德语
+      - value: el
+        label:
+          en_US: Greek
+          zh_Hans: 希腊语
+      - value: en
+        label:
+          en_US: English
+          zh_Hans: 英语
+      - value: es
+        label:
+          en_US: Spanish
+          zh_Hans: 西班牙语
+      - value: et
+        label:
+          en_US: Estonian
+          zh_Hans: 爱沙尼亚语
+      - value: eu
+        label:
+          en_US: Basque
+          zh_Hans: 巴斯克语
+      - value: fa
+        label:
+          en_US: Persian
+          zh_Hans: 波斯语
+      - value: fi
+        label:
+          en_US: Finnish
+          zh_Hans: 芬兰语
+      - value: fo
+        label:
+          en_US: Faroese
+          zh_Hans: 法罗语
+      - value: fr
+        label:
+          en_US: French
+          zh_Hans: 法语
+      - value: gl
+        label:
+          en_US: Galician
+          zh_Hans: 加利西亚语
+      - value: gu
+        label:
+          en_US: Gujarati
+          zh_Hans: 古吉拉特语
+      - value: ha
+        label:
+          en_US: Hausa
+          zh_Hans: 毫萨语
+      - value: haw
+        label:
+          en_US: Hawaiian
+          zh_Hans: 夏威夷语
+      - value: he
+        label:
+          en_US: Hebrew
+          zh_Hans: 希伯来语
+      - value: hi
+        label:
+          en_US: Hindi
+          zh_Hans: 印地语
+      - value: hr
+        label:
+          en_US: Croatian
+          zh_Hans: 克罗地亚语
+      - value: ht
+        label:
+          en_US: Haitian Creole
+          zh_Hans: 海地克里奥尔语
+      - value: hu
+        label:
+          en_US: Hungarian
+          zh_Hans: 匈牙利语
+      - value: hy
+        label:
+          en_US: Armenian
+          zh_Hans: 亚美尼亚语
+      - value: id
+        label:
+          en_US: Indonesian
+          zh_Hans: 印度尼西亚语
+      - value: is
+        label:
+          en_US: Icelandic
+          zh_Hans: 冰岛语
+      - value: it
+        label:
+          en_US: Italian
+          zh_Hans: 意大利语
+      - value: ja
+        label:
+          en_US: Japanese
+          zh_Hans: 日语
+      - value: jw
+        label:
+          en_US: Javanese
+          zh_Hans: 爪哇语
+      - value: ka
+        label:
+          en_US: Georgian
+          zh_Hans: 格鲁吉亚语
+      - value: kk
+        label:
+          en_US: Kazakh
+          zh_Hans: 哈萨克语
+      - value: km
+        label:
+          en_US: Khmer
+          zh_Hans: 高棉语
+      - value: kn
+        label:
+          en_US: Kannada
+          zh_Hans: 卡纳达语
+      - value: ko
+        label:
+          en_US: Korean
+          zh_Hans: 韩语
+      - value: la
+        label:
+          en_US: Latin
+          zh_Hans: 拉丁语
+      - value: lb
+        label:
+          en_US: Luxembourgish
+          zh_Hans: 卢森堡语
+      - value: ln
+        label:
+          en_US: Lingala
+          zh_Hans: 林加拉语
+      - value: lo
+        label:
+          en_US: Lao
+          zh_Hans: 老挝语
+      - value: lt
+        label:
+          en_US: Lithuanian
+          zh_Hans: 立陶宛语
+      - value: lv
+        label:
+          en_US: Latvian
+          zh_Hans: 拉脱维亚语
+      - value: mg
+        label:
+          en_US: Malagasy
+          zh_Hans: 马尔加什语
+      - value: mi
+        label:
+          en_US: Maori
+          zh_Hans: 毛利语
+      - value: mk
+        label:
+          en_US: Macedonian
+          zh_Hans: 马其顿语
+      - value: ml
+        label:
+          en_US: Malayalam
+          zh_Hans: 马拉雅拉姆语
+      - value: mn
+        label:
+          en_US: Mongolian
+          zh_Hans: 蒙古语
+      - value: mr
+        label:
+          en_US: Marathi
+          zh_Hans: 马拉地语
+      - value: ms
+        label:
+          en_US: Malay
+          zh_Hans: 马来语
+      - value: mt
+        label:
+          en_US: Maltese
+          zh_Hans: 马耳他语
+      - value: my
+        label:
+          en_US: Burmese
+          zh_Hans: 缅甸语
+      - value: ne
+        label:
+          en_US: Nepali
+          zh_Hans: 尼泊尔语
+      - value: nl
+        label:
+          en_US: Dutch
+          zh_Hans: 荷兰语
+      - value: nn
+        label:
+          en_US: Norwegian Nynorsk
+          zh_Hans: 新挪威语
+      - value: no
+        label:
+          en_US: Norwegian
+          zh_Hans: 挪威语
+      - value: oc
+        label:
+          en_US: Occitan
+          zh_Hans: 奥克语
+      - value: pa
+        label:
+          en_US: Punjabi
+          zh_Hans: 旁遮普语
+      - value: pl
+        label:
+          en_US: Polish
+          zh_Hans: 波兰语
+      - value: ps
+        label:
+          en_US: Pashto
+          zh_Hans: 普什图语
+      - value: pt
+        label:
+          en_US: Portuguese
+          zh_Hans: 葡萄牙语
+      - value: ro
+        label:
+          en_US: Romanian
+          zh_Hans: 罗马尼亚语
+      - value: ru
+        label:
+          en_US: Russian
+          zh_Hans: 俄语
+      - value: sa
+        label:
+          en_US: Sanskrit
+          zh_Hans: 梵语
+      - value: sd
+        label:
+          en_US: Sindhi
+          zh_Hans: 信德语
+      - value: si
+        label:
+          en_US: Sinhala
+          zh_Hans: 僧伽罗语
+      - value: sk
+        label:
+          en_US: Slovak
+          zh_Hans: 斯洛伐克语
+      - value: sl
+        label:
+          en_US: Slovenian
+          zh_Hans: 斯洛文尼亚语
+      - value: sn
+        label:
+          en_US: Shona
+          zh_Hans: 修纳语
+      - value: so
+        label:
+          en_US: Somali
+          zh_Hans: 索马里语
+      - value: sq
+        label:
+          en_US: Albanian
+          zh_Hans: 阿尔巴尼亚语
+      - value: sr
+        label:
+          en_US: Serbian
+          zh_Hans: 塞尔维亚语
+      - value: su
+        label:
+          en_US: Sundanese
+          zh_Hans: 巽他语
+      - value: sv
+        label:
+          en_US: Swedish
+          zh_Hans: 瑞典语
+      - value: sw
+        label:
+          en_US: Swahili
+          zh_Hans: 斯瓦希里语
+      - value: ta
+        label:
+          en_US: Tamil
+          zh_Hans: 泰米尔语
+      - value: te
+        label:
+          en_US: Telugu
+          zh_Hans: 泰卢固语
+      - value: tg
+        label:
+          en_US: Tajik
+          zh_Hans: 塔吉克语
+      - value: th
+        label:
+          en_US: Thai
+          zh_Hans: 泰语
+      - value: tk
+        label:
+          en_US: Turkmen
+          zh_Hans: 土库曼语
+      - value: tl
+        label:
+          en_US: Tagalog
+          zh_Hans: 他加禄语
+      - value: tr
+        label:
+          en_US: Turkish
+          zh_Hans: 土耳其语
+      - value: tt
+        label:
+          en_US: Tatar
+          zh_Hans: 鞑靼语
+      - value: uk
+        label:
+          en_US: Ukrainian
+          zh_Hans: 乌克兰语
+      - value: ur
+        label:
+          en_US: Urdu
+          zh_Hans: 乌尔都语
+      - value: uz
+        label:
+          en_US: Uzbek
+          zh_Hans: 乌兹别克语
+      - value: vi
+        label:
+          en_US: Vietnamese
+          zh_Hans: 越南语
+      - value: yi
+        label:
+          en_US: Yiddish
+          zh_Hans: 意第绪语
+      - value: yo
+        label:
+          en_US: Yoruba
+          zh_Hans: 约鲁巴语
+      - value: yue
+        label:
+          en_US: Cantonese
+          zh_Hans: 粤语
+      - value: zh
+        label:
+          en_US: Chinese
+          zh_Hans: 中文
+  - name: chunk_level
+    type: select
+    label:
+      en_US: Chunk Level
+      zh_Hans: 分块级别
+    human_description:
+      en_US: "Choose how the transcription should be divided into chunks"
+      zh_Hans: "选择如何将转录内容分成块"
+    llm_description: "Level of the chunks to return."
+    form: form
+    default: segment
+    options:
+      - value: segment
+        label:
+          en_US: Segment
+          zh_Hans: 段
+  - name: version
+    type: select
+    label:
+      en_US: Version
+      zh_Hans: 版本
+    human_description:
+      en_US: "Select which version of the Whisper large model to use"
+      zh_Hans: "选择要使用的 Whisper large 模型版本"
+    llm_description: "Version of the model to use. All of the models are the Whisper large variant."
+    form: form
+    default: "3"
+    options:
+      - value: "3"
+        label:
+          en_US: Version 3
+          zh_Hans: 版本 3

api/core/workflow/nodes/http_request/node.py

@@ -107,6 +107,7 @@ class HttpRequestNode(BaseNode[HttpRequestNodeData]):
         node_data: HttpRequestNodeData,
     ) -> Mapping[str, Sequence[str]]:
         selectors: list[VariableSelector] = []
+        selectors += variable_template_parser.extract_selectors_from_template(node_data.url)
         selectors += variable_template_parser.extract_selectors_from_template(node_data.headers)
         selectors += variable_template_parser.extract_selectors_from_template(node_data.params)
         if node_data.body:

api/core/workflow/nodes/tool/tool_node.py

@@ -1,5 +1,4 @@
 from collections.abc import Mapping, Sequence
-from os import path
 from typing import Any
 
 from sqlalchemy import select
@@ -180,7 +179,6 @@ class ToolNode(BaseNode[ToolNodeData]):
         for response in tool_response:
             if response.type in {ToolInvokeMessage.MessageType.IMAGE_LINK, ToolInvokeMessage.MessageType.IMAGE}:
                 url = str(response.message) if response.message else None
-                ext = path.splitext(url)[1] if url else ".bin"
                 tool_file_id = str(url).split("/")[-1].split(".")[0]
                 transfer_method = response.meta.get("transfer_method", FileTransferMethod.TOOL_FILE)
 
@@ -202,7 +200,6 @@ class ToolNode(BaseNode[ToolNodeData]):
                 )
                 result.append(file)
             elif response.type == ToolInvokeMessage.MessageType.BLOB:
-                # get tool file id
                 tool_file_id = str(response.message).split("/")[-1].split(".")[0]
                 with Session(db.engine) as session:
                     stmt = select(ToolFile).where(ToolFile.id == tool_file_id)
@@ -211,7 +208,6 @@ class ToolNode(BaseNode[ToolNodeData]):
                         raise ValueError(f"tool file {tool_file_id} not exists")
                 mapping = {
                     "tool_file_id": tool_file_id,
-                    "type": FileType.IMAGE,
                     "transfer_method": FileTransferMethod.TOOL_FILE,
                 }
                 file = file_factory.build_from_mapping(
@@ -228,13 +224,8 @@ class ToolNode(BaseNode[ToolNodeData]):
                     tool_file = session.scalar(stmt)
                     if tool_file is None:
                         raise ToolFileError(f"Tool file {tool_file_id} does not exist")
-                if "." in url:
-                    extension = "." + url.split("/")[-1].split(".")[1]
-                else:
-                    extension = ".bin"
                 mapping = {
                     "tool_file_id": tool_file_id,
-                    "type": FileType.IMAGE,
                     "transfer_method": transfer_method,
                     "url": url,
                 }

api/factories/file_factory.py

@@ -180,6 +180,20 @@ def _get_remote_file_info(url: str):
     return mime_type, filename, file_size
 
 
+def _get_file_type_by_mimetype(mime_type: str) -> FileType:
+    if "image" in mime_type:
+        file_type = FileType.IMAGE
+    elif "video" in mime_type:
+        file_type = FileType.VIDEO
+    elif "audio" in mime_type:
+        file_type = FileType.AUDIO
+    elif "text" in mime_type or "pdf" in mime_type:
+        file_type = FileType.DOCUMENT
+    else:
+        file_type = FileType.CUSTOM
+    return file_type
+
+
 def _build_from_tool_file(
     *,
     mapping: Mapping[str, Any],
@@ -199,12 +213,13 @@ def _build_from_tool_file(
         raise ValueError(f"ToolFile {mapping.get('tool_file_id')} not found")
 
     extension = "." + tool_file.file_key.split(".")[-1] if "." in tool_file.file_key else ".bin"
+    file_type = mapping.get("type", _get_file_type_by_mimetype(tool_file.mimetype))
 
     return File(
         id=mapping.get("id"),
         tenant_id=tenant_id,
         filename=tool_file.name,
-        type=FileType.value_of(mapping.get("type")),
+        type=file_type,
         transfer_method=transfer_method,
         remote_url=tool_file.original_url,
         related_id=tool_file.id,

api/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -932,6 +932,10 @@ files = [
     {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a37b8f0391212d29b3a91a799c8e4a2855e0576911cdfb2515487e30e322253d"},
     {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:e84799f09591700a4154154cab9787452925578841a94321d5ee8fb9a9a328f0"},
     {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:f66b5337fa213f1da0d9000bc8dc0cb5b896b726eefd9c6046f699b169c41b9e"},
+    {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:5dab0844f2cf82be357a0eb11a9087f70c5430b2c241493fc122bb6f2bb0917c"},
+    {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:e4fe605b917c70283db7dfe5ada75e04561479075761a0b3866c081d035b01c1"},
+    {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:1e9a65b5736232e7a7f91ff3d02277f11d339bf34099a56cdab6a8b3410a02b2"},
+    {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:58d4b711689366d4a03ac7957ab8c28890415e267f9b6589969e74b6e42225ec"},
     {file = "Brotli-1.1.0-cp310-cp310-win32.whl", hash = "sha256:be36e3d172dc816333f33520154d708a2657ea63762ec16b62ece02ab5e4daf2"},
     {file = "Brotli-1.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:0c6244521dda65ea562d5a69b9a26120769b7a9fb3db2fe9545935ed6735b128"},
     {file = "Brotli-1.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:a3daabb76a78f829cafc365531c972016e4aa8d5b4bf60660ad8ecee19df7ccc"},
@@ -944,8 +948,14 @@ files = [
     {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:19c116e796420b0cee3da1ccec3b764ed2952ccfcc298b55a10e5610ad7885f9"},
     {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:510b5b1bfbe20e1a7b3baf5fed9e9451873559a976c1a78eebaa3b86c57b4265"},
     {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a1fd8a29719ccce974d523580987b7f8229aeace506952fa9ce1d53a033873c8"},
+    {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c247dd99d39e0338a604f8c2b3bc7061d5c2e9e2ac7ba9cc1be5a69cb6cd832f"},
+    {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:1b2c248cd517c222d89e74669a4adfa5577e06ab68771a529060cf5a156e9757"},
+    {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:2a24c50840d89ded6c9a8fdc7b6ed3692ed4e86f1c4a4a938e1e92def92933e0"},
+    {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:f31859074d57b4639318523d6ffdca586ace54271a73ad23ad021acd807eb14b"},
     {file = "Brotli-1.1.0-cp311-cp311-win32.whl", hash = "sha256:39da8adedf6942d76dc3e46653e52df937a3c4d6d18fdc94a7c29d263b1f5b50"},
     {file = "Brotli-1.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:aac0411d20e345dc0920bdec5548e438e999ff68d77564d5e9463a7ca9d3e7b1"},
+    {file = "Brotli-1.1.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:32d95b80260d79926f5fab3c41701dbb818fde1c9da590e77e571eefd14abe28"},
+    {file = "Brotli-1.1.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:b760c65308ff1e462f65d69c12e4ae085cff3b332d894637f6273a12a482d09f"},
     {file = "Brotli-1.1.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:316cc9b17edf613ac76b1f1f305d2a748f1b976b033b049a6ecdfd5612c70409"},
     {file = "Brotli-1.1.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:caf9ee9a5775f3111642d33b86237b05808dafcd6268faa492250e9b78046eb2"},
     {file = "Brotli-1.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:70051525001750221daa10907c77830bc889cb6d865cc0b813d9db7fefc21451"},
@@ -956,8 +966,24 @@ files = [
     {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:4093c631e96fdd49e0377a9c167bfd75b6d0bad2ace734c6eb20b348bc3ea180"},
     {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:7e4c4629ddad63006efa0ef968c8e4751c5868ff0b1c5c40f76524e894c50248"},
     {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:861bf317735688269936f755fa136a99d1ed526883859f86e41a5d43c61d8966"},
+    {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:87a3044c3a35055527ac75e419dfa9f4f3667a1e887ee80360589eb8c90aabb9"},
+    {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:c5529b34c1c9d937168297f2c1fde7ebe9ebdd5e121297ff9c043bdb2ae3d6fb"},
+    {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:ca63e1890ede90b2e4454f9a65135a4d387a4585ff8282bb72964fab893f2111"},
+    {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e79e6520141d792237c70bcd7a3b122d00f2613769ae0cb61c52e89fd3443839"},
     {file = "Brotli-1.1.0-cp312-cp312-win32.whl", hash = "sha256:5f4d5ea15c9382135076d2fb28dde923352fe02951e66935a9efaac8f10e81b0"},
     {file = "Brotli-1.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:906bc3a79de8c4ae5b86d3d75a8b77e44404b0f4261714306e3ad248d8ab0951"},
+    {file = "Brotli-1.1.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:8bf32b98b75c13ec7cf774164172683d6e7891088f6316e54425fde1efc276d5"},
+    {file = "Brotli-1.1.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7bc37c4d6b87fb1017ea28c9508b36bbcb0c3d18b4260fcdf08b200c74a6aee8"},
+    {file = "Brotli-1.1.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3c0ef38c7a7014ffac184db9e04debe495d317cc9c6fb10071f7fefd93100a4f"},
+    {file = "Brotli-1.1.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:91d7cc2a76b5567591d12c01f019dd7afce6ba8cba6571187e21e2fc418ae648"},
+    {file = "Brotli-1.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a93dde851926f4f2678e704fadeb39e16c35d8baebd5252c9fd94ce8ce68c4a0"},
+    {file = "Brotli-1.1.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f0db75f47be8b8abc8d9e31bc7aad0547ca26f24a54e6fd10231d623f183d089"},
+    {file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:6967ced6730aed543b8673008b5a391c3b1076d834ca438bbd70635c73775368"},
+    {file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:7eedaa5d036d9336c95915035fb57422054014ebdeb6f3b42eac809928e40d0c"},
+    {file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:d487f5432bf35b60ed625d7e1b448e2dc855422e87469e3f450aa5552b0eb284"},
+    {file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:832436e59afb93e1836081a20f324cb185836c617659b07b129141a8426973c7"},
+    {file = "Brotli-1.1.0-cp313-cp313-win32.whl", hash = "sha256:43395e90523f9c23a3d5bdf004733246fba087f2948f87ab28015f12359ca6a0"},
+    {file = "Brotli-1.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:9011560a466d2eb3f5a6e4929cf4a09be405c64154e12df0dd72713f6500e32b"},
     {file = "Brotli-1.1.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:a090ca607cbb6a34b0391776f0cb48062081f5f60ddcce5d11838e67a01928d1"},
     {file = "Brotli-1.1.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2de9d02f5bda03d27ede52e8cfe7b865b066fa49258cbab568720aa5be80a47d"},
     {file = "Brotli-1.1.0-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2333e30a5e00fe0fe55903c8832e08ee9c3b1382aacf4db26664a16528d51b4b"},
@@ -967,6 +993,10 @@ files = [
     {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:fd5f17ff8f14003595ab414e45fce13d073e0762394f957182e69035c9f3d7c2"},
     {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:069a121ac97412d1fe506da790b3e69f52254b9df4eb665cd42460c837193354"},
     {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:e93dfc1a1165e385cc8239fab7c036fb2cd8093728cbd85097b284d7b99249a2"},
+    {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_aarch64.whl", hash = "sha256:aea440a510e14e818e67bfc4027880e2fb500c2ccb20ab21c7a7c8b5b4703d75"},
+    {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_i686.whl", hash = "sha256:6974f52a02321b36847cd19d1b8e381bf39939c21efd6ee2fc13a28b0d99348c"},
+    {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_ppc64le.whl", hash = "sha256:a7e53012d2853a07a4a79c00643832161a910674a893d296c9f1259859a289d2"},
+    {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:d7702622a8b40c49bffb46e1e3ba2e81268d5c04a34f460978c6b5517a34dd52"},
     {file = "Brotli-1.1.0-cp36-cp36m-win32.whl", hash = "sha256:a599669fd7c47233438a56936988a2478685e74854088ef5293802123b5b2460"},
     {file = "Brotli-1.1.0-cp36-cp36m-win_amd64.whl", hash = "sha256:d143fd47fad1db3d7c27a1b1d66162e855b5d50a89666af46e1679c496e8e579"},
     {file = "Brotli-1.1.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:11d00ed0a83fa22d29bc6b64ef636c4552ebafcef57154b4ddd132f5638fbd1c"},
@@ -978,6 +1008,10 @@ files = [
     {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:919e32f147ae93a09fe064d77d5ebf4e35502a8df75c29fb05788528e330fe74"},
     {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:23032ae55523cc7bccb4f6a0bf368cd25ad9bcdcc1990b64a647e7bbcce9cb5b"},
     {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:224e57f6eac61cc449f498cc5f0e1725ba2071a3d4f48d5d9dffba42db196438"},
+    {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:cb1dac1770878ade83f2ccdf7d25e494f05c9165f5246b46a621cc849341dc01"},
+    {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_i686.whl", hash = "sha256:3ee8a80d67a4334482d9712b8e83ca6b1d9bc7e351931252ebef5d8f7335a547"},
+    {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_ppc64le.whl", hash = "sha256:5e55da2c8724191e5b557f8e18943b1b4839b8efc3ef60d65985bcf6f587dd38"},
+    {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:d342778ef319e1026af243ed0a07c97acf3bad33b9f29e7ae6a1f68fd083e90c"},
     {file = "Brotli-1.1.0-cp37-cp37m-win32.whl", hash = "sha256:587ca6d3cef6e4e868102672d3bd9dc9698c309ba56d41c2b9c85bbb903cdb95"},
     {file = "Brotli-1.1.0-cp37-cp37m-win_amd64.whl", hash = "sha256:2954c1c23f81c2eaf0b0717d9380bd348578a94161a65b3a2afc62c86467dd68"},
     {file = "Brotli-1.1.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:efa8b278894b14d6da122a72fefcebc28445f2d3f880ac59d46c90f4c13be9a3"},
@@ -990,6 +1024,10 @@ files = [
     {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:1ab4fbee0b2d9098c74f3057b2bc055a8bd92ccf02f65944a241b4349229185a"},
     {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:141bd4d93984070e097521ed07e2575b46f817d08f9fa42b16b9b5f27b5ac088"},
     {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:fce1473f3ccc4187f75b4690cfc922628aed4d3dd013d047f95a9b3919a86596"},
+    {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:d2b35ca2c7f81d173d2fadc2f4f31e88cc5f7a39ae5b6db5513cf3383b0e0ec7"},
+    {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:af6fa6817889314555aede9a919612b23739395ce767fe7fcbea9a80bf140fe5"},
+    {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:2feb1d960f760a575dbc5ab3b1c00504b24caaf6986e2dc2b01c09c87866a943"},
+    {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:4410f84b33374409552ac9b6903507cdb31cd30d2501fc5ca13d18f73548444a"},
     {file = "Brotli-1.1.0-cp38-cp38-win32.whl", hash = "sha256:db85ecf4e609a48f4b29055f1e144231b90edc90af7481aa731ba2d059226b1b"},
     {file = "Brotli-1.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:3d7954194c36e304e1523f55d7042c59dc53ec20dd4e9ea9d151f1b62b4415c0"},
     {file = "Brotli-1.1.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:5fb2ce4b8045c78ebbc7b8f3c15062e435d47e7393cc57c25115cfd49883747a"},
@@ -1002,6 +1040,10 @@ files = [
     {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:949f3b7c29912693cee0afcf09acd6ebc04c57af949d9bf77d6101ebb61e388c"},
     {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:89f4988c7203739d48c6f806f1e87a1d96e0806d44f0fba61dba81392c9e474d"},
     {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:de6551e370ef19f8de1807d0a9aa2cdfdce2e85ce88b122fe9f6b2b076837e59"},
+    {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:0737ddb3068957cf1b054899b0883830bb1fec522ec76b1098f9b6e0f02d9419"},
+    {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:4f3607b129417e111e30637af1b56f24f7a49e64763253bbc275c75fa887d4b2"},
+    {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:6c6e0c425f22c1c719c42670d561ad682f7bfeeef918edea971a79ac5252437f"},
+    {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:494994f807ba0b92092a163a0a283961369a65f6cbe01e8891132b7a320e61eb"},
     {file = "Brotli-1.1.0-cp39-cp39-win32.whl", hash = "sha256:f0d8a7a6b5983c2496e364b969f0e526647a06b075d034f3297dc66f3b360c64"},
     {file = "Brotli-1.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:cdad5b9014d83ca68c25d2e9444e28e967ef16e80f6b436918c700c117a85467"},
     {file = "Brotli-1.1.0.tar.gz", hash = "sha256:81de08ac11bcb85841e440c13611c00b67d3bf82698314928d0b676362546724"},
@@ -2411,6 +2453,26 @@ files = [
 [package.extras]
 test = ["pytest (>=6)"]
 
+[[package]]
+name = "fal-client"
+version = "0.5.6"
+description = "Python client for fal.ai"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "fal_client-0.5.6-py3-none-any.whl", hash = "sha256:631fd857a3c44753ee46a2eea1e7276471453aca58faac9c3702f744c7c84050"},
+    {file = "fal_client-0.5.6.tar.gz", hash = "sha256:d3afc4b6250023d0ee8437ec504558231d3b106d7aabc12cda8c39883faddecb"},
+]
+
+[package.dependencies]
+httpx = ">=0.21.0,<1"
+httpx-sse = ">=0.4.0,<0.5"
+
+[package.extras]
+dev = ["fal-client[docs,test]"]
+docs = ["sphinx", "sphinx-autodoc-typehints", "sphinx-rtd-theme"]
+test = ["pillow", "pytest", "pytest-asyncio"]
+
 [[package]]
 name = "fastapi"
 version = "0.115.4"
@@ -4049,6 +4111,17 @@ http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
 zstd = ["zstandard (>=0.18.0)"]
 
+[[package]]
+name = "httpx-sse"
+version = "0.4.0"
+description = "Consume Server-Sent Event (SSE) messages with HTTPX."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "httpx-sse-0.4.0.tar.gz", hash = "sha256:1e81a3a3070ce322add1d3529ed42eb5f70817f45ed6ec915ab753f961139721"},
+    {file = "httpx_sse-0.4.0-py3-none-any.whl", hash = "sha256:f329af6eae57eaa2bdfd962b42524764af68075ea87370a2de920af5341e318f"},
+]
+
 [[package]]
 name = "huggingface-hub"
 version = "0.16.4"
@@ -8466,29 +8539,29 @@ pyasn1 = ">=0.1.3"
 
 [[package]]
 name = "ruff"
-version = "0.6.9"
+version = "0.7.3"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "ruff-0.6.9-py3-none-linux_armv6l.whl", hash = "sha256:064df58d84ccc0ac0fcd63bc3090b251d90e2a372558c0f057c3f75ed73e1ccd"},
-    {file = "ruff-0.6.9-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:140d4b5c9f5fc7a7b074908a78ab8d384dd7f6510402267bc76c37195c02a7ec"},
-    {file = "ruff-0.6.9-py3-none-macosx_11_0_arm64.whl", hash = "sha256:53fd8ca5e82bdee8da7f506d7b03a261f24cd43d090ea9db9a1dc59d9313914c"},
-    {file = "ruff-0.6.9-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:645d7d8761f915e48a00d4ecc3686969761df69fb561dd914a773c1a8266e14e"},
-    {file = "ruff-0.6.9-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:eae02b700763e3847595b9d2891488989cac00214da7f845f4bcf2989007d577"},
-    {file = "ruff-0.6.9-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7d5ccc9e58112441de8ad4b29dcb7a86dc25c5f770e3c06a9d57e0e5eba48829"},
-    {file = "ruff-0.6.9-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:417b81aa1c9b60b2f8edc463c58363075412866ae4e2b9ab0f690dc1e87ac1b5"},
-    {file = "ruff-0.6.9-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3c866b631f5fbce896a74a6e4383407ba7507b815ccc52bcedabb6810fdb3ef7"},
-    {file = "ruff-0.6.9-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7b118afbb3202f5911486ad52da86d1d52305b59e7ef2031cea3425142b97d6f"},
-    {file = "ruff-0.6.9-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a67267654edc23c97335586774790cde402fb6bbdb3c2314f1fc087dee320bfa"},
-    {file = "ruff-0.6.9-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:3ef0cc774b00fec123f635ce5c547dac263f6ee9fb9cc83437c5904183b55ceb"},
-    {file = "ruff-0.6.9-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:12edd2af0c60fa61ff31cefb90aef4288ac4d372b4962c2864aeea3a1a2460c0"},
-    {file = "ruff-0.6.9-py3-none-musllinux_1_2_i686.whl", hash = "sha256:55bb01caeaf3a60b2b2bba07308a02fca6ab56233302406ed5245180a05c5625"},
-    {file = "ruff-0.6.9-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:925d26471fa24b0ce5a6cdfab1bb526fb4159952385f386bdcc643813d472039"},
-    {file = "ruff-0.6.9-py3-none-win32.whl", hash = "sha256:eb61ec9bdb2506cffd492e05ac40e5bc6284873aceb605503d8494180d6fc84d"},
-    {file = "ruff-0.6.9-py3-none-win_amd64.whl", hash = "sha256:785d31851c1ae91f45b3d8fe23b8ae4b5170089021fbb42402d811135f0b7117"},
-    {file = "ruff-0.6.9-py3-none-win_arm64.whl", hash = "sha256:a9641e31476d601f83cd602608739a0840e348bda93fec9f1ee816f8b6798b93"},
-    {file = "ruff-0.6.9.tar.gz", hash = "sha256:b076ef717a8e5bc819514ee1d602bbdca5b4420ae13a9cf61a0c0a4f53a2baa2"},
+    {file = "ruff-0.7.3-py3-none-linux_armv6l.whl", hash = "sha256:34f2339dc22687ec7e7002792d1f50712bf84a13d5152e75712ac08be565d344"},
+    {file = "ruff-0.7.3-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:fb397332a1879b9764a3455a0bb1087bda876c2db8aca3a3cbb67b3dbce8cda0"},
+    {file = "ruff-0.7.3-py3-none-macosx_11_0_arm64.whl", hash = "sha256:37d0b619546103274e7f62643d14e1adcbccb242efda4e4bdb9544d7764782e9"},
+    {file = "ruff-0.7.3-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d59f0c3ee4d1a6787614e7135b72e21024875266101142a09a61439cb6e38a5"},
+    {file = "ruff-0.7.3-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:44eb93c2499a169d49fafd07bc62ac89b1bc800b197e50ff4633aed212569299"},
+    {file = "ruff-0.7.3-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6d0242ce53f3a576c35ee32d907475a8d569944c0407f91d207c8af5be5dae4e"},
+    {file = "ruff-0.7.3-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:6b6224af8b5e09772c2ecb8dc9f3f344c1aa48201c7f07e7315367f6dd90ac29"},
+    {file = "ruff-0.7.3-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c50f95a82b94421c964fae4c27c0242890a20fe67d203d127e84fbb8013855f5"},
+    {file = "ruff-0.7.3-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7f3eff9961b5d2644bcf1616c606e93baa2d6b349e8aa8b035f654df252c8c67"},
+    {file = "ruff-0.7.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b8963cab06d130c4df2fd52c84e9f10d297826d2e8169ae0c798b6221be1d1d2"},
+    {file = "ruff-0.7.3-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:61b46049d6edc0e4317fb14b33bd693245281a3007288b68a3f5b74a22a0746d"},
+    {file = "ruff-0.7.3-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:10ebce7696afe4644e8c1a23b3cf8c0f2193a310c18387c06e583ae9ef284de2"},
+    {file = "ruff-0.7.3-py3-none-musllinux_1_2_i686.whl", hash = "sha256:3f36d56326b3aef8eeee150b700e519880d1aab92f471eefdef656fd57492aa2"},
+    {file = "ruff-0.7.3-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:5d024301109a0007b78d57ab0ba190087b43dce852e552734ebf0b0b85e4fb16"},
+    {file = "ruff-0.7.3-py3-none-win32.whl", hash = "sha256:4ba81a5f0c5478aa61674c5a2194de8b02652f17addf8dfc40c8937e6e7d79fc"},
+    {file = "ruff-0.7.3-py3-none-win_amd64.whl", hash = "sha256:588a9ff2fecf01025ed065fe28809cd5a53b43505f48b69a1ac7707b1b7e4088"},
+    {file = "ruff-0.7.3-py3-none-win_arm64.whl", hash = "sha256:1713e2c5545863cdbfe2cbce21f69ffaf37b813bfd1fb3b90dc9a6f1963f5a8c"},
+    {file = "ruff-0.7.3.tar.gz", hash = "sha256:e1d1ba2e40b6e71a61b063354d04be669ab0d39c352461f3d789cac68b54a313"},
 ]
 
 [[package]]
@@ -11005,4 +11078,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<3.13"
-content-hash = "f20bd678044926913dbbc24bd0cf22503a75817aa55f59457ff7822032139b77"
+content-hash = "2ba4b464eebc26598f290fa94713acc44c588f902176e6efa80622911d40f0ac"

api/pyproject.toml

@@ -122,6 +122,7 @@ celery = "~5.4.0"
 chardet = "~5.1.0"
 cohere = "~5.2.4"
 dashscope = { version = "~1.17.0", extras = ["tokenizer"] }
+fal-client = "0.5.6"
 flask = "~3.0.1"
 flask-compress = "~1.14"
 flask-cors = "~4.0.0"
@@ -278,4 +279,4 @@ pytest-mock = "~3.14.0"
 optional = true
 [tool.poetry.group.lint.dependencies]
 dotenv-linter = "~0.5.0"
-ruff = "~0.6.9"
+ruff = "~0.7.3"

api/services/dataset_service.py

@@ -1458,6 +1458,7 @@ class SegmentService:
             pre_segment_data_list = []
             segment_data_list = []
             keywords_list = []
+            position = max_position + 1 if max_position else 1
             for segment_item in segments:
                 content = segment_item["content"]
                 doc_id = str(uuid.uuid4())
@@ -1475,7 +1476,7 @@ class SegmentService:
                     document_id=document.id,
                     index_node_id=doc_id,
                     index_node_hash=segment_hash,
-                    position=max_position + 1 if max_position else 1,
+                    position=position,
                     content=content,
                     word_count=len(content),
                     tokens=tokens,
@@ -1490,6 +1491,7 @@ class SegmentService:
                 increment_word_count += segment_document.word_count
                 db.session.add(segment_document)
                 segment_data_list.append(segment_document)
+                position += 1
 
                 pre_segment_data_list.append(segment_document)
                 if "keywords" in segment_item:

api/tests/integration_tests/vdb/__mock/baiduvectordb.py

@@ -1,4 +1,5 @@
 import os
+from collections import UserDict
 from unittest.mock import MagicMock
 
 import pytest
@@ -11,7 +12,7 @@ from pymochow.model.table import Table
 from requests.adapters import HTTPAdapter
 
 
-class AttrDict(dict):
+class AttrDict(UserDict):
     def __getattr__(self, item):
         return self.get(item)
 

api/tests/integration_tests/vdb/__mock/upstashvectordb.py

@@ -1,4 +1,5 @@
 import os
+from collections import UserDict
 from typing import Optional
 
 import pytest
@@ -50,7 +51,7 @@ class MockIndex:
         return AttrDict({"dimension": 1024})
 
 
-class AttrDict(dict):
+class AttrDict(UserDict):
     def __getattr__(self, item):
         return self.get(item)
 

api/tests/unit_tests/core/workflow/nodes/test_document_extractor_node.py

@@ -140,10 +140,10 @@ def test_extract_text_from_plain_text():
     assert text == "Hello, world!"
 
 
-def tet_extract_text_from_plain_text_non_utf8():
+def test_extract_text_from_plain_text_non_utf8():
     import tempfile
 
-    non_utf8_content = b"Hello world\xa9."  # \xA9 represents © in Latin-1
+    non_utf8_content = b"Hello, world\xa9."  # \xA9 represents © in Latin-1
     with tempfile.NamedTemporaryFile(delete=True) as temp_file:
         temp_file.write(non_utf8_content)
         temp_file.seek(0)

api/tests/unit_tests/oss/__mock/volcengine_tos.py

@@ -1,4 +1,5 @@
 import os
+from collections import UserDict
 from unittest.mock import MagicMock
 
 import pytest
@@ -14,7 +15,7 @@ from tests.unit_tests.oss.__mock.base import (
 )
 
 
-class AttrDict(dict):
+class AttrDict(UserDict):
     def __getattr__(self, item):
         return self.get(item)
 

web/Dockerfile

@@ -1,5 +1,5 @@
 # base image
-FROM node:20.11-alpine3.19 AS base
+FROM node:20-alpine3.20 AS base
 LABEL maintainer="takatost@gmail.com"
 
 # if you located in China, you can use aliyun mirror to speed up

web/i18n/pt-BR/app-log.ts

@@ -86,8 +86,8 @@ const translation = {
   agenteLogDetail: {
     agentMode: 'Modo Agente',
     toolUsed: 'Ferramenta usada',
-    iterações: 'Iterações',
-    iteração: 'Iteração',
+    iterations: 'Iterações',
+    iteration: 'Iteração',
     finalProcessing: 'Processamento Final',
   },
   agentLogDetail: {