feat: add text-embedding functon and LLM models to Siliconflow (#7090)

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

@@ -1,8 +1,20 @@
-- deepseek-v2-chat
-- qwen2-72b-instruct
-- qwen2-57b-a14b-instruct
-- qwen2-7b-instruct
-- yi-1.5-34b-chat
-- yi-1.5-9b-chat
-- yi-1.5-6b-chat
-- glm4-9B-chat
+- Qwen/Qwen2-72B-Instruct
+- Qwen/Qwen2-57B-A14B-Instruct
+- Qwen/Qwen2-7B-Instruct
+- Qwen/Qwen2-1.5B-Instruct
+- 01-ai/Yi-1.5-34B-Chat
+- 01-ai/Yi-1.5-9B-Chat-16K
+- 01-ai/Yi-1.5-6B-Chat
+- THUDM/glm-4-9b-chat
+- deepseek-ai/DeepSeek-V2-Chat
+- deepseek-ai/DeepSeek-Coder-V2-Instruct
+- internlm/internlm2_5-7b-chat
+- google/gemma-2-27b-it
+- google/gemma-2-9b-it
+- meta-llama/Meta-Llama-3-70B-Instruct
+- meta-llama/Meta-Llama-3-8B-Instruct
+- meta-llama/Meta-Llama-3.1-405B-Instruct
+- meta-llama/Meta-Llama-3.1-70B-Instruct
+- meta-llama/Meta-Llama-3.1-8B-Instruct
+- mistralai/Mixtral-8x7B-Instruct-v0.1
+- mistralai/Mistral-7B-Instruct-v0.2

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

@@ -1,4 +1,4 @@
-model: deepseek-ai/deepseek-v2-chat
+model: deepseek-ai/DeepSeek-V2-Chat
 label:
   en_US: deepseek-ai/DeepSeek-V2-Chat
 model_type: llm

api/core/model_runtime/model_providers/siliconflow/llm/gemma-2-27b-it.yaml

@@ -0,0 +1,30 @@
+model: google/gemma-2-27b-it
+label:
+  en_US: google/gemma-2-27b-it
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8196
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '1.26'
+  output: '1.26'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/gemma-2-9b-it.yaml

@@ -0,0 +1,30 @@
+model: google/gemma-2-9b-it
+label:
+  en_US: google/gemma-2-9b-it
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8196
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0'
+  output: '0'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/glm4-9b-chat.yaml

@@ -1,4 +1,4 @@
-model: zhipuai/glm4-9B-chat
+model: THUDM/glm-4-9b-chat
 label:
   en_US: THUDM/glm-4-9b-chat
 model_type: llm
@@ -24,7 +24,7 @@ parameter_rules:
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:
-  input: '0.6'
-  output: '0.6'
+  input: '0'
+  output: '0'
   unit: '0.000001'
   currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/internlm2_5-7b-chat.yaml

@@ -0,0 +1,30 @@
+model: internlm/internlm2_5-7b-chat
+label:
+  en_US: internlm/internlm2_5-7b-chat
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0'
+  output: '0'
+  unit: '0.000001'
+  currency: RMB

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

@@ -0,0 +1,30 @@
+model: meta-llama/Meta-Llama-3-70B-Instruct
+label:
+  en_US: meta-llama/Meta-Llama-3-70B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '4.13'
+  output: '4.13'
+  unit: '0.000001'
+  currency: RMB

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

@@ -0,0 +1,30 @@
+model: meta-llama/Meta-Llama-3-8B-Instruct
+label:
+  en_US: meta-llama/Meta-Llama-3-8B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0'
+  output: '0'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3.1-405b-instruct.yaml

@@ -0,0 +1,30 @@
+model: meta-llama/Meta-Llama-3.1-405B-Instruct
+label:
+  en_US: meta-llama/Meta-Llama-3.1-405B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '21'
+  output: '21'
+  unit: '0.000001'
+  currency: RMB

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

@@ -0,0 +1,30 @@
+model: meta-llama/Meta-Llama-3.1-70B-Instruct
+label:
+  en_US: meta-llama/Meta-Llama-3.1-70B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '4.13'
+  output: '4.13'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3.1-8b-instruct.yaml

@@ -0,0 +1,30 @@
+model: meta-llama/Meta-Llama-3.1-8B-Instruct
+label:
+  en_US: meta-llama/Meta-Llama-3.1-8B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0'
+  output: '0'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/mistral-7b-instruct-v0.2.yaml

@@ -0,0 +1,30 @@
+model: mistralai/Mistral-7B-Instruct-v0.2
+label:
+  en_US: mistralai/Mistral-7B-Instruct-v0.2
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0'
+  output: '0'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/mistral-8x7b-instruct-v0.1.yaml

@@ -0,0 +1,30 @@
+model: mistralai/Mixtral-8x7B-Instruct-v0.1
+label:
+  en_US: mistralai/Mixtral-8x7B-Instruct-v0.1
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '1.26'
+  output: '1.26'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-1.5b-instruct.yaml

@@ -0,0 +1,30 @@
+model: Qwen/Qwen2-1.5B-Instruct
+label:
+  en_US: Qwen/Qwen2-1.5B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0'
+  output: '0'
+  unit: '0.000001'
+  currency: RMB

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

@@ -1,4 +1,4 @@
-model: alibaba/Qwen2-57B-A14B-Instruct
+model: Qwen/Qwen2-57B-A14B-Instruct
 label:
   en_US: Qwen/Qwen2-57B-A14B-Instruct
 model_type: llm

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

@@ -1,4 +1,4 @@
-model: alibaba/Qwen2-72B-Instruct
+model: Qwen/Qwen2-72B-Instruct
 label:
   en_US: Qwen/Qwen2-72B-Instruct
 model_type: llm

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

@@ -1,4 +1,4 @@
-model: alibaba/Qwen2-7B-Instruct
+model: Qwen/Qwen2-7B-Instruct
 label:
   en_US: Qwen/Qwen2-7B-Instruct
 model_type: llm
@@ -24,7 +24,7 @@ parameter_rules:
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:
-  input: '0.35'
-  output: '0.35'
+  input: '0'
+  output: '0'
   unit: '0.000001'
   currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-6b-chat.yaml

@@ -24,7 +24,7 @@ parameter_rules:
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:
-  input: '0.35'
-  output: '0.35'
+  input: '0'
+  output: '0'
   unit: '0.000001'
   currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-9b-chat.yaml

@@ -1,4 +1,4 @@
-model: 01-ai/Yi-1.5-9B-Chat
+model: 01-ai/Yi-1.5-9B-Chat-16K
 label:
   en_US: 01-ai/Yi-1.5-9B-Chat-16K
 model_type: llm
@@ -24,7 +24,7 @@ parameter_rules:
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:
-  input: '0.42'
-  output: '0.42'
+  input: '0'
+  output: '0'
   unit: '0.000001'
   currency: RMB

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

@@ -15,6 +15,7 @@ help:
     en_US: https://cloud.siliconflow.cn/keys
 supported_model_types:
   - llm
+  - text-embedding
 configurate_methods:
   - predefined-model
 provider_credential_schema:

api/core/model_runtime/model_providers/siliconflow/text_embedding/bge-large-en-v1.5.yaml

@@ -0,0 +1,5 @@
+model: BAAI/bge-large-en-v1.5
+model_type: text-embedding
+model_properties:
+  context_size: 512
+  max_chunks: 1

api/core/model_runtime/model_providers/siliconflow/text_embedding/bge-large-zh-v1.5.yaml

@@ -0,0 +1,5 @@
+model: BAAI/bge-large-zh-v1.5
+model_type: text-embedding
+model_properties:
+  context_size: 512
+  max_chunks: 1

api/core/model_runtime/model_providers/siliconflow/text_embedding/text_embedding.py

@@ -0,0 +1,29 @@
+from typing import Optional
+
+from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
+from core.model_runtime.model_providers.openai_api_compatible.text_embedding.text_embedding import (
+    OAICompatEmbeddingModel,
+)
+
+
+class SiliconflowTextEmbeddingModel(OAICompatEmbeddingModel):
+    """
+    Model class for Siliconflow text embedding model.
+    """
+    def validate_credentials(self, model: str, credentials: dict) -> None:
+        self._add_custom_parameters(credentials)
+        super().validate_credentials(model, credentials)
+
+    def _invoke(self, model: str, credentials: dict,
+                texts: list[str], user: Optional[str] = None) \
+            -> TextEmbeddingResult:
+        self._add_custom_parameters(credentials)
+        return super()._invoke(model, credentials, texts, user)
+    
+    def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
+        self._add_custom_parameters(credentials)
+        return super().get_num_tokens(model, credentials, texts)
+    
+    @classmethod
+    def _add_custom_parameters(cls, credentials: dict) -> None:
+        credentials['endpoint_url'] = 'https://api.siliconflow.cn/v1'

api/tests/integration_tests/model_runtime/siliconflow/test_text_embedding.py

@@ -0,0 +1,62 @@
+import os
+
+import pytest
+
+from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.siliconflow.text_embedding.text_embedding import (
+    SiliconflowTextEmbeddingModel,
+)
+
+
+def test_validate_credentials():
+    model = SiliconflowTextEmbeddingModel()
+
+    with pytest.raises(CredentialsValidateFailedError):
+        model.validate_credentials(
+            model="BAAI/bge-large-zh-v1.5",
+            credentials={
+                "api_key": "invalid_key"
+            },
+        )
+
+    model.validate_credentials(
+        model="BAAI/bge-large-zh-v1.5",
+        credentials={
+            "api_key": os.environ.get("API_KEY"),
+        },
+    )
+
+
+def test_invoke_model():
+    model = SiliconflowTextEmbeddingModel()
+
+    result = model.invoke(
+        model="BAAI/bge-large-zh-v1.5",
+        credentials={
+            "api_key": os.environ.get("API_KEY"),
+        },
+        texts=[
+            "hello",
+            "world",
+        ],
+        user="abc-123",
+    )
+
+    assert isinstance(result, TextEmbeddingResult)
+    assert len(result.embeddings) == 2
+    assert result.usage.total_tokens == 6
+
+
+def test_get_num_tokens():
+    model = SiliconflowTextEmbeddingModel()
+
+    num_tokens = model.get_num_tokens(
+        model="BAAI/bge-large-zh-v1.5",
+        credentials={
+            "api_key": os.environ.get("API_KEY"),
+        },
+        texts=["hello", "world"],
+    )
+
+    assert num_tokens == 2