diff --git a/api/core/model_runtime/model_providers/bedrock/llm/amazon.nova-lite-v1.yaml b/api/core/model_runtime/model_providers/bedrock/llm/amazon.nova-lite-v1.yaml new file mode 100644 index 0000000000..ccc866ca49 --- /dev/null +++ b/api/core/model_runtime/model_providers/bedrock/llm/amazon.nova-lite-v1.yaml @@ -0,0 +1,52 @@ +model: amazon.nova-lite-v1:0 +label: + en_US: Nova Lite V1 +model_type: llm +features: + - agent-thought + - tool-call + - stream-tool-call +model_properties: + mode: chat + context_size: 300000 +parameter_rules: + - name: max_new_tokens + use_template: max_tokens + required: true + default: 2048 + min: 1 + max: 5000 + - name: temperature + use_template: temperature + required: false + type: float + default: 1 + min: 0.0 + max: 1.0 + help: + zh_Hans: 生成内容的随机性。 + en_US: The amount of randomness injected into the response. + - name: top_p + required: false + type: float + default: 0.999 + min: 0.000 + max: 1.000 + help: + zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。 + en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both. + - name: top_k + required: false + type: int + default: 0 + min: 0 + # tip docs from aws has error, max value is 500 + max: 500 + help: + zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。 + en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses. +pricing: + input: '0.0008' + output: '0.0016' + unit: '0.001' + currency: USD diff --git a/api/core/model_runtime/model_providers/bedrock/llm/amazon.nova-micro-v1.yaml b/api/core/model_runtime/model_providers/bedrock/llm/amazon.nova-micro-v1.yaml new file mode 100644 index 0000000000..96d9c6075c --- /dev/null +++ b/api/core/model_runtime/model_providers/bedrock/llm/amazon.nova-micro-v1.yaml @@ -0,0 +1,52 @@ +model: amazon.nova-micro-v1:0 +label: + en_US: Nova Micro V1 +model_type: llm +features: + - agent-thought + - tool-call + - stream-tool-call +model_properties: + mode: chat + context_size: 128000 +parameter_rules: + - name: max_new_tokens + use_template: max_tokens + required: true + default: 2048 + min: 1 + max: 5000 + - name: temperature + use_template: temperature + required: false + type: float + default: 1 + min: 0.0 + max: 1.0 + help: + zh_Hans: 生成内容的随机性。 + en_US: The amount of randomness injected into the response. + - name: top_p + required: false + type: float + default: 0.999 + min: 0.000 + max: 1.000 + help: + zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。 + en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both. + - name: top_k + required: false + type: int + default: 0 + min: 0 + # tip docs from aws has error, max value is 500 + max: 500 + help: + zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。 + en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses. +pricing: + input: '0.0008' + output: '0.0016' + unit: '0.001' + currency: USD diff --git a/api/core/model_runtime/model_providers/bedrock/llm/amazon.nova-pro-v1.yaml b/api/core/model_runtime/model_providers/bedrock/llm/amazon.nova-pro-v1.yaml new file mode 100644 index 0000000000..ce6c57c66b --- /dev/null +++ b/api/core/model_runtime/model_providers/bedrock/llm/amazon.nova-pro-v1.yaml @@ -0,0 +1,52 @@ +model: amazon.nova-pro-v1:0 +label: + en_US: Nova Pro V1 +model_type: llm +features: + - agent-thought + - tool-call + - stream-tool-call +model_properties: + mode: chat + context_size: 300000 +parameter_rules: + - name: max_new_tokens + use_template: max_tokens + required: true + default: 2048 + min: 1 + max: 5000 + - name: temperature + use_template: temperature + required: false + type: float + default: 1 + min: 0.0 + max: 1.0 + help: + zh_Hans: 生成内容的随机性。 + en_US: The amount of randomness injected into the response. + - name: top_p + required: false + type: float + default: 0.999 + min: 0.000 + max: 1.000 + help: + zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。 + en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both. + - name: top_k + required: false + type: int + default: 0 + min: 0 + # tip docs from aws has error, max value is 500 + max: 500 + help: + zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。 + en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses. +pricing: + input: '0.0008' + output: '0.0016' + unit: '0.001' + currency: USD diff --git a/api/core/model_runtime/model_providers/bedrock/llm/llm.py b/api/core/model_runtime/model_providers/bedrock/llm/llm.py index ef4dfaf6f1..62fd6201f0 100644 --- a/api/core/model_runtime/model_providers/bedrock/llm/llm.py +++ b/api/core/model_runtime/model_providers/bedrock/llm/llm.py @@ -70,6 +70,8 @@ class BedrockLargeLanguageModel(LargeLanguageModel): {"prefix": "cohere.command-r", "support_system_prompts": True, "support_tool_use": True}, {"prefix": "amazon.titan", "support_system_prompts": False, "support_tool_use": False}, {"prefix": "ai21.jamba-1-5", "support_system_prompts": True, "support_tool_use": False}, + {"prefix": "amazon.nova", "support_system_prompts": True, "support_tool_use": False}, + {"prefix": "us.amazon.nova", "support_system_prompts": True, "support_tool_use": False}, ] @staticmethod diff --git a/api/core/model_runtime/model_providers/bedrock/llm/us.amazon.nova-lite-v1.yaml b/api/core/model_runtime/model_providers/bedrock/llm/us.amazon.nova-lite-v1.yaml new file mode 100644 index 0000000000..c8b5012f45 --- /dev/null +++ b/api/core/model_runtime/model_providers/bedrock/llm/us.amazon.nova-lite-v1.yaml @@ -0,0 +1,52 @@ +model: us.amazon.nova-lite-v1:0 +label: + en_US: Nova Lite V1 (US.Cross Region Inference) +model_type: llm +features: + - agent-thought + - tool-call + - stream-tool-call +model_properties: + mode: chat + context_size: 300000 +parameter_rules: + - name: max_new_tokens + use_template: max_tokens + required: true + default: 2048 + min: 1 + max: 5000 + - name: temperature + use_template: temperature + required: false + type: float + default: 1 + min: 0.0 + max: 1.0 + help: + zh_Hans: 生成内容的随机性。 + en_US: The amount of randomness injected into the response. + - name: top_p + required: false + type: float + default: 0.999 + min: 0.000 + max: 1.000 + help: + zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。 + en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both. + - name: top_k + required: false + type: int + default: 0 + min: 0 + # tip docs from aws has error, max value is 500 + max: 500 + help: + zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。 + en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses. +pricing: + input: '0.0008' + output: '0.0016' + unit: '0.001' + currency: USD diff --git a/api/core/model_runtime/model_providers/bedrock/llm/us.amazon.nova-micro-v1.yaml b/api/core/model_runtime/model_providers/bedrock/llm/us.amazon.nova-micro-v1.yaml new file mode 100644 index 0000000000..cb56f5d736 --- /dev/null +++ b/api/core/model_runtime/model_providers/bedrock/llm/us.amazon.nova-micro-v1.yaml @@ -0,0 +1,52 @@ +model: us.amazon.nova-micro-v1:0 +label: + en_US: Nova Micro V1 (US.Cross Region Inference) +model_type: llm +features: + - agent-thought + - tool-call + - stream-tool-call +model_properties: + mode: chat + context_size: 128000 +parameter_rules: + - name: max_new_tokens + use_template: max_tokens + required: true + default: 2048 + min: 1 + max: 5000 + - name: temperature + use_template: temperature + required: false + type: float + default: 1 + min: 0.0 + max: 1.0 + help: + zh_Hans: 生成内容的随机性。 + en_US: The amount of randomness injected into the response. + - name: top_p + required: false + type: float + default: 0.999 + min: 0.000 + max: 1.000 + help: + zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。 + en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both. + - name: top_k + required: false + type: int + default: 0 + min: 0 + # tip docs from aws has error, max value is 500 + max: 500 + help: + zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。 + en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses. +pricing: + input: '0.0008' + output: '0.0016' + unit: '0.001' + currency: USD diff --git a/api/core/model_runtime/model_providers/bedrock/llm/us.amazon.nova-pro-v1.yaml b/api/core/model_runtime/model_providers/bedrock/llm/us.amazon.nova-pro-v1.yaml new file mode 100644 index 0000000000..8b69544816 --- /dev/null +++ b/api/core/model_runtime/model_providers/bedrock/llm/us.amazon.nova-pro-v1.yaml @@ -0,0 +1,52 @@ +model: us.amazon.nova-pro-v1:0 +label: + en_US: Nova Pro V1 (US.Cross Region Inference) +model_type: llm +features: + - agent-thought + - tool-call + - stream-tool-call +model_properties: + mode: chat + context_size: 300000 +parameter_rules: + - name: max_new_tokens + use_template: max_tokens + required: true + default: 2048 + min: 1 + max: 5000 + - name: temperature + use_template: temperature + required: false + type: float + default: 1 + min: 0.0 + max: 1.0 + help: + zh_Hans: 生成内容的随机性。 + en_US: The amount of randomness injected into the response. + - name: top_p + required: false + type: float + default: 0.999 + min: 0.000 + max: 1.000 + help: + zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。 + en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both. + - name: top_k + required: false + type: int + default: 0 + min: 0 + # tip docs from aws has error, max value is 500 + max: 500 + help: + zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。 + en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses. +pricing: + input: '0.0008' + output: '0.0016' + unit: '0.001' + currency: USD