Upload 45 files

.gitattributes

@@ -12,3 +12,17 @@ api/core/tools/docs/images/index/image.png filter=lfs diff=lfs merge=lfs -text
 api/core/tools/provider/builtin/comfyui/_assets/icon.png filter=lfs diff=lfs merge=lfs -text
 api/core/tools/provider/builtin/dalle/_assets/icon.png filter=lfs diff=lfs merge=lfs -text
 api/core/tools/provider/builtin/wecom/_assets/icon.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/en_US/images/index/image-1.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/en_US/images/index/image-2.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/en_US/images/index/image-20231210143654461.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/en_US/images/index/image-20231210144229650.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/en_US/images/index/image-20231210144814617.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/en_US/images/index/image-20231210165243632.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/en_US/images/index/image.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/zh_Hans/images/index/image-1.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/zh_Hans/images/index/image-2.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/zh_Hans/images/index/image-20231210143654461.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/zh_Hans/images/index/image-20231210144229650.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/zh_Hans/images/index/image-20231210144814617.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/zh_Hans/images/index/image-20231210165243632.png filter=lfs diff=lfs merge=lfs -text
+api/core/model_runtime/docs/zh_Hans/images/index/image.png filter=lfs diff=lfs merge=lfs -text

api/core/model_runtime/callbacks/base_callback.py

@@ -0,0 +1,152 @@
+from abc import ABC, abstractmethod
+from collections.abc import Sequence
+from typing import Optional
+
+from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
+from core.model_runtime.entities.message_entities import PromptMessage, PromptMessageTool
+from core.model_runtime.model_providers.__base.ai_model import AIModel
+
+_TEXT_COLOR_MAPPING = {
+    "blue": "36;1",
+    "yellow": "33;1",
+    "pink": "38;5;200",
+    "green": "32;1",
+    "red": "31;1",
+}
+
+
+class Callback(ABC):
+    """
+    Base class for callbacks.
+    Only for LLM.
+    """
+
+    raise_error: bool = False
+
+    @abstractmethod
+    def on_before_invoke(
+        self,
+        llm_instance: AIModel,
+        model: str,
+        credentials: dict,
+        prompt_messages: list[PromptMessage],
+        model_parameters: dict,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[Sequence[str]] = None,
+        stream: bool = True,
+        user: Optional[str] = None,
+    ) -> None:
+        """
+        Before invoke callback
+
+        :param llm_instance: LLM instance
+        :param model: model name
+        :param credentials: model credentials
+        :param prompt_messages: prompt messages
+        :param model_parameters: model parameters
+        :param tools: tools for tool calling
+        :param stop: stop words
+        :param stream: is stream response
+        :param user: unique user id
+        """
+        raise NotImplementedError()
+
+    @abstractmethod
+    def on_new_chunk(
+        self,
+        llm_instance: AIModel,
+        chunk: LLMResultChunk,
+        model: str,
+        credentials: dict,
+        prompt_messages: list[PromptMessage],
+        model_parameters: dict,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[Sequence[str]] = None,
+        stream: bool = True,
+        user: Optional[str] = None,
+    ):
+        """
+        On new chunk callback
+
+        :param llm_instance: LLM instance
+        :param chunk: chunk
+        :param model: model name
+        :param credentials: model credentials
+        :param prompt_messages: prompt messages
+        :param model_parameters: model parameters
+        :param tools: tools for tool calling
+        :param stop: stop words
+        :param stream: is stream response
+        :param user: unique user id
+        """
+        raise NotImplementedError()
+
+    @abstractmethod
+    def on_after_invoke(
+        self,
+        llm_instance: AIModel,
+        result: LLMResult,
+        model: str,
+        credentials: dict,
+        prompt_messages: list[PromptMessage],
+        model_parameters: dict,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[Sequence[str]] = None,
+        stream: bool = True,
+        user: Optional[str] = None,
+    ) -> None:
+        """
+        After invoke callback
+
+        :param llm_instance: LLM instance
+        :param result: result
+        :param model: model name
+        :param credentials: model credentials
+        :param prompt_messages: prompt messages
+        :param model_parameters: model parameters
+        :param tools: tools for tool calling
+        :param stop: stop words
+        :param stream: is stream response
+        :param user: unique user id
+        """
+        raise NotImplementedError()
+
+    @abstractmethod
+    def on_invoke_error(
+        self,
+        llm_instance: AIModel,
+        ex: Exception,
+        model: str,
+        credentials: dict,
+        prompt_messages: list[PromptMessage],
+        model_parameters: dict,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[Sequence[str]] = None,
+        stream: bool = True,
+        user: Optional[str] = None,
+    ) -> None:
+        """
+        Invoke error callback
+
+        :param llm_instance: LLM instance
+        :param ex: exception
+        :param model: model name
+        :param credentials: model credentials
+        :param prompt_messages: prompt messages
+        :param model_parameters: model parameters
+        :param tools: tools for tool calling
+        :param stop: stop words
+        :param stream: is stream response
+        :param user: unique user id
+        """
+        raise NotImplementedError()
+
+    def print_text(self, text: str, color: Optional[str] = None, end: str = "") -> None:
+        """Print text with highlighting and no end characters."""
+        text_to_print = self._get_colored_text(text, color) if color else text
+        print(text_to_print, end=end)
+
+    def _get_colored_text(self, text: str, color: str) -> str:
+        """Get colored text."""
+        color_str = _TEXT_COLOR_MAPPING[color]
+        return f"\u001b[{color_str}m\033[1;3m{text}\u001b[0m"

api/core/model_runtime/callbacks/logging_callback.py

@@ -0,0 +1,170 @@
+import json
+import logging
+import sys
+from collections.abc import Sequence
+from typing import Optional, cast
+
+from core.model_runtime.callbacks.base_callback import Callback
+from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
+from core.model_runtime.entities.message_entities import PromptMessage, PromptMessageTool
+from core.model_runtime.model_providers.__base.ai_model import AIModel
+
+logger = logging.getLogger(__name__)
+
+
+class LoggingCallback(Callback):
+    def on_before_invoke(
+        self,
+        llm_instance: AIModel,
+        model: str,
+        credentials: dict,
+        prompt_messages: list[PromptMessage],
+        model_parameters: dict,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[Sequence[str]] = None,
+        stream: bool = True,
+        user: Optional[str] = None,
+    ) -> None:
+        """
+        Before invoke callback
+
+        :param llm_instance: LLM instance
+        :param model: model name
+        :param credentials: model credentials
+        :param prompt_messages: prompt messages
+        :param model_parameters: model parameters
+        :param tools: tools for tool calling
+        :param stop: stop words
+        :param stream: is stream response
+        :param user: unique user id
+        """
+        self.print_text("\n[on_llm_before_invoke]\n", color="blue")
+        self.print_text(f"Model: {model}\n", color="blue")
+        self.print_text("Parameters:\n", color="blue")
+        for key, value in model_parameters.items():
+            self.print_text(f"\t{key}: {value}\n", color="blue")
+
+        if stop:
+            self.print_text(f"\tstop: {stop}\n", color="blue")
+
+        if tools:
+            self.print_text("\tTools:\n", color="blue")
+            for tool in tools:
+                self.print_text(f"\t\t{tool.name}\n", color="blue")
+
+        self.print_text(f"Stream: {stream}\n", color="blue")
+
+        if user:
+            self.print_text(f"User: {user}\n", color="blue")
+
+        self.print_text("Prompt messages:\n", color="blue")
+        for prompt_message in prompt_messages:
+            if prompt_message.name:
+                self.print_text(f"\tname: {prompt_message.name}\n", color="blue")
+
+            self.print_text(f"\trole: {prompt_message.role.value}\n", color="blue")
+            self.print_text(f"\tcontent: {prompt_message.content}\n", color="blue")
+
+        if stream:
+            self.print_text("\n[on_llm_new_chunk]")
+
+    def on_new_chunk(
+        self,
+        llm_instance: AIModel,
+        chunk: LLMResultChunk,
+        model: str,
+        credentials: dict,
+        prompt_messages: list[PromptMessage],
+        model_parameters: dict,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[Sequence[str]] = None,
+        stream: bool = True,
+        user: Optional[str] = None,
+    ):
+        """
+        On new chunk callback
+
+        :param llm_instance: LLM instance
+        :param chunk: chunk
+        :param model: model name
+        :param credentials: model credentials
+        :param prompt_messages: prompt messages
+        :param model_parameters: model parameters
+        :param tools: tools for tool calling
+        :param stop: stop words
+        :param stream: is stream response
+        :param user: unique user id
+        """
+        sys.stdout.write(cast(str, chunk.delta.message.content))
+        sys.stdout.flush()
+
+    def on_after_invoke(
+        self,
+        llm_instance: AIModel,
+        result: LLMResult,
+        model: str,
+        credentials: dict,
+        prompt_messages: list[PromptMessage],
+        model_parameters: dict,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[Sequence[str]] = None,
+        stream: bool = True,
+        user: Optional[str] = None,
+    ) -> None:
+        """
+        After invoke callback
+
+        :param llm_instance: LLM instance
+        :param result: result
+        :param model: model name
+        :param credentials: model credentials
+        :param prompt_messages: prompt messages
+        :param model_parameters: model parameters
+        :param tools: tools for tool calling
+        :param stop: stop words
+        :param stream: is stream response
+        :param user: unique user id
+        """
+        self.print_text("\n[on_llm_after_invoke]\n", color="yellow")
+        self.print_text(f"Content: {result.message.content}\n", color="yellow")
+
+        if result.message.tool_calls:
+            self.print_text("Tool calls:\n", color="yellow")
+            for tool_call in result.message.tool_calls:
+                self.print_text(f"\t{tool_call.id}\n", color="yellow")
+                self.print_text(f"\t{tool_call.function.name}\n", color="yellow")
+                self.print_text(f"\t{json.dumps(tool_call.function.arguments)}\n", color="yellow")
+
+        self.print_text(f"Model: {result.model}\n", color="yellow")
+        self.print_text(f"Usage: {result.usage}\n", color="yellow")
+        self.print_text(f"System Fingerprint: {result.system_fingerprint}\n", color="yellow")
+
+    def on_invoke_error(
+        self,
+        llm_instance: AIModel,
+        ex: Exception,
+        model: str,
+        credentials: dict,
+        prompt_messages: list[PromptMessage],
+        model_parameters: dict,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[Sequence[str]] = None,
+        stream: bool = True,
+        user: Optional[str] = None,
+    ) -> None:
+        """
+        Invoke error callback
+
+        :param llm_instance: LLM instance
+        :param ex: exception
+        :param model: model name
+        :param credentials: model credentials
+        :param prompt_messages: prompt messages
+        :param model_parameters: model parameters
+        :param tools: tools for tool calling
+        :param stop: stop words
+        :param stream: is stream response
+        :param user: unique user id
+        """
+        self.print_text("\n[on_llm_invoke_error]\n", color="red")
+        logger.exception(ex)

api/core/model_runtime/docs/en_US/customizable_model_scale_out.md

@@ -0,0 +1,310 @@
+## Custom Integration of Pre-defined Models
+
+### Introduction
+
+After completing the vendors integration, the next step is to connect the vendor's models. To illustrate the entire connection process, we will use Xinference as an example to demonstrate a complete vendor integration.
+
+It is important to note that for custom models, each model connection requires a complete vendor credential.
+
+Unlike pre-defined models, a custom vendor integration always includes the following two parameters, which do not need to be defined in the vendor YAML file.
+
+![](images/index/image-3.png)
+
+As mentioned earlier, vendors do not need to implement validate_provider_credential. The runtime will automatically call the corresponding model layer's validate_credentials to validate the credentials based on the model type and name selected by the user.
+
+### Writing the Vendor YAML
+
+First, we need to identify the types of models supported by the vendor we are integrating.
+
+Currently supported model types are as follows:
+
+- `llm` Text Generation Models
+
+- `text_embedding` Text Embedding Models
+
+- `rerank` Rerank Models
+
+- `speech2text` Speech-to-Text
+
+- `tts` Text-to-Speech
+
+- `moderation` Moderation
+
+Xinference supports LLM, Text Embedding, and Rerank. So we will start by writing xinference.yaml.
+
+```yaml
+provider: xinference #Define the vendor identifier
+label: # Vendor display name, supports both en_US (English) and zh_Hans (Simplified Chinese). If zh_Hans is not set, it will use en_US by default.
+  en_US: Xorbits Inference
+icon_small: # Small icon, refer to other vendors' icons stored in the _assets directory within the vendor implementation directory; follows the same language policy as the label
+  en_US: icon_s_en.svg
+icon_large: # Large icon
+  en_US: icon_l_en.svg
+help: # Help information
+  title:
+    en_US: How to deploy Xinference
+    zh_Hans: 如何部署 Xinference
+  url:
+    en_US: https://github.com/xorbitsai/inference
+supported_model_types: # Supported model types. Xinference supports LLM, Text Embedding, and Rerank
+- llm
+- text-embedding
+- rerank
+configurate_methods: # Since Xinference is a locally deployed vendor with no predefined models, users need to deploy whatever models they need according to Xinference documentation. Thus, it only supports custom models.
+- customizable-model
+provider_credential_schema:
+  credential_form_schemas:
+```
+
+
+Then, we need to determine what credentials are required to define a model in Xinference.
+
+- Since it supports three different types of models, we need to specify the model_type to denote the model type. Here is how we can define it:
+
+```yaml
+provider_credential_schema:
+  credential_form_schemas:
+  - variable: model_type
+    type: select
+    label:
+      en_US: Model type
+      zh_Hans: 模型类型
+    required: true
+    options:
+    - value: text-generation
+      label:
+        en_US: Language Model
+        zh_Hans: 语言模型
+    - value: embeddings
+      label:
+        en_US: Text Embedding
+    - value: reranking
+      label:
+        en_US: Rerank
+```
+
+- Next, each model has its own model_name, so we need to define that here:
+
+```yaml
+  - variable: model_name
+    type: text-input
+    label:
+      en_US: Model name
+      zh_Hans: 模型名称
+    required: true
+    placeholder:
+      zh_Hans: 填写模型名称
+      en_US: Input model name
+```
+
+- Specify the Xinference local deployment address:
+
+```yaml
+  - variable: server_url
+    label:
+      zh_Hans: 服务器URL
+      en_US: Server url
+    type: text-input
+    required: true
+    placeholder:
+      zh_Hans: 在此输入Xinference的服务器地址，如 https://example.com/xxx
+      en_US: Enter the url of your Xinference, for example https://example.com/xxx
+```
+
+- Each model has a unique model_uid, so we also need to define that here:
+
+```yaml
+  - variable: model_uid
+    label:
+      zh_Hans: 模型UID
+      en_US: Model uid
+    type: text-input
+    required: true
+    placeholder:
+      zh_Hans: 在此输入您的Model UID
+      en_US: Enter the model uid
+```
+
+Now, we have completed the basic definition of the vendor.
+
+### Writing the Model Code
+
+Next, let's take the `llm` type as an example and write `xinference.llm.llm.py`.
+
+In `llm.py`, create a Xinference LLM class, we name it `XinferenceAILargeLanguageModel` (this can be arbitrary), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
+
+- LLM Invocation
+
+Implement the core method for LLM invocation, supporting both stream and synchronous responses.
+
+```python
+def _invoke(self, model: str, credentials: dict,
+            prompt_messages: list[PromptMessage], model_parameters: dict,
+            tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
+            stream: bool = True, user: Optional[str] = None) \
+        -> Union[LLMResult, Generator]:
+    """
+    Invoke large language model
+    
+    :param model: model name
+	:param credentials: model credentials
+	:param prompt_messages: prompt messages
+	:param model_parameters: model parameters
+	:param tools: tools for tool usage
+	:param stop: stop words
+	:param stream: is the response a stream
+	:param user: unique user id
+	:return: full response or stream response chunk generator result
+	"""
+```
+
+When implementing, ensure to use two functions to return data separately for synchronous and stream responses. This is important because Python treats functions containing the `yield` keyword as generator functions, mandating them to return `Generator` types. Here’s an example (note that the example uses simplified parameters; in real implementation, use the parameter list as defined above):
+
+```python
+def _invoke(self, stream: bool, **kwargs) \
+        -> Union[LLMResult, Generator]:
+    if stream:
+          return self._handle_stream_response(**kwargs)
+    return self._handle_sync_response(**kwargs)
+
+def _handle_stream_response(self, **kwargs) -> Generator:
+    for chunk in response:
+          yield chunk
+def _handle_sync_response(self, **kwargs) -> LLMResult:
+    return LLMResult(**response)
+```
+
+- Pre-compute Input Tokens
+
+If the model does not provide an interface for pre-computing tokens, you can return 0 directly.
+
+```python
+def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],tools: Optional[list[PromptMessageTool]] = None) -> int:
+  """
+  Get number of tokens for given prompt messages
+
+  :param model: model name
+  :param credentials: model credentials
+  :param prompt_messages: prompt messages
+  :param tools: tools for tool usage
+  :return: token count
+  """
+```
+
+
+Sometimes, you might not want to return 0 directly. In such cases, you can use `self._get_num_tokens_by_gpt2(text: str)` to get pre-computed tokens. This method is provided by the `AIModel` base class, and it uses GPT2's Tokenizer for calculation. However, it should be noted that this is only a substitute and may not be fully accurate.
+
+- Model Credentials Validation
+
+Similar to vendor credentials validation, this method validates individual model credentials.
+
+```python
+def validate_credentials(self, model: str, credentials: dict) -> None:
+    """
+    Validate model credentials
+    
+    :param model: model name
+	:param credentials: model credentials
+	:return: None
+	"""
+```
+
+- Model Parameter Schema
+
+Unlike custom types, since the YAML file does not define which parameters a model supports, we need to dynamically generate the model parameter schema.
+
+For instance, Xinference supports `max_tokens`, `temperature`, and `top_p` parameters.
+
+However, some vendors may support different parameters for different models. For example, the `OpenLLM` vendor supports `top_k`, but not all models provided by this vendor support `top_k`. Let's say model A supports `top_k` but model B does not. In such cases, we need to dynamically generate the model parameter schema, as illustrated below:
+
+```python
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+        """
+            used to define customizable model schema
+        """
+        rules = [
+            ParameterRule(
+                name='temperature', type=ParameterType.FLOAT,
+                use_template='temperature',
+                label=I18nObject(
+                    zh_Hans='温度', en_US='Temperature'
+                )
+            ),
+            ParameterRule(
+                name='top_p', type=ParameterType.FLOAT,
+                use_template='top_p',
+                label=I18nObject(
+                    zh_Hans='Top P', en_US='Top P'
+                )
+            ),
+            ParameterRule(
+                name='max_tokens', type=ParameterType.INT,
+                use_template='max_tokens',
+                min=1,
+                default=512,
+                label=I18nObject(
+                    zh_Hans='最大生成长度', en_US='Max Tokens'
+                )
+            )
+        ]
+
+        # if model is A, add top_k to rules
+        if model == 'A':
+            rules.append(
+                ParameterRule(
+                    name='top_k', type=ParameterType.INT,
+                    use_template='top_k',
+                    min=1,
+                    default=50,
+                    label=I18nObject(
+                        zh_Hans='Top K', en_US='Top K'
+                    )
+                )
+            )
+
+        """
+            some NOT IMPORTANT code here
+        """
+
+        entity = AIModelEntity(
+            model=model,
+            label=I18nObject(
+                en_US=model
+            ),
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_type=model_type,
+            model_properties={ 
+                ModelPropertyKey.MODE:  ModelType.LLM,
+            },
+            parameter_rules=rules
+        )
+
+        return entity
+```
+
+- Exception Error Mapping
+
+When a model invocation error occurs, it should be mapped to the runtime's specified `InvokeError` type, enabling Dify to handle different errors appropriately.
+
+Runtime Errors:
+
+- `InvokeConnectionError` Connection error during invocation
+- `InvokeServerUnavailableError` Service provider unavailable
+- `InvokeRateLimitError` Rate limit reached
+- `InvokeAuthorizationError` Authorization failure
+- `InvokeBadRequestError` Invalid request parameters
+
+```python
+  @property
+  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+      """
+      Map model invoke error to unified error
+      The key is the error type thrown to the caller
+      The value is the error type thrown by the model,
+      which needs to be converted into a unified error type for the caller.
+  
+      :return: Invoke error mapping
+      """
+```
+
+For interface method details, see: [Interfaces](./interfaces.md). For specific implementations, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

api/core/model_runtime/docs/en_US/interfaces.md

@@ -0,0 +1,706 @@
+# Interface Methods
+
+This section describes the interface methods and parameter explanations that need to be implemented by providers and various model types.
+
+## Provider
+
+Inherit the `__base.model_provider.ModelProvider` base class and implement the following interfaces:
+
+```python
+def validate_provider_credentials(self, credentials: dict) -> None:
+    """
+    Validate provider credentials
+    You can choose any validate_credentials method of model type or implement validate method by yourself,
+    such as: get model list api
+
+    if validate failed, raise exception
+
+    :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
+    """
+```
+
+- `credentials` (object) Credential information
+
+  The parameters of credential information are defined by the `provider_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
+
+If verification fails, throw the `errors.validate.CredentialsValidateFailedError` error.
+
+## Model
+
+Models are divided into 5 different types, each inheriting from different base classes and requiring the implementation of different methods.
+
+All models need to uniformly implement the following 2 methods:
+
+- Model Credential Verification
+
+  Similar to provider credential verification, this step involves verification for an individual model.
+
+
+  ```python
+  def validate_credentials(self, model: str, credentials: dict) -> None:
+      """
+      Validate model credentials
+  
+      :param model: model name
+      :param credentials: model credentials
+      :return:
+      """
+  ```
+
+  Parameters:
+
+  - `model` (string) Model name
+
+  - `credentials` (object) Credential information
+
+    The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
+
+  If verification fails, throw the `errors.validate.CredentialsValidateFailedError` error.
+
+- Invocation Error Mapping Table
+
+  When there is an exception in model invocation, it needs to be mapped to the `InvokeError` type specified by Runtime. This facilitates Dify's ability to handle different errors with appropriate follow-up actions.
+
+  Runtime Errors:
+
+  - `InvokeConnectionError` Invocation connection error
+  - `InvokeServerUnavailableError` Invocation service provider unavailable
+  - `InvokeRateLimitError` Invocation reached rate limit
+  - `InvokeAuthorizationError` Invocation authorization failure
+  - `InvokeBadRequestError` Invocation parameter error
+
+  ```python
+  @property
+  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+      """
+      Map model invoke error to unified error
+      The key is the error type thrown to the caller
+      The value is the error type thrown by the model,
+      which needs to be converted into a unified error type for the caller.
+  
+      :return: Invoke error mapping
+      """
+  ```
+
+​	You can refer to OpenAI's `_invoke_error_mapping` for an example.
+
+### LLM
+
+Inherit the `__base.large_language_model.LargeLanguageModel` base class and implement the following interfaces:
+
+- LLM Invocation
+
+  Implement the core method for LLM invocation, which can support both streaming and synchronous returns.
+
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              prompt_messages: list[PromptMessage], model_parameters: dict,
+              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[List[str]] = None,
+              stream: bool = True, user: Optional[str] = None) \
+          -> Union[LLMResult, Generator]:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param model_parameters: model parameters
+      :param tools: tools for tool calling
+      :param stop: stop words
+      :param stream: is stream response
+      :param user: unique user id
+      :return: full response or stream response chunk generator result
+      """
+  ```
+
+  - Parameters:
+
+    - `model` (string) Model name
+
+    - `credentials` (object) Credential information
+
+      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
+
+    - `prompt_messages` (array[[PromptMessage](#PromptMessage)]) List of prompts
+
+      If the model is of the `Completion` type, the list only needs to include one [UserPromptMessage](#UserPromptMessage) element;
+
+      If the model is of the `Chat` type, it requires a list of elements such as [SystemPromptMessage](#SystemPromptMessage), [UserPromptMessage](#UserPromptMessage), [AssistantPromptMessage](#AssistantPromptMessage), [ToolPromptMessage](#ToolPromptMessage) depending on the message.
+
+    - `model_parameters` (object) Model parameters
+
+      The model parameters are defined by the `parameter_rules` in the model's YAML configuration.
+
+    - `tools` (array[[PromptMessageTool](#PromptMessageTool)]) [optional] List of tools, equivalent to the `function` in `function calling`.
+
+      That is, the tool list for tool calling.
+
+    - `stop` (array[string]) [optional] Stop sequences
+
+      The model output will stop before the string defined by the stop sequence.
+
+    - `stream` (bool) Whether to output in a streaming manner, default is True
+
+      Streaming output returns Generator[[LLMResultChunk](#LLMResultChunk)], non-streaming output returns [LLMResult](#LLMResult).
+
+    - `user` (string) [optional] Unique identifier of the user
+
+      This can help the provider monitor and detect abusive behavior.
+
+  - Returns
+
+    Streaming output returns Generator[[LLMResultChunk](#LLMResultChunk)], non-streaming output returns [LLMResult](#LLMResult).
+
+- Pre-calculating Input Tokens
+
+  If the model does not provide a pre-calculated tokens interface, you can directly return 0.
+
+  ```python
+  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
+                     tools: Optional[list[PromptMessageTool]] = None) -> int:
+      """
+      Get number of tokens for given prompt messages
+
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param tools: tools for tool calling
+      :return:
+      """
+  ```
+
+  For parameter explanations, refer to the above section on `LLM Invocation`.
+
+- Fetch Custom Model Schema [Optional]
+
+  ```python
+  def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+      """
+      Get customizable model schema
+
+      :param model: model name
+      :param credentials: model credentials
+      :return: model schema
+      """
+  ```
+
+  When the provider supports adding custom LLMs, this method can be implemented to allow custom models to fetch model schema. The default return null.
+
+
+### TextEmbedding
+
+Inherit the `__base.text_embedding_model.TextEmbeddingModel` base class and implement the following interfaces:
+
+- Embedding Invocation
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              texts: list[str], user: Optional[str] = None) \
+          -> TextEmbeddingResult:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param texts: texts to embed
+      :param user: unique user id
+      :return: embeddings result
+      """
+  ```
+
+  - Parameters:
+
+    - `model` (string) Model name
+
+    - `credentials` (object) Credential information
+
+      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
+
+    - `texts` (array[string]) List of texts, capable of batch processing
+
+    - `user` (string) [optional] Unique identifier of the user
+
+      This can help the provider monitor and detect abusive behavior.
+
+  - Returns:
+
+    [TextEmbeddingResult](#TextEmbeddingResult) entity.
+
+- Pre-calculating Tokens
+
+  ```python
+  def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
+      """
+      Get number of tokens for given prompt messages
+
+      :param model: model name
+      :param credentials: model credentials
+      :param texts: texts to embed
+      :return:
+      """
+  ```
+
+  For parameter explanations, refer to the above section on `Embedding Invocation`.
+
+### Rerank
+
+Inherit the `__base.rerank_model.RerankModel` base class and implement the following interfaces:
+
+- Rerank Invocation
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              query: str, docs: list[str], score_threshold: Optional[float] = None, top_n: Optional[int] = None,
+              user: Optional[str] = None) \
+          -> RerankResult:
+      """
+      Invoke rerank model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param query: search query
+      :param docs: docs for reranking
+      :param score_threshold: score threshold
+      :param top_n: top n
+      :param user: unique user id
+      :return: rerank result
+      """
+  ```
+
+  - Parameters:
+
+    - `model` (string) Model name
+
+    - `credentials` (object) Credential information
+
+      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
+
+    - `query` (string) Query request content
+
+    - `docs` (array[string]) List of segments to be reranked
+
+    - `score_threshold` (float) [optional] Score threshold
+
+    - `top_n` (int) [optional] Select the top n segments
+
+    - `user` (string) [optional] Unique identifier of the user
+
+      This can help the provider monitor and detect abusive behavior.
+
+  - Returns:
+
+    [RerankResult](#RerankResult) entity.
+
+### Speech2text
+
+Inherit the `__base.speech2text_model.Speech2TextModel` base class and implement the following interfaces:
+
+- Invoke Invocation
+
+  ```python
+  def _invoke(self, model: str, credentials: dict, file: IO[bytes], user: Optional[str] = None) -> str:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param file: audio file
+      :param user: unique user id
+      :return: text for given audio file
+      """	
+  ```
+
+  - Parameters:
+
+    - `model` (string) Model name
+
+    - `credentials` (object) Credential information
+
+      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
+
+    - `file` (File) File stream
+
+    - `user` (string) [optional] Unique identifier of the user
+
+      This can help the provider monitor and detect abusive behavior.
+
+  - Returns:
+
+    The string after speech-to-text conversion.
+
+### Text2speech
+
+Inherit the `__base.text2speech_model.Text2SpeechModel` base class and implement the following interfaces:
+
+- Invoke Invocation
+
+  ```python
+  def _invoke(self, model: str, credentials: dict, content_text: str, streaming: bool, user: Optional[str] = None):
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param content_text: text content to be translated
+      :param streaming: output is streaming
+      :param user: unique user id
+      :return: translated audio file
+      """	
+  ```
+
+  - Parameters：
+
+    - `model` (string) Model name
+
+    - `credentials` (object) Credential information
+
+      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
+
+    - `content_text` (string) The text content that needs to be converted
+
+    - `streaming` (bool) Whether to stream output
+
+    - `user` (string) [optional] Unique identifier of the user
+
+      This can help the provider monitor and detect abusive behavior.
+
+  - Returns：
+
+    Text converted speech stream。
+
+### Moderation
+
+Inherit the `__base.moderation_model.ModerationModel` base class and implement the following interfaces:
+
+- Invoke Invocation
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              text: str, user: Optional[str] = None) \
+          -> bool:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param text: text to moderate
+      :param user: unique user id
+      :return: false if text is safe, true otherwise
+      """
+  ```
+
+  - Parameters:
+
+    - `model` (string) Model name
+
+    - `credentials` (object) Credential information
+
+      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
+
+    - `text` (string) Text content
+
+    - `user` (string) [optional] Unique identifier of the user
+
+      This can help the provider monitor and detect abusive behavior.
+
+  - Returns:
+
+    False indicates that the input text is safe, True indicates otherwise.
+
+
+
+## Entities
+
+### PromptMessageRole 
+
+Message role
+
+```python
+class PromptMessageRole(Enum):
+    """
+    Enum class for prompt message.
+    """
+    SYSTEM = "system"
+    USER = "user"
+    ASSISTANT = "assistant"
+    TOOL = "tool"
+```
+
+### PromptMessageContentType
+
+Message content types, divided into text and image.
+
+```python
+class PromptMessageContentType(Enum):
+    """
+    Enum class for prompt message content type.
+    """
+    TEXT = 'text'
+    IMAGE = 'image'
+```
+
+### PromptMessageContent
+
+Message content base class, used only for parameter declaration and cannot be initialized.
+
+```python
+class PromptMessageContent(BaseModel):
+    """
+    Model class for prompt message content.
+    """
+    type: PromptMessageContentType
+    data: str
+```
+
+Currently, two types are supported: text and image. It's possible to simultaneously input text and multiple images.
+
+You need to initialize `TextPromptMessageContent` and `ImagePromptMessageContent` separately for input.
+
+### TextPromptMessageContent
+
+```python
+class TextPromptMessageContent(PromptMessageContent):
+    """
+    Model class for text prompt message content.
+    """
+    type: PromptMessageContentType = PromptMessageContentType.TEXT
+```
+
+If inputting a combination of text and images, the text needs to be constructed into this entity as part of the `content` list.
+
+### ImagePromptMessageContent
+
+```python
+class ImagePromptMessageContent(PromptMessageContent):
+    """
+    Model class for image prompt message content.
+    """
+    class DETAIL(Enum):
+        LOW = 'low'
+        HIGH = 'high'
+
+    type: PromptMessageContentType = PromptMessageContentType.IMAGE
+    detail: DETAIL = DETAIL.LOW  # Resolution
+```
+
+If inputting a combination of text and images, the images need to be constructed into this entity as part of the `content` list.
+
+`data` can be either a `url` or a `base64` encoded string of the image.
+
+### PromptMessage
+
+The base class for all Role message bodies, used only for parameter declaration and cannot be initialized.
+
+```python
+class PromptMessage(ABC, BaseModel):
+    """
+    Model class for prompt message.
+    """
+    role: PromptMessageRole
+    content: Optional[str | list[PromptMessageContent]] = None  # Supports two types: string and content list. The content list is designed to meet the needs of multimodal inputs. For more details, see the PromptMessageContent explanation.
+    name: Optional[str] = None
+```
+
+### UserPromptMessage
+
+UserMessage message body, representing a user's message.
+
+```python
+class UserPromptMessage(PromptMessage):
+    """
+    Model class for user prompt message.
+    """
+    role: PromptMessageRole = PromptMessageRole.USER
+```
+
+### AssistantPromptMessage
+
+Represents a message returned by the model, typically used for `few-shots` or inputting chat history.
+
+```python
+class AssistantPromptMessage(PromptMessage):
+    """
+    Model class for assistant prompt message.
+    """
+    class ToolCall(BaseModel):
+        """
+        Model class for assistant prompt message tool call.
+        """
+        class ToolCallFunction(BaseModel):
+            """
+            Model class for assistant prompt message tool call function.
+            """
+            name: str  # tool name
+            arguments: str  # tool arguments
+
+        id: str  # Tool ID, effective only in OpenAI tool calls. It's the unique ID for tool invocation and the same tool can be called multiple times.
+        type: str  # default: function
+        function: ToolCallFunction  # tool call information
+
+    role: PromptMessageRole = PromptMessageRole.ASSISTANT
+    tool_calls: list[ToolCall] = []  # The result of tool invocation in response from the model (returned only when tools are input and the model deems it necessary to invoke a tool).
+```
+
+Where `tool_calls` are the list of `tool calls` returned by the model after invoking the model with the `tools` input.
+
+### SystemPromptMessage
+
+Represents system messages, usually used for setting system commands given to the model.
+
+```python
+class SystemPromptMessage(PromptMessage):
+    """
+    Model class for system prompt message.
+    """
+    role: PromptMessageRole = PromptMessageRole.SYSTEM
+```
+
+### ToolPromptMessage
+
+Represents tool messages, used for conveying the results of a tool execution to the model for the next step of processing.
+
+```python
+class ToolPromptMessage(PromptMessage):
+    """
+    Model class for tool prompt message.
+    """
+    role: PromptMessageRole = PromptMessageRole.TOOL
+    tool_call_id: str  # Tool invocation ID. If OpenAI tool call is not supported, the name of the tool can also be inputted.
+```
+
+The base class's `content` takes in the results of tool execution.
+
+### PromptMessageTool
+
+```python
+class PromptMessageTool(BaseModel):
+    """
+    Model class for prompt message tool.
+    """
+    name: str
+    description: str
+    parameters: dict
+```
+
+---
+
+### LLMResult
+
+```python
+class LLMResult(BaseModel):
+    """
+    Model class for llm result.
+    """
+    model: str  # Actual used modele
+    prompt_messages: list[PromptMessage]  # prompt messages
+    message: AssistantPromptMessage  # response message
+    usage: LLMUsage  # usage info
+    system_fingerprint: Optional[str] = None  # request fingerprint, refer to OpenAI definition
+```
+
+### LLMResultChunkDelta
+
+In streaming returns, each iteration contains the `delta` entity.
+
+```python
+class LLMResultChunkDelta(BaseModel):
+    """
+    Model class for llm result chunk delta.
+    """
+    index: int
+    message: AssistantPromptMessage  # response message
+    usage: Optional[LLMUsage] = None  # usage info
+    finish_reason: Optional[str] = None  # finish reason, only the last one returns
+```
+
+### LLMResultChunk
+
+Each iteration entity in streaming returns.
+
+```python
+class LLMResultChunk(BaseModel):
+    """
+    Model class for llm result chunk.
+    """
+    model: str  # Actual used modele
+    prompt_messages: list[PromptMessage]  # prompt messages
+    system_fingerprint: Optional[str] = None  # request fingerprint, refer to OpenAI definition
+    delta: LLMResultChunkDelta
+```
+
+### LLMUsage
+
+```python
+class LLMUsage(ModelUsage):
+    """
+    Model class for LLM usage.
+    """
+    prompt_tokens: int  # Tokens used for prompt
+    prompt_unit_price: Decimal  # Unit price for prompt
+    prompt_price_unit: Decimal  # Price unit for prompt, i.e., the unit price based on how many tokens
+    prompt_price: Decimal  # Cost for prompt
+    completion_tokens: int  # Tokens used for response
+    completion_unit_price: Decimal  # Unit price for response
+    completion_price_unit: Decimal  # Price unit for response, i.e., the unit price based on how many tokens
+    completion_price: Decimal  # Cost for response
+    total_tokens: int  # Total number of tokens used
+    total_price: Decimal  # Total cost
+    currency: str  # Currency unit
+    latency: float  # Request latency (s)
+```
+
+---
+
+### TextEmbeddingResult
+
+```python
+class TextEmbeddingResult(BaseModel):
+    """
+    Model class for text embedding result.
+    """
+    model: str  # Actual model used
+    embeddings: list[list[float]]  # List of embedding vectors, corresponding to the input texts list
+    usage: EmbeddingUsage  # Usage information
+```
+
+### EmbeddingUsage
+
+```python
+class EmbeddingUsage(ModelUsage):
+    """
+    Model class for embedding usage.
+    """
+    tokens: int  # Number of tokens used
+    total_tokens: int  # Total number of tokens used
+    unit_price: Decimal  # Unit price
+    price_unit: Decimal  # Price unit, i.e., the unit price based on how many tokens
+    total_price: Decimal  # Total cost
+    currency: str  # Currency unit
+    latency: float  # Request latency (s)
+```
+
+---
+
+### RerankResult
+
+```python
+class RerankResult(BaseModel):
+    """
+    Model class for rerank result.
+    """
+    model: str  # Actual model used
+    docs: list[RerankDocument]  # Reranked document list	
+```
+
+### RerankDocument
+
+```python
+class RerankDocument(BaseModel):
+    """
+    Model class for rerank document.
+    """
+    index: int  # original index
+    text: str
+    score: float
+```

api/core/model_runtime/docs/en_US/predefined_model_scale_out.md

@@ -0,0 +1,173 @@
+## Predefined Model Integration
+
+After completing the vendor integration, the next step is to integrate the models from the vendor.
+
+First, we need to determine the type of model to be integrated and create the corresponding model type `module` under the respective vendor's directory.
+
+Currently supported model types are:
+
+- `llm` Text Generation Model
+- `text_embedding` Text Embedding Model
+- `rerank` Rerank Model
+- `speech2text` Speech-to-Text
+- `tts` Text-to-Speech
+- `moderation` Moderation
+
+Continuing with `Anthropic` as an example, `Anthropic` only supports LLM, so create a `module` named `llm` under `model_providers.anthropic`.
+
+For predefined models, we first need to create a YAML file named after the model under the `llm` `module`, such as `claude-2.1.yaml`.
+
+### Prepare Model YAML
+
+```yaml
+model: claude-2.1  # Model identifier
+# Display name of the model, which can be set to en_US English or zh_Hans Chinese. If zh_Hans is not set, it will default to en_US.
+# This can also be omitted, in which case the model identifier will be used as the label
+label:
+  en_US: claude-2.1
+model_type: llm  # Model type, claude-2.1 is an LLM
+features:  # Supported features, agent-thought supports Agent reasoning, vision supports image understanding
+- agent-thought
+model_properties:  # Model properties
+  mode: chat  # LLM mode, complete for text completion models, chat for conversation models
+  context_size: 200000  # Maximum context size
+parameter_rules:  # Parameter rules for the model call; only LLM requires this
+- name: temperature  # Parameter variable name
+  # Five default configuration templates are provided: temperature/top_p/max_tokens/presence_penalty/frequency_penalty
+  # The template variable name can be set directly in use_template, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE
+  # Additional configuration parameters will override the default configuration if set
+  use_template: temperature
+- name: top_p
+  use_template: top_p
+- name: top_k
+  label:  # Display name of the parameter
+    zh_Hans: 取样数量
+    en_US: Top k
+  type: int  # Parameter type, supports float/int/string/boolean
+  help:  # Help information, describing the parameter's function
+    zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+    en_US: Only sample from the top K options for each subsequent token.
+  required: false  # Whether the parameter is mandatory; can be omitted
+- name: max_tokens_to_sample
+  use_template: max_tokens
+  default: 4096  # Default value of the parameter
+  min: 1  # Minimum value of the parameter, applicable to float/int only
+  max: 4096  # Maximum value of the parameter, applicable to float/int only
+pricing:  # Pricing information
+  input: '8.00'  # Input unit price, i.e., prompt price
+  output: '24.00'  # Output unit price, i.e., response content price
+  unit: '0.000001'  # Price unit, meaning the above prices are per 100K
+  currency: USD  # Price currency
+```
+
+It is recommended to prepare all model configurations before starting the implementation of the model code.
+
+You can also refer to the YAML configuration information under the corresponding model type directories of other vendors in the `model_providers` directory. For the complete YAML rules, refer to: [Schema](schema.md#aimodelentity).
+
+### Implement the Model Call Code
+
+Next, create a Python file named `llm.py` under the `llm` `module` to write the implementation code.
+
+Create an Anthropic LLM class named `AnthropicLargeLanguageModel` (or any other name), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
+
+- LLM Call
+
+Implement the core method for calling the LLM, supporting both streaming and synchronous responses.
+
+```python
+  def _invoke(self, model: str, credentials: dict,
+              prompt_messages: list[PromptMessage], model_parameters: dict,
+              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
+              stream: bool = True, user: Optional[str] = None) \
+          -> Union[LLMResult, Generator]:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param model_parameters: model parameters
+      :param tools: tools for tool calling
+      :param stop: stop words
+      :param stream: is stream response
+      :param user: unique user id
+      :return: full response or stream response chunk generator result
+      """
+```
+
+Ensure to use two functions for returning data, one for synchronous returns and the other for streaming returns, because Python identifies functions containing the `yield` keyword as generator functions, fixing the return type to `Generator`. Thus, synchronous and streaming returns need to be implemented separately, as shown below (note that the example uses simplified parameters, for actual implementation follow the above parameter list):
+
+```python
+  def _invoke(self, stream: bool, **kwargs) \
+          -> Union[LLMResult, Generator]:
+      if stream:
+            return self._handle_stream_response(**kwargs)
+      return self._handle_sync_response(**kwargs)
+
+  def _handle_stream_response(self, **kwargs) -> Generator:
+      for chunk in response:
+            yield chunk
+  def _handle_sync_response(self, **kwargs) -> LLMResult:
+      return LLMResult(**response)
+```
+
+- Pre-compute Input Tokens
+
+If the model does not provide an interface to precompute tokens, return 0 directly.
+
+```python
+  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
+                     tools: Optional[list[PromptMessageTool]] = None) -> int:
+      """
+      Get number of tokens for given prompt messages
+
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param tools: tools for tool calling
+      :return:
+      """
+```
+
+- Validate Model Credentials
+
+Similar to vendor credential validation, but specific to a single model.
+
+```python
+  def validate_credentials(self, model: str, credentials: dict) -> None:
+      """
+      Validate model credentials
+  
+      :param model: model name
+      :param credentials: model credentials
+      :return:
+      """
+```
+
+- Map Invoke Errors
+
+When a model call fails, map it to a specific `InvokeError` type as required by Runtime, allowing Dify to handle different errors accordingly.
+
+Runtime Errors:
+
+- `InvokeConnectionError` Connection error
+
+- `InvokeServerUnavailableError` Service provider unavailable
+- `InvokeRateLimitError` Rate limit reached
+- `InvokeAuthorizationError` Authorization failed
+- `InvokeBadRequestError` Parameter error
+
+```python
+  @property
+  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+      """
+      Map model invoke error to unified error
+      The key is the error type thrown to the caller
+      The value is the error type thrown by the model,
+      which needs to be converted into a unified error type for the caller.
+  
+      :return: Invoke error mapping
+      """
+```
+
+For interface method explanations, see: [Interfaces](./interfaces.md). For detailed implementation, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

api/core/model_runtime/docs/en_US/provider_scale_out.md

@@ -0,0 +1,265 @@
+## Adding a New Provider
+
+Providers support three types of model configuration methods:
+
+- `predefined-model` Predefined model
+
+  This indicates that users only need to configure the unified provider credentials to use the predefined models under the provider.
+
+- `customizable-model` Customizable model
+
+  Users need to add credential configurations for each model.
+
+- `fetch-from-remote` Fetch from remote
+
+  This is consistent with the `predefined-model` configuration method. Only unified provider credentials need to be configured, and models are obtained from the provider through credential information.
+
+These three configuration methods **can coexist**, meaning a provider can support `predefined-model` + `customizable-model` or `predefined-model` + `fetch-from-remote`, etc. In other words, configuring the unified provider credentials allows the use of predefined and remotely fetched models, and if new models are added, they can be used in addition to the custom models.
+
+## Getting Started
+
+Adding a new provider starts with determining the English identifier of the provider, such as `anthropic`, and using this identifier to create a `module` in `model_providers`.
+
+Under this `module`, we first need to prepare the provider's YAML configuration.
+
+### Preparing Provider YAML
+
+Here, using `Anthropic` as an example, we preset the provider's basic information, supported model types, configuration methods, and credential rules.
+
+```YAML
+provider: anthropic  # Provider identifier
+label:  # Provider display name, can be set in en_US English and zh_Hans Chinese, zh_Hans will default to en_US if not set.
+  en_US: Anthropic
+icon_small:  # Small provider icon, stored in the _assets directory under the corresponding provider implementation directory, same language strategy as label
+  en_US: icon_s_en.png
+icon_large:  # Large provider icon, stored in the _assets directory under the corresponding provider implementation directory, same language strategy as label
+  en_US: icon_l_en.png
+supported_model_types:  # Supported model types, Anthropic only supports LLM
+- llm
+configurate_methods:  # Supported configuration methods, Anthropic only supports predefined models
+- predefined-model
+provider_credential_schema:  # Provider credential rules, as Anthropic only supports predefined models, unified provider credential rules need to be defined
+  credential_form_schemas:  # List of credential form items
+  - variable: anthropic_api_key  # Credential parameter variable name
+    label:  # Display name
+      en_US: API Key
+    type: secret-input  # Form type, here secret-input represents an encrypted information input box, showing masked information when editing.
+    required: true  # Whether required
+    placeholder:  # Placeholder information
+      zh_Hans: Enter your API Key here
+      en_US: Enter your API Key
+  - variable: anthropic_api_url
+    label:
+      en_US: API URL
+    type: text-input  # Form type, here text-input represents a text input box
+    required: false
+    placeholder:
+      zh_Hans: Enter your API URL here
+      en_US: Enter your API URL
+```
+
+You can also refer to the YAML configuration information under other provider directories in `model_providers`. The complete YAML rules are available at: [Schema](schema.md#provider).
+
+### Implementing Provider Code
+
+Providers need to inherit the `__base.model_provider.ModelProvider` base class and implement the `validate_provider_credentials` method for unified provider credential verification. For reference, see [AnthropicProvider](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/anthropic.py).
+> If the provider is the type of `customizable-model`, there is no need to implement the `validate_provider_credentials` method.
+
+```python
+def validate_provider_credentials(self, credentials: dict) -> None:
+    """
+    Validate provider credentials
+    You can choose any validate_credentials method of model type or implement validate method by yourself,
+    such as: get model list api
+
+    if validate failed, raise exception
+
+    :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
+    """
+```
+
+Of course, you can also preliminarily reserve the implementation of `validate_provider_credentials` and directly reuse it after the model credential verification method is implemented.
+
+---
+
+### Adding Models
+
+After the provider integration is complete, the next step is to integrate models under the provider.
+
+First, we need to determine the type of the model to be integrated and create a `module` for the corresponding model type in the provider's directory.
+
+The currently supported model types are as follows:
+
+- `llm` Text generation model
+- `text_embedding` Text Embedding model
+- `rerank` Rerank model
+- `speech2text` Speech to text
+- `tts` Text to speech
+- `moderation` Moderation
+
+Continuing with `Anthropic` as an example, since `Anthropic` only supports LLM, we create a `module` named `llm` in `model_providers.anthropic`.
+
+For predefined models, we first need to create a YAML file named after the model, such as `claude-2.1.yaml`, under the `llm` `module`.
+
+#### Preparing Model YAML
+
+```yaml
+model: claude-2.1  # Model identifier
+# Model display name, can be set in en_US English and zh_Hans Chinese, zh_Hans will default to en_US if not set.
+# Alternatively, if the label is not set, use the model identifier content.
+label:
+  en_US: claude-2.1
+model_type: llm  # Model type, claude-2.1 is an LLM
+features:  # Supported features, agent-thought for Agent reasoning, vision for image understanding
+- agent-thought
+model_properties:  # Model properties
+  mode: chat  # LLM mode, complete for text completion model, chat for dialogue model
+  context_size: 200000  # Maximum supported context size
+parameter_rules:  # Model invocation parameter rules, only required for LLM
+- name: temperature  # Invocation parameter variable name
+  # Default preset with 5 variable content configuration templates: temperature/top_p/max_tokens/presence_penalty/frequency_penalty
+  # Directly set the template variable name in use_template, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE
+  # If additional configuration parameters are set, they will override the default configuration
+  use_template: temperature
+- name: top_p
+  use_template: top_p
+- name: top_k
+  label:  # Invocation parameter display name
+    zh_Hans: Sampling quantity
+    en_US: Top k
+  type: int  # Parameter type, supports float/int/string/boolean
+  help:  # Help information, describing the role of the parameter
+    zh_Hans: Only sample from the top K options for each subsequent token.
+    en_US: Only sample from the top K options for each subsequent token.
+  required: false  # Whether required, can be left unset
+- name: max_tokens_to_sample
+  use_template: max_tokens
+  default: 4096  # Default parameter value
+  min: 1  # Minimum parameter value, only applicable for float/int
+  max: 4096  # Maximum parameter value, only applicable for float/int
+pricing:  # Pricing information
+  input: '8.00'  # Input price, i.e., Prompt price
+  output: '24.00'  # Output price, i.e., returned content price
+  unit: '0.000001'  # Pricing unit, i.e., the above prices are per 100K
+  currency: USD  # Currency
+```
+
+It is recommended to prepare all model configurations before starting the implementation of the model code.
+
+Similarly, you can also refer to the YAML configuration information for corresponding model types of other providers in the `model_providers` directory. The complete YAML rules can be found at: [Schema](schema.md#AIModel).
+
+#### Implementing Model Invocation Code
+
+Next, you need to create a python file named `llm.py` under the `llm` `module` to write the implementation code.
+
+In `llm.py`, create an Anthropic LLM class, which we name `AnthropicLargeLanguageModel` (arbitrarily), inheriting the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
+
+- LLM Invocation
+
+  Implement the core method for LLM invocation, which can support both streaming and synchronous returns.
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              prompt_messages: list[PromptMessage], model_parameters: dict,
+              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
+              stream: bool = True, user: Optional[str] = None) \
+          -> Union[LLMResult, Generator]:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param model_parameters: model parameters
+      :param tools: tools for tool calling
+      :param stop: stop words
+      :param stream: is stream response
+      :param user: unique user id
+      :return: full response or stream response chunk generator result
+      """
+  ```
+
+- Pre-calculating Input Tokens
+
+  If the model does not provide a pre-calculated tokens interface, you can directly return 0.
+
+  ```python
+  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
+                   tools: Optional[list[PromptMessageTool]] = None) -> int:
+    """
+    Get number of tokens for given prompt messages
+
+    :param model: model name
+    :param credentials: model credentials
+    :param prompt_messages: prompt messages
+    :param tools: tools for tool calling
+    :return:
+    """
+  ```
+
+- Model Credential Verification
+
+  Similar to provider credential verification, this step involves verification for an individual model.
+
+  ```python
+  def validate_credentials(self, model: str, credentials: dict) -> None:
+      """
+      Validate model credentials
+  
+      :param model: model name
+      :param credentials: model credentials
+      :return:
+      """
+  ```
+
+- Invocation Error Mapping Table
+
+  When there is an exception in model invocation, it needs to be mapped to the `InvokeError` type specified by Runtime. This facilitates Dify's ability to handle different errors with appropriate follow-up actions.
+
+  Runtime Errors:
+
+  - `InvokeConnectionError` Invocation connection error
+  - `InvokeServerUnavailableError` Invocation service provider unavailable
+  - `InvokeRateLimitError` Invocation reached rate limit
+  - `InvokeAuthorizationError` Invocation authorization failure
+  - `InvokeBadRequestError` Invocation parameter error
+
+  ```python
+  @property
+  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+      """
+      Map model invoke error to unified error
+      The key is the error type thrown to the caller
+      The value is the error type thrown by the model,
+      which needs to be converted into a unified error type for the caller.
+  
+      :return: Invoke error mapping
+      """
+  ```
+
+For details on the interface methods, see: [Interfaces](interfaces.md). For specific implementations, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).
+
+### Testing
+
+To ensure the availability of integrated providers/models, each method written needs corresponding integration test code in the `tests` directory.
+
+Continuing with `Anthropic` as an example:
+
+Before writing test code, you need to first add the necessary credential environment variables for the test provider in `.env.example`, such as: `ANTHROPIC_API_KEY`.
+
+Before execution, copy `.env.example` to `.env` and then execute.
+
+#### Writing Test Code
+
+Create a `module` with the same name as the provider in the `tests` directory: `anthropic`, and continue to create `test_provider.py` and test py files for the corresponding model types within this module, as shown below:
+
+```shell
+.
+├── __init__.py
+├── anthropic
+│   ├── __init__.py
+│   ├── test_llm.py       # LLM Testing
+│   └── test_provider.py  # Provider Testing
+```
+
+Write test code for all the various cases implemented above and submit the code after passing the tests.

api/core/model_runtime/docs/en_US/schema.md

@@ -0,0 +1,206 @@
+# Configuration Rules
+
+- Provider rules are based on the [Provider](#Provider) entity.
+- Model rules are based on the [AIModelEntity](#AIModelEntity) entity.
+
+> All entities mentioned below are based on `Pydantic BaseModel` and can be found in the `entities` module.
+
+### Provider
+
+- `provider` (string) Provider identifier, e.g., `openai`
+- `label` (object) Provider display name, i18n, with `en_US` English and `zh_Hans` Chinese language settings
+  - `zh_Hans` (string) [optional] Chinese label name, if `zh_Hans` is not set, `en_US` will be used by default.
+  - `en_US` (string) English label name
+- `description` (object) Provider description, i18n
+  - `zh_Hans` (string) [optional] Chinese description
+  - `en_US` (string) English description
+- `icon_small` (string) [optional] Small provider ICON, stored in the `_assets` directory under the corresponding provider implementation directory, with the same language strategy as `label`
+  - `zh_Hans` (string) Chinese ICON
+  - `en_US` (string) English ICON
+- `icon_large` (string) [optional] Large provider ICON, stored in the `_assets` directory under the corresponding provider implementation directory, with the same language strategy as `label`
+  - `zh_Hans` (string) Chinese ICON
+  - `en_US` (string) English ICON
+- `background` (string) [optional] Background color value, e.g., #FFFFFF, if empty, the default frontend color value will be displayed.
+- `help` (object) [optional] help information
+  - `title` (object) help title, i18n
+    - `zh_Hans` (string) [optional] Chinese title
+    - `en_US` (string) English title
+  - `url` (object) help link, i18n
+    - `zh_Hans` (string) [optional] Chinese link
+    - `en_US` (string) English link
+- `supported_model_types` (array[[ModelType](#ModelType)]) Supported model types
+- `configurate_methods` (array[[ConfigurateMethod](#ConfigurateMethod)]) Configuration methods
+- `provider_credential_schema` ([ProviderCredentialSchema](#ProviderCredentialSchema)) Provider credential specification
+- `model_credential_schema` ([ModelCredentialSchema](#ModelCredentialSchema)) Model credential specification
+
+### AIModelEntity
+
+- `model` (string) Model identifier, e.g., `gpt-3.5-turbo`
+- `label` (object) [optional] Model display name, i18n, with `en_US` English and `zh_Hans` Chinese language settings
+  - `zh_Hans` (string) [optional] Chinese label name
+  - `en_US` (string) English label name
+- `model_type` ([ModelType](#ModelType)) Model type
+- `features` (array[[ModelFeature](#ModelFeature)]) [optional] Supported feature list
+- `model_properties` (object) Model properties
+  - `mode` ([LLMMode](#LLMMode)) Mode (available for model type `llm`)
+  - `context_size` (int) Context size (available for model types `llm`, `text-embedding`)
+  - `max_chunks` (int) Maximum number of chunks (available for model types `text-embedding`, `moderation`)
+  - `file_upload_limit` (int) Maximum file upload limit, in MB (available for model type `speech2text`)
+  - `supported_file_extensions` (string) Supported file extension formats, e.g., mp3, mp4 (available for model type `speech2text`)
+  - `default_voice` (string)  default voice, e.g.：alloy,echo,fable,onyx,nova,shimmer（available for model type `tts`）
+  - `voices` (list)  List of available voice.（available for model type `tts`）
+    - `mode` (string)  voice model.（available for model type `tts`）
+    - `name` (string)  voice model display name.（available for model type `tts`）
+    - `language` (string)  the voice model supports languages.（available for model type `tts`）
+  - `word_limit` (int)  Single conversion word limit, paragraph-wise by default（available for model type `tts`）
+  - `audio_type` (string)  Support audio file extension format, e.g.：mp3,wav（available for model type `tts`）
+  - `max_workers` (int)  Number of concurrent workers supporting text and audio conversion（available for model type`tts`）
+  - `max_characters_per_chunk` (int) Maximum characters per chunk (available for model type `moderation`)
+- `parameter_rules` (array[[ParameterRule](#ParameterRule)]) [optional] Model invocation parameter rules
+- `pricing` ([PriceConfig](#PriceConfig)) [optional] Pricing information
+- `deprecated` (bool) Whether deprecated. If deprecated, the model will no longer be displayed in the list, but those already configured can continue to be used. Default False.
+
+### ModelType
+
+- `llm` Text generation model
+- `text-embedding` Text Embedding model
+- `rerank` Rerank model
+- `speech2text` Speech to text
+- `tts` Text to speech
+- `moderation` Moderation
+
+### ConfigurateMethod
+
+- `predefined-model` Predefined model
+
+  Indicates that users can use the predefined models under the provider by configuring the unified provider credentials.
+- `customizable-model` Customizable model
+
+  Users need to add credential configuration for each model.
+
+- `fetch-from-remote` Fetch from remote
+
+  Consistent with the `predefined-model` configuration method, only unified provider credentials need to be configured, and models are obtained from the provider through credential information.
+
+### ModelFeature
+
+- `agent-thought` Agent reasoning, generally over 70B with thought chain capability.
+- `vision` Vision, i.e., image understanding.
+- `tool-call`
+- `multi-tool-call`
+- `stream-tool-call`
+
+### FetchFrom
+
+- `predefined-model` Predefined model
+- `fetch-from-remote` Remote model
+
+### LLMMode
+
+- `complete` Text completion
+- `chat` Dialogue
+
+### ParameterRule
+
+- `name` (string) Actual model invocation parameter name
+- `use_template` (string) [optional] Using template
+
+  By default, 5 variable content configuration templates are preset:
+
+  - `temperature`
+  - `top_p`
+  - `frequency_penalty`
+  - `presence_penalty`
+  - `max_tokens`
+  
+  In use_template, you can directly set the template variable name, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE
+  No need to set any parameters other than `name` and `use_template`. If additional configuration parameters are set, they will override the default configuration.
+  Refer to `openai/llm/gpt-3.5-turbo.yaml`.
+
+- `label` (object) [optional] Label, i18n
+
+  - `zh_Hans`(string) [optional] Chinese label name
+  - `en_US` (string) English label name
+
+- `type`(string) [optional] Parameter type
+
+  - `int` Integer
+  - `float` Float
+  - `string` String
+  - `boolean` Boolean
+
+- `help` (string) [optional] Help information
+
+  - `zh_Hans` (string) [optional] Chinese help information
+  - `en_US` (string) English help information
+
+- `required` (bool) Required, default False.
+
+- `default`(int/float/string/bool) [optional] Default value
+
+- `min`(int/float) [optional] Minimum value, applicable only to numeric types
+
+- `max`(int/float) [optional] Maximum value, applicable only to numeric types
+
+- `precision`(int) [optional] Precision, number of decimal places to keep, applicable only to numeric types
+
+- `options` (array[string]) [optional] Dropdown option values, applicable only when `type` is `string`, if not set or null, option values are not restricted
+
+### PriceConfig
+
+- `input` (float) Input price, i.e., Prompt price
+- `output` (float) Output price, i.e., returned content price
+- `unit` (float) Pricing unit, e.g., if the price is measured in 1M tokens, the corresponding token amount for the unit price is `0.000001`.
+- `currency` (string) Currency unit
+
+### ProviderCredentialSchema
+
+- `credential_form_schemas` (array[[CredentialFormSchema](#CredentialFormSchema)]) Credential form standard
+
+### ModelCredentialSchema
+
+- `model` (object) Model identifier, variable name defaults to `model`
+  - `label` (object) Model form item display name
+    - `en_US` (string) English
+    - `zh_Hans`(string) [optional] Chinese
+  - `placeholder` (object) Model prompt content
+    - `en_US`(string) English
+    - `zh_Hans`(string) [optional] Chinese
+- `credential_form_schemas` (array[[CredentialFormSchema](#CredentialFormSchema)]) Credential form standard
+
+### CredentialFormSchema
+
+- `variable` (string) Form item variable name
+- `label` (object) Form item label name
+  - `en_US`(string) English
+  - `zh_Hans` (string) [optional] Chinese
+- `type` ([FormType](#FormType)) Form item type
+- `required` (bool) Whether required
+- `default`(string) Default value
+- `options` (array[[FormOption](#FormOption)]) Specific property of form items of type `select` or `radio`, defining dropdown content
+- `placeholder`(object) Specific property of form items of type `text-input`, placeholder content
+  - `en_US`(string) English
+  - `zh_Hans` (string) [optional] Chinese
+- `max_length` (int) Specific property of form items of type `text-input`, defining maximum input length, 0 for no limit.
+- `show_on` (array[[FormShowOnObject](#FormShowOnObject)]) Displayed when other form item values meet certain conditions, displayed always if empty.
+
+### FormType
+
+- `text-input` Text input component
+- `secret-input` Password input component
+- `select` Single-choice dropdown
+- `radio` Radio component
+- `switch` Switch component, only supports `true` and `false` values
+
+### FormOption
+
+- `label` (object) Label
+  - `en_US`(string) English
+  - `zh_Hans`(string) [optional] Chinese
+- `value` (string) Dropdown option value
+- `show_on` (array[[FormShowOnObject](#FormShowOnObject)]) Displayed when other form item values meet certain conditions, displayed always if empty.
+
+### FormShowOnObject
+
+- `variable` (string) Variable name of other form items
+- `value` (string) Variable value of other form items

api/core/model_runtime/docs/zh_Hans/customizable_model_scale_out.md

@@ -0,0 +1,297 @@
+## 自定义预定义模型接入
+
+### 介绍
+
+供应商集成完成后，接下来为供应商下模型的接入，为了帮助理解整个接入过程，我们以`Xinference`为例，逐步完成一个完整的供应商接入。
+
+需要注意的是，对于自定义模型，每一个模型的接入都需要填写一个完整的供应商凭据。
+
+而不同于预定义模型，自定义供应商接入时永远会拥有如下两个参数，不需要在供应商yaml中定义。
+
+![Alt text](images/index/image-3.png)
+
+
+在前文中，我们已经知道了供应商无需实现`validate_provider_credential`，Runtime会自行根据用户在此选择的模型类型和模型名称调用对应的模型层的`validate_credentials`来进行验证。
+
+### 编写供应商yaml
+
+我们首先要确定，接入的这个供应商支持哪些类型的模型。
+
+当前支持模型类型如下：
+
+- `llm` 文本生成模型
+- `text_embedding` 文本 Embedding 模型
+- `rerank` Rerank 模型
+- `speech2text` 语音转文字
+- `tts` 文字转语音
+- `moderation` 审查
+
+`Xinference`支持`LLM`和`Text Embedding`和Rerank，那么我们开始编写`xinference.yaml`。
+
+```yaml
+provider: xinference #确定供应商标识
+label: # 供应商展示名称，可设置 en_US 英文、zh_Hans 中文两种语言，zh_Hans 不设置将默认使用 en_US。
+  en_US: Xorbits Inference
+icon_small: # 小图标，可以参考其他供应商的图标，存储在对应供应商实现目录下的 _assets 目录，中英文策略同 label
+  en_US: icon_s_en.svg
+icon_large: # 大图标
+  en_US: icon_l_en.svg
+help: # 帮助
+  title:
+    en_US: How to deploy Xinference
+    zh_Hans: 如何部署 Xinference
+  url:
+    en_US: https://github.com/xorbitsai/inference
+supported_model_types: # 支持的模型类型，Xinference同时支持LLM/Text Embedding/Rerank
+- llm
+- text-embedding
+- rerank
+configurate_methods: # 因为Xinference为本地部署的供应商，并且没有预定义模型，需要用什么模型需要根据Xinference的文档自己部署，所以这里只支持自定义模型
+- customizable-model
+provider_credential_schema:
+  credential_form_schemas:
+```
+
+随后，我们需要思考在Xinference中定义一个模型需要哪些凭据
+
+- 它支持三种不同的模型，因此，我们需要有`model_type`来指定这个模型的类型，它有三种类型，所以我们这么编写
+```yaml
+provider_credential_schema:
+  credential_form_schemas:
+  - variable: model_type
+    type: select
+    label:
+      en_US: Model type
+      zh_Hans: 模型类型
+    required: true
+    options:
+    - value: text-generation
+      label:
+        en_US: Language Model
+        zh_Hans: 语言模型
+    - value: embeddings
+      label:
+        en_US: Text Embedding
+    - value: reranking
+      label:
+        en_US: Rerank
+```
+- 每一个模型都有自己的名称`model_name`，因此需要在这里定义
+```yaml
+  - variable: model_name
+    type: text-input
+    label:
+      en_US: Model name
+      zh_Hans: 模型名称
+    required: true
+    placeholder:
+      zh_Hans: 填写模型名称
+      en_US: Input model name
+```
+- 填写Xinference本地部署的地址
+```yaml
+  - variable: server_url
+    label:
+      zh_Hans: 服务器URL
+      en_US: Server url
+    type: text-input
+    required: true
+    placeholder:
+      zh_Hans: 在此输入Xinference的服务器地址，如 https://example.com/xxx
+      en_US: Enter the url of your Xinference, for example https://example.com/xxx
+```
+- 每个模型都有唯一的model_uid，因此需要在这里定义
+```yaml
+  - variable: model_uid
+    label:
+      zh_Hans: 模型UID
+      en_US: Model uid
+    type: text-input
+    required: true
+    placeholder:
+      zh_Hans: 在此输入您的Model UID
+      en_US: Enter the model uid
+```
+现在，我们就完成了供应商的基础定义。
+
+### 编写模型代码
+
+然后我们以`llm`类型为例，编写`xinference.llm.llm.py`
+
+在 `llm.py` 中创建一个 Xinference LLM 类，我们取名为 `XinferenceAILargeLanguageModel`（随意），继承 `__base.large_language_model.LargeLanguageModel` 基类，实现以下几个方法：
+
+- LLM 调用
+
+  实现 LLM 调用的核心方法，可同时支持流式和同步返回。
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              prompt_messages: list[PromptMessage], model_parameters: dict,
+              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
+              stream: bool = True, user: Optional[str] = None) \
+          -> Union[LLMResult, Generator]:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param model_parameters: model parameters
+      :param tools: tools for tool calling
+      :param stop: stop words
+      :param stream: is stream response
+      :param user: unique user id
+      :return: full response or stream response chunk generator result
+      """
+  ```
+
+  在实现时，需要注意使用两个函数来返回数据，分别用于处理同步返回和流式返回，因为Python会将函数中包含 `yield` 关键字的函数识别为生成器函数，返回的数据类型固定为 `Generator`，因此同步和流式返回需要分别实现，就像下面这样（注意下面例子使用了简化参数，实际实现时需要按照上面的参数列表进行实现）：
+
+  ```python
+  def _invoke(self, stream: bool, **kwargs) \
+          -> Union[LLMResult, Generator]:
+      if stream:
+            return self._handle_stream_response(**kwargs)
+      return self._handle_sync_response(**kwargs)
+
+  def _handle_stream_response(self, **kwargs) -> Generator:
+      for chunk in response:
+            yield chunk
+  def _handle_sync_response(self, **kwargs) -> LLMResult:
+      return LLMResult(**response)
+  ```
+
+- 预计算输入 tokens
+
+  若模型未提供预计算 tokens 接口，可直接返回 0。
+
+  ```python
+  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
+                   tools: Optional[list[PromptMessageTool]] = None) -> int:
+    """
+    Get number of tokens for given prompt messages
+
+    :param model: model name
+    :param credentials: model credentials
+    :param prompt_messages: prompt messages
+    :param tools: tools for tool calling
+    :return:
+    """
+  ```
+
+  有时候，也许你不需要直接返回0，所以你可以使用`self._get_num_tokens_by_gpt2(text: str)`来获取预计算的tokens，这个方法位于`AIModel`基类中，它会使用GPT2的Tokenizer进行计算，但是只能作为替代方法，并不完全准确。
+
+- 模型凭据校验
+
+  与供应商凭据校验类似，这里针对单个模型进行校验。
+
+  ```python
+  def validate_credentials(self, model: str, credentials: dict) -> None:
+      """
+      Validate model credentials
+  
+      :param model: model name
+      :param credentials: model credentials
+      :return:
+      """
+  ```
+
+- 模型参数Schema
+  
+  与自定义类型不同，由于没有在yaml文件中定义一个模型支持哪些参数，因此，我们需要动态时间模型参数的Schema。
+  
+  如Xinference支持`max_tokens` `temperature` `top_p` 这三个模型参数。
+  
+  但是有的供应商根据不同的模型支持不同的参数，如供应商`OpenLLM`支持`top_k`，但是并不是这个供应商提供的所有模型都支持`top_k`，我们这里举例A模型支持`top_k`，B模型不支持`top_k`，那么我们需要在这里动态生成模型参数的Schema，如下所示：
+  
+    ```python
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+        """
+            used to define customizable model schema
+        """
+        rules = [
+            ParameterRule(
+                name='temperature', type=ParameterType.FLOAT,
+                use_template='temperature',
+                label=I18nObject(
+                    zh_Hans='温度', en_US='Temperature'
+                )
+            ),
+            ParameterRule(
+                name='top_p', type=ParameterType.FLOAT,
+                use_template='top_p',
+                label=I18nObject(
+                    zh_Hans='Top P', en_US='Top P'
+                )
+            ),
+            ParameterRule(
+                name='max_tokens', type=ParameterType.INT,
+                use_template='max_tokens',
+                min=1,
+                default=512,
+                label=I18nObject(
+                    zh_Hans='最大生成长度', en_US='Max Tokens'
+                )
+            )
+        ]
+
+        # if model is A, add top_k to rules
+        if model == 'A':
+            rules.append(
+                ParameterRule(
+                    name='top_k', type=ParameterType.INT,
+                    use_template='top_k',
+                    min=1,
+                    default=50,
+                    label=I18nObject(
+                        zh_Hans='Top K', en_US='Top K'
+                    )
+                )
+            )
+
+        """
+            some NOT IMPORTANT code here
+        """
+
+        entity = AIModelEntity(
+            model=model,
+            label=I18nObject(
+                en_US=model
+            ),
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_type=model_type,
+            model_properties={ 
+                ModelPropertyKey.MODE:  ModelType.LLM,
+            },
+            parameter_rules=rules
+        )
+
+        return entity
+    ```
+    
+- 调用异常错误映射表
+
+  当模型调用异常时需要映射到 Runtime 指定的 `InvokeError` 类型，方便 Dify 针对不同错误做不同后续处理。
+
+  Runtime Errors:
+
+  - `InvokeConnectionError` 调用连接错误
+  - `InvokeServerUnavailableError ` 调用服务方不可用
+  - `InvokeRateLimitError ` 调用达到限额
+  - `InvokeAuthorizationError`  调用鉴权失败
+  - `InvokeBadRequestError ` 调用传参有误
+
+  ```python
+  @property
+  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+      """
+      Map model invoke error to unified error
+      The key is the error type thrown to the caller
+      The value is the error type thrown by the model,
+      which needs to be converted into a unified error type for the caller.
+  
+      :return: Invoke error mapping
+      """
+  ```
+
+接口方法说明见：[Interfaces](./interfaces.md)，具体实现可参考：[llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py)。

api/core/model_runtime/docs/zh_Hans/interfaces.md

@@ -0,0 +1,746 @@
+# 接口方法
+
+这里介绍供应商和各模型类型需要实现的接口方法和参数说明。
+
+## 供应商
+
+继承 `__base.model_provider.ModelProvider` 基类，实现以下接口：
+
+```python
+def validate_provider_credentials(self, credentials: dict) -> None:
+    """
+    Validate provider credentials
+    You can choose any validate_credentials method of model type or implement validate method by yourself,
+    such as: get model list api
+
+    if validate failed, raise exception
+
+    :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
+    """
+```
+
+- `credentials` (object) 凭据信息
+
+  凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 定义，传入如：`api_key` 等。
+
+验证失败请抛出 `errors.validate.CredentialsValidateFailedError` 错误。
+
+**注：预定义模型需完整实现该接口，自定义模型供应商只需要如下简单实现即可**
+
+```python
+class XinferenceProvider(Provider):
+    def validate_provider_credentials(self, credentials: dict) -> None:
+        pass
+```
+
+## 模型
+
+模型分为 5 种不同的模型类型，不同模型类型继承的基类不同，需要实现的方法也不同。
+
+### 通用接口
+
+所有模型均需要统一实现下面 2 个方法：
+
+- 模型凭据校验
+
+  与供应商凭据校验类似，这里针对单个模型进行校验。
+
+  ```python
+  def validate_credentials(self, model: str, credentials: dict) -> None:
+      """
+      Validate model credentials
+  
+      :param model: model name
+      :param credentials: model credentials
+      :return:
+      """
+  ```
+
+  参数：
+
+  - `model` (string) 模型名称
+
+  - `credentials` (object) 凭据信息
+
+    凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
+
+  验证失败请抛出 `errors.validate.CredentialsValidateFailedError` 错误。
+
+- 调用异常错误映射表
+
+  当模型调用异常时需要映射到 Runtime 指定的 `InvokeError` 类型，方便 Dify 针对不同错误做不同后续处理。
+
+  Runtime Errors:
+
+  - `InvokeConnectionError` 调用连接错误
+  - `InvokeServerUnavailableError ` 调用服务方不可用
+  - `InvokeRateLimitError ` 调用达到限额
+  - `InvokeAuthorizationError`  调用鉴权失败
+  - `InvokeBadRequestError ` 调用传参有误
+
+  ```python
+  @property
+  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+      """
+      Map model invoke error to unified error
+      The key is the error type thrown to the caller
+      The value is the error type thrown by the model,
+      which needs to be converted into a unified error type for the caller.
+  
+      :return: Invoke error mapping
+      """
+  ```
+
+  也可以直接抛出对应 Errors，并做如下定义，这样在之后的调用中可以直接抛出`InvokeConnectionError`等异常。
+  
+    ```python
+    @property
+    def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+        return {
+            InvokeConnectionError: [
+              InvokeConnectionError
+            ],
+            InvokeServerUnavailableError: [
+              InvokeServerUnavailableError
+            ],
+            InvokeRateLimitError: [
+              InvokeRateLimitError
+            ],
+            InvokeAuthorizationError: [
+              InvokeAuthorizationError
+            ],
+            InvokeBadRequestError: [
+              InvokeBadRequestError
+            ],
+        }
+    ```
+
+​	可参考 OpenAI `_invoke_error_mapping`。  
+
+### LLM
+
+继承 `__base.large_language_model.LargeLanguageModel` 基类，实现以下接口：
+
+- LLM 调用
+
+  实现 LLM 调用的核心方法，可同时支持流式和同步返回。
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              prompt_messages: list[PromptMessage], model_parameters: dict,
+              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
+              stream: bool = True, user: Optional[str] = None) \
+          -> Union[LLMResult, Generator]:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param model_parameters: model parameters
+      :param tools: tools for tool calling
+      :param stop: stop words
+      :param stream: is stream response
+      :param user: unique user id
+      :return: full response or stream response chunk generator result
+      """
+  ```
+
+  - 参数：
+
+    - `model` (string) 模型名称
+
+    - `credentials` (object) 凭据信息
+    
+      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
+
+    - `prompt_messages` (array[[PromptMessage](#PromptMessage)]) Prompt 列��
+    
+      若模型为 `Completion` 类型，则列表只需要传入一个 [UserPromptMessage](#UserPromptMessage) 元素即可；
+    
+      若模型为 `Chat` 类型，需要根据消息不同传入 [SystemPromptMessage](#SystemPromptMessage), [UserPromptMessage](#UserPromptMessage), [AssistantPromptMessage](#AssistantPromptMessage), [ToolPromptMessage](#ToolPromptMessage) 元素列表
+
+    - `model_parameters` (object) 模型参数
+    
+      模型参数由模型 YAML 配置的 `parameter_rules` 定义。
+
+    - `tools` (array[[PromptMessageTool](#PromptMessageTool)]) [optional] 工具列表，等同于 `function calling` 中的 `function`。
+    
+      即传入 tool calling 的工具列表。
+
+    - `stop` (array[string]) [optional] 停止序列
+    
+      模型返回将在停止序列定义的字符串之前停止输出。
+
+    - `stream` (bool) 是否流式输出，默认 True
+    
+      流式输出返回 Generator[[LLMResultChunk](#LLMResultChunk)]，非流式输出返回 [LLMResult](#LLMResult)。
+
+    - `user` (string) [optional] 用户的唯一标识符
+    
+      可以帮助供应商监控和检测滥用行为。
+
+  - 返回
+
+    流式输出返回 Generator[[LLMResultChunk](#LLMResultChunk)]，非流式输出返回 [LLMResult](#LLMResult)。
+
+- 预计算输入 tokens
+
+  若模型未提供预计算 tokens 接口，可直接返回 0。
+
+  ```python
+  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
+                     tools: Optional[list[PromptMessageTool]] = None) -> int:
+      """
+      Get number of tokens for given prompt messages
+
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param tools: tools for tool calling
+      :return:
+      """
+  ```
+
+  参数说明见上述 `LLM 调用`。
+
+  该接口需要根据对应`model`选择合适的`tokenizer`进行计算，如果对应模型没有提供`tokenizer`，可以使用`AIModel`基类中的`_get_num_tokens_by_gpt2(text: str)`方法进行计算。
+
+- 获取自定义模型规则 [可选]
+
+  ```python
+  def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+      """
+      Get customizable model schema
+
+      :param model: model name
+      :param credentials: model credentials
+      :return: model schema
+      """
+  ```
+
+​当供应商支持增加自定义 LLM 时，可实现此方法让自定义模型可获取模型规则，默认返回 None。
+
+对于`OpenAI`供应商下的大部分微调模型，可以通过其微调模型名称获取到其基类模型，如`gpt-3.5-turbo-1106`，然后返回基类模型的预定义参数规则，参考[openai](https://github.com/langgenius/dify/blob/feat/model-runtime/api/core/model_runtime/model_providers/openai/llm/llm.py#L801)
+的具体实现
+
+### TextEmbedding
+
+继承 `__base.text_embedding_model.TextEmbeddingModel` 基类，实现以下接口：
+
+- Embedding 调用
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              texts: list[str], user: Optional[str] = None) \
+          -> TextEmbeddingResult:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param texts: texts to embed
+      :param user: unique user id
+      :return: embeddings result
+      """
+  ```
+
+  - 参数：
+
+    - `model` (string) 模型名称
+
+    - `credentials` (object) 凭据信息
+
+      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
+
+    - `texts` (array[string]) 文本列表，可批量处理
+
+    - `user` (string) [optional] 用户的唯一标识符
+
+      可以帮助供应商监控和检测滥用行为。
+
+  - 返回：
+
+    [TextEmbeddingResult](#TextEmbeddingResult) 实体。
+
+- 预计算 tokens
+
+  ```python
+  def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
+      """
+      Get number of tokens for given prompt messages
+
+      :param model: model name
+      :param credentials: model credentials
+      :param texts: texts to embed
+      :return:
+      """
+  ```
+
+  参数说明见上述 `Embedding 调用`。
+
+  同上述`LargeLanguageModel`，该接口需要根据对应`model`选择合适的`tokenizer`进行计算，如果对应模型没有提供`tokenizer`，可以使用`AIModel`基类中的`_get_num_tokens_by_gpt2(text: str)`方法进行计算。
+
+### Rerank
+
+继承 `__base.rerank_model.RerankModel` 基类，实现以下接口：
+
+- rerank 调用
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              query: str, docs: list[str], score_threshold: Optional[float] = None, top_n: Optional[int] = None,
+              user: Optional[str] = None) \
+          -> RerankResult:
+      """
+      Invoke rerank model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param query: search query
+      :param docs: docs for reranking
+      :param score_threshold: score threshold
+      :param top_n: top n
+      :param user: unique user id
+      :return: rerank result
+      """
+  ```
+
+  - 参数：
+
+    - `model` (string) 模型名称
+
+    - `credentials` (object) 凭据信息
+
+      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
+
+    - `query` (string) 查询请求内容
+
+    - `docs` (array[string]) 需要重排的分段列表
+
+    - `score_threshold` (float) [optional] Score 阈值
+
+    - `top_n` (int) [optional] 取前 n 个分段
+
+    - `user` (string) [optional] 用户的唯一标识符
+
+      可以帮助供应商监控和检测滥用行为。
+
+  - 返回：
+
+    [RerankResult](#RerankResult) 实体。
+
+### Speech2text
+
+继承 `__base.speech2text_model.Speech2TextModel` 基类，实现以下接口：
+
+- Invoke 调用
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              file: IO[bytes], user: Optional[str] = None) \
+          -> str:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param file: audio file
+      :param user: unique user id
+      :return: text for given audio file
+      """	
+  ```
+
+  - 参数：
+
+    - `model` (string) 模型名称
+
+    - `credentials` (object) 凭据信息
+
+      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
+
+    - `file` (File) 文件流
+
+    - `user` (string) [optional] 用户的唯一标识符
+
+      可以帮助供应商监控和检测滥用行为。
+
+  - 返回：
+
+    语音转换后的字符串。
+
+### Text2speech
+
+继承 `__base.text2speech_model.Text2SpeechModel` 基类，实现以下接口：
+
+- Invoke 调用
+
+  ```python
+  def _invoke(self, model: str, credentials: dict, content_text: str, streaming: bool, user: Optional[str] = None):
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param content_text: text content to be translated
+      :param streaming: output is streaming
+      :param user: unique user id
+      :return: translated audio file
+      """	
+  ```
+
+  - 参数：
+
+    - `model` (string) 模型名称
+
+    - `credentials` (object) 凭据信息
+
+      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
+
+    - `content_text` (string) 需要转换的文本内容
+
+    - `streaming` (bool) 是否进行流式输出
+
+    - `user` (string) [optional] 用户的唯一标识符
+
+      可以帮助供应商监控和检测滥用行为。
+
+  - 返回：
+
+    文本转换后的语音流。
+
+### Moderation
+
+继承 `__base.moderation_model.ModerationModel` 基类，实现以下接口：
+
+- Invoke 调用
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              text: str, user: Optional[str] = None) \
+          -> bool:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param text: text to moderate
+      :param user: unique user id
+      :return: false if text is safe, true otherwise
+      """
+  ```
+
+  - 参数：
+
+    - `model` (string) 模型名称
+
+    - `credentials` (object) 凭据信息
+
+      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
+
+    - `text` (string) 文本内容
+
+    - `user` (string) [optional] 用户的唯一标识符
+
+      可以帮助供应商监控和检测滥用行为。
+
+  - 返回：
+
+    False 代表传入的文本安全，True 则反之。
+
+
+
+## 实体
+
+### PromptMessageRole 
+
+消息角色
+
+```python
+class PromptMessageRole(Enum):
+    """
+    Enum class for prompt message.
+    """
+    SYSTEM = "system"
+    USER = "user"
+    ASSISTANT = "assistant"
+    TOOL = "tool"
+```
+
+### PromptMessageContentType
+
+消息内容类型，分为纯文本和图片。
+
+```python
+class PromptMessageContentType(Enum):
+    """
+    Enum class for prompt message content type.
+    """
+    TEXT = 'text'
+    IMAGE = 'image'
+```
+
+### PromptMessageContent
+
+消息内容基类，仅作为参数声明用，不可初始化。
+
+```python
+class PromptMessageContent(BaseModel):
+    """
+    Model class for prompt message content.
+    """
+    type: PromptMessageContentType
+    data: str  # 内容数据
+```
+
+当前支持文本和图片两种类型，可支持同时传入文本和多图。
+
+需要分别初始化 `TextPromptMessageContent` 和 `ImagePromptMessageContent` 传入。
+
+### TextPromptMessageContent
+
+```python
+class TextPromptMessageContent(PromptMessageContent):
+    """
+    Model class for text prompt message content.
+    """
+    type: PromptMessageContentType = PromptMessageContentType.TEXT
+```
+
+若传入图文，其中文字需要构造此实体作为 `content` 列表中的一部分。
+
+### ImagePromptMessageContent
+
+```python
+class ImagePromptMessageContent(PromptMessageContent):
+    """
+    Model class for image prompt message content.
+    """
+    class DETAIL(Enum):
+        LOW = 'low'
+        HIGH = 'high'
+
+    type: PromptMessageContentType = PromptMessageContentType.IMAGE
+    detail: DETAIL = DETAIL.LOW  # 分辨率
+```
+
+若传入图文，其中图片需要构造此实体作为 `content` 列表中的一部分
+
+`data` 可以为 `url` 或者图片 `base64` 加密后的字符串。
+
+### PromptMessage
+
+所有 Role 消息体的基类，仅作为参数声明用，不可初始化。
+
+```python
+class PromptMessage(ABC, BaseModel):
+    """
+    Model class for prompt message.
+    """
+    role: PromptMessageRole  # 消息角色
+    content: Optional[str | list[PromptMessageContent]] = None  # 支持两种类型，字符串和内容列表，内容列表是为了满足多模态的需要，可详见 PromptMessageContent 说明。
+    name: Optional[str] = None  # 名称，可选。
+```
+
+### UserPromptMessage
+
+UserMessage 消息体，代表用户消息。
+
+```python
+class UserPromptMessage(PromptMessage):
+    """
+    Model class for user prompt message.
+    """
+    role: PromptMessageRole = PromptMessageRole.USER
+```
+
+### AssistantPromptMessage
+
+代表模型返回消息，通常用于 `few-shots` 或聊天历史传入。
+
+```python
+class AssistantPromptMessage(PromptMessage):
+    """
+    Model class for assistant prompt message.
+    """
+    class ToolCall(BaseModel):
+        """
+        Model class for assistant prompt message tool call.
+        """
+        class ToolCallFunction(BaseModel):
+            """
+            Model class for assistant prompt message tool call function.
+            """
+            name: str  # 工具名称
+            arguments: str  # 工具参数
+
+        id: str  # 工具 ID，仅在 OpenAI tool call 生效，为工具调用的唯一 ID，同一个工具可以调用多次
+        type: str  # 默认 function
+        function: ToolCallFunction  # 工具调用信息
+
+    role: PromptMessageRole = PromptMessageRole.ASSISTANT
+    tool_calls: list[ToolCall] = []  # 模型回复的工具调用结果（仅当传入 tools，并且模型认为需要调用工具时返回）
+```
+
+其中 `tool_calls` 为调用模型传入 `tools` 后，由模型返回的 `tool call` 列表。
+
+### SystemPromptMessage
+
+代表系统消息，通常用于设定给模型的系统指令。
+
+```python
+class SystemPromptMessage(PromptMessage):
+    """
+    Model class for system prompt message.
+    """
+    role: PromptMessageRole = PromptMessageRole.SYSTEM
+```
+
+### ToolPromptMessage
+
+代表工具消息，用于工具执行后将结果交给模型进行下一步计划。
+
+```python
+class ToolPromptMessage(PromptMessage):
+    """
+    Model class for tool prompt message.
+    """
+    role: PromptMessageRole = PromptMessageRole.TOOL
+    tool_call_id: str  # 工具调用 ID，若不支持 OpenAI tool call，也可传入工具名称
+```
+
+基类的 `content` 传入工具执行结果。
+
+### PromptMessageTool
+
+```python
+class PromptMessageTool(BaseModel):
+    """
+    Model class for prompt message tool.
+    """
+    name: str  # 工具名称
+    description: str  # 工具描述
+    parameters: dict  # 工具参数 dict
+```
+
+---
+
+### LLMResult
+
+```python
+class LLMResult(BaseModel):
+    """
+    Model class for llm result.
+    """
+    model: str  # 实际使用模型
+    prompt_messages: list[PromptMessage]  # prompt 消息列表
+    message: AssistantPromptMessage  # 回复消息
+    usage: LLMUsage  # 使用的 tokens 及费用信息
+    system_fingerprint: Optional[str] = None  # 请求指纹，可参考 OpenAI 该参数定义
+```
+
+### LLMResultChunkDelta
+
+流式返回中每个迭代内部 `delta` 实体
+
+```python
+class LLMResultChunkDelta(BaseModel):
+    """
+    Model class for llm result chunk delta.
+    """
+    index: int  # 序号
+    message: AssistantPromptMessage  # 回复消息
+    usage: Optional[LLMUsage] = None  # 使用的 tokens 及费用信息，仅最后一条返回
+    finish_reason: Optional[str] = None  # 结束原因，仅最后一条返回
+```
+
+### LLMResultChunk
+
+流式返回中每个迭代实体
+
+```python
+class LLMResultChunk(BaseModel):
+    """
+    Model class for llm result chunk.
+    """
+    model: str  # 实际使用模型
+    prompt_messages: list[PromptMessage]  # prompt 消息列表
+    system_fingerprint: Optional[str] = None  # 请求指纹，可参考 OpenAI 该参数定义
+    delta: LLMResultChunkDelta  # 每个迭代存在变化的内容
+```
+
+### LLMUsage
+
+```python
+class LLMUsage(ModelUsage):
+    """
+    Model class for llm usage.
+    """
+    prompt_tokens: int  # prompt 使用 tokens
+    prompt_unit_price: Decimal  # prompt 单价
+    prompt_price_unit: Decimal  # prompt 价格单位，即单价基于多少 tokens 
+    prompt_price: Decimal  # prompt 费用
+    completion_tokens: int  # 回复使用 tokens
+    completion_unit_price: Decimal  # 回复单价
+    completion_price_unit: Decimal  # 回复价格单位，即单价基于多少 tokens 
+    completion_price: Decimal  # 回复费用
+    total_tokens: int  # 总使用 token 数
+    total_price: Decimal  # 总费用
+    currency: str  # 货币单位
+    latency: float  # 请求耗时(s)
+```
+
+---
+
+### TextEmbeddingResult
+
+```python
+class TextEmbeddingResult(BaseModel):
+    """
+    Model class for text embedding result.
+    """
+    model: str  # 实际使用模型
+    embeddings: list[list[float]]  # embedding 向量列表，对应传入的 texts 列表
+    usage: EmbeddingUsage  # 使用信息
+```
+
+### EmbeddingUsage
+
+```python
+class EmbeddingUsage(ModelUsage):
+    """
+    Model class for embedding usage.
+    """
+    tokens: int  # 使用 token 数
+    total_tokens: int  # 总使用 token 数
+    unit_price: Decimal  # 单价
+    price_unit: Decimal  # 价格单位，即单价基于多少 tokens
+    total_price: Decimal  # 总费用
+    currency: str  # 货币单位
+    latency: float  # 请求耗时(s)
+```
+
+---
+
+### RerankResult
+
+```python
+class RerankResult(BaseModel):
+    """
+    Model class for rerank result.
+    """
+    model: str  # 实际使用模型
+    docs: list[RerankDocument]  # 重排后的分段列表	
+```
+
+### RerankDocument
+
+```python
+class RerankDocument(BaseModel):
+    """
+    Model class for rerank document.
+    """
+    index: int  # 原序号
+    text: str  # 分段文本内容
+    score: float  # 分数
+```

api/core/model_runtime/docs/zh_Hans/predefined_model_scale_out.md

@@ -0,0 +1,172 @@
+## 预定义模型接入
+
+供应商集成完成后，接下来为供应商下模型的接入。
+
+我们首先需要确定接入模型的类型，并在对应供应商的目录下创建对应模型类型的 `module`。
+
+当前支持模型类型如下：
+
+- `llm` 文本生成模型
+- `text_embedding` 文本 Embedding 模型
+- `rerank` Rerank 模型
+- `speech2text` 语音转文字
+- `tts` 文字转语音
+- `moderation` 审查
+
+依旧以 `Anthropic` 为例，`Anthropic` 仅支持 LLM，因此在 `model_providers.anthropic` 创建一个 `llm` 为名称的 `module`。
+
+对于预定义的模型，我们首先需要在 `llm` `module` 下创建以模型名为文件名称的 YAML 文件，如：`claude-2.1.yaml`。
+
+### 准备模型 YAML
+
+```yaml
+model: claude-2.1  # 模型标识
+# 模型展示名称，可设置 en_US 英文、zh_Hans 中文两种语言，zh_Hans 不设置将默认使用 en_US。
+# 也可不设置 label，则使用 model 标识内容。
+label:
+  en_US: claude-2.1
+model_type: llm  # 模型类型，claude-2.1 为 LLM
+features:  # 支持功能，agent-thought 为支持 Agent 推理，vision 为支持图片理解
+- agent-thought
+model_properties:  # 模型属性
+  mode: chat  # LLM 模式，complete 文本补全模型，chat 对话模型
+  context_size: 200000  # 支持最大上下文大小
+parameter_rules:  # 模型调用参数规则，仅 LLM 需要提供
+- name: temperature  # 调用参数变量名
+  # 默认预置了 5 种变量内容配置模板，temperature/top_p/max_tokens/presence_penalty/frequency_penalty
+  # 可在 use_template 中直接设置模板变量名，将会使用 entities.defaults.PARAMETER_RULE_TEMPLATE 中的默认配置
+  # 若设置了额外的配置参数，将覆盖默认配置
+  use_template: temperature
+- name: top_p
+  use_template: top_p
+- name: top_k
+  label:  # 调用参数展示名称
+    zh_Hans: 取样数量
+    en_US: Top k
+  type: int  # 参数类型，支持 float/int/string/boolean
+  help:  # 帮助信息，描述参数作用
+    zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+    en_US: Only sample from the top K options for each subsequent token.
+  required: false  # 是否必填，可不设置
+- name: max_tokens_to_sample
+  use_template: max_tokens
+  default: 4096  # 参数默认值
+  min: 1  # 参数最小值，仅 float/int 可用
+  max: 4096  # 参数最大值，仅 float/int 可用
+pricing:  # 价格信息
+  input: '8.00'  # 输入单价，即 Prompt 单价
+  output: '24.00'  # 输出单价，即返回内容单价
+  unit: '0.000001'  # 价格单位，即上述价格为每 100K 的单价
+  currency: USD  # 价格货币
+```
+
+建议将所有模型配置都准备完毕后再开始模型代码的实现。
+
+同样，也可以参考  `model_providers` 目录下其他供应商对应模型类型目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#aimodelentity)。
+
+### 实现模型调用代码
+
+接下来需要在 `llm` `module` 下创建一个同名的 python 文件 `llm.py` 来编写代码实现。
+
+在 `llm.py` 中创建一个 Anthropic LLM 类，我们取名为 `AnthropicLargeLanguageModel`（随意），继承 `__base.large_language_model.LargeLanguageModel` 基类，实现以下几个方法：
+
+- LLM 调用
+
+  实现 LLM 调用的核心方法，可同时支持流式和同步返回。
+
+  ```python
+  def _invoke(self, model: str, credentials: dict,
+              prompt_messages: list[PromptMessage], model_parameters: dict,
+              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
+              stream: bool = True, user: Optional[str] = None) \
+          -> Union[LLMResult, Generator]:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param model_parameters: model parameters
+      :param tools: tools for tool calling
+      :param stop: stop words
+      :param stream: is stream response
+      :param user: unique user id
+      :return: full response or stream response chunk generator result
+      """
+  ```
+
+  在实现时，需要注意使用两个函数来返回数据，分别用于处理同步返回和流式返回，因为Python会将函数中包含 `yield` 关键字的函数识别为生成器函数，返回的数据类型固定为 `Generator`，因此同步和流式返回需要分别实现，就像下面这样（注意下面例子使用了简化参数，实际实现时需要按照上面的参数列表进行实现）：
+
+  ```python
+  def _invoke(self, stream: bool, **kwargs) \
+          -> Union[LLMResult, Generator]:
+      if stream:
+            return self._handle_stream_response(**kwargs)
+      return self._handle_sync_response(**kwargs)
+
+  def _handle_stream_response(self, **kwargs) -> Generator:
+      for chunk in response:
+            yield chunk
+  def _handle_sync_response(self, **kwargs) -> LLMResult:
+      return LLMResult(**response)
+  ```
+
+- 预计算输入 tokens
+
+  若模型未提供预计算 tokens 接口，可直接返回 0。
+
+  ```python
+  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
+                     tools: Optional[list[PromptMessageTool]] = None) -> int:
+      """
+      Get number of tokens for given prompt messages
+
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param tools: tools for tool calling
+      :return:
+      """
+  ```
+
+- 模型凭据校验
+
+  与供应商凭据校验类似，这里针对单个模型进行校验。
+
+  ```python
+  def validate_credentials(self, model: str, credentials: dict) -> None:
+      """
+      Validate model credentials
+  
+      :param model: model name
+      :param credentials: model credentials
+      :return:
+      """
+  ```
+
+- 调用异常错误映射表
+
+  当模型调用异常时需要映射到 Runtime 指定的 `InvokeError` 类型，方便 Dify 针对不同错误做不同后续处理。
+
+  Runtime Errors:
+
+  - `InvokeConnectionError` 调用连接错误
+  - `InvokeServerUnavailableError ` 调用服务方不可用
+  - `InvokeRateLimitError ` 调用达到限额
+  - `InvokeAuthorizationError`  调用鉴权失败
+  - `InvokeBadRequestError ` 调用传参有误
+
+  ```python
+  @property
+  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+      """
+      Map model invoke error to unified error
+      The key is the error type thrown to the caller
+      The value is the error type thrown by the model,
+      which needs to be converted into a unified error type for the caller.
+  
+      :return: Invoke error mapping
+      """
+  ```
+
+接口方法说明见：[Interfaces](./interfaces.md)，具体实现可参考：[llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py)。

api/core/model_runtime/docs/zh_Hans/provider_scale_out.md

@@ -0,0 +1,188 @@
+## 增加新供应商
+
+供应商支持三种模型配置方式：
+
+- `predefined-model  ` 预定义模型
+
+  表示用户只需要配置统一的供应商凭据即可使用供应商下的预定义模型。
+  
+- `customizable-model` 自定义模型
+
+  用户需要新增每个模型的凭据配置，如Xinference，它同时支持 LLM 和 Text Embedding，但是每个模型都有唯一的**model_uid**，如果想要将两者同时接入，就需要为每个模型配置一个**model_uid**。
+
+- `fetch-from-remote` 从远程获取
+
+  与 `predefined-model` 配置方式一致，只需要配置统一的供应商凭据即可，模型通过凭据信息从供应商获取。
+
+  如OpenAI，我们可以基于gpt-turbo-3.5来Fine Tune多个模型，而他们都位于同一个**api_key**下，当配置为 `fetch-from-remote` 时，开发者只需要配置统一的**api_key**即可让DifyRuntime获取到开发者所有的微调模型并接入Dify。
+
+这三种配置方式**支持共存**，即存在供应商支持 `predefined-model` + `customizable-model` 或 `predefined-model` + `fetch-from-remote` 等，也就是配置了供应商统一凭据可以使用预定义模型和从远程获取的模型，若新增了模型，则可以在此基础上额外使用自定义的模型。
+
+## 开始
+
+### 介绍
+
+#### 名词解释
+ - `module`: 一个`module`即为一个Python Package，或者通俗一点，称为一个文件夹，里面包含了一个`__init__.py`文件，以及其他的`.py`文件。
+
+#### 步骤
+新增一个供应商主要分为几步，这里简单列出，帮助大家有一个大概的认识，具体的步骤会在下面详细介绍。
+
+- 创建供应商yaml文件，根据[ProviderSchema](./schema.md#provider)编写
+- 创建供应商代码，实现一个`class`。
+- 根据模型类型，在供应商`module`下创建对应的模型类型 `module`，如`llm`或`text_embedding`。
+- 根据模型类型，在对应的模型`module`下创建同名的代码文件，如`llm.py`，并实现一个`class`。
+- 如果有预定义模型，根据模型名称创建同名的yaml文件在模型`module`下，如`claude-2.1.yaml`，根据[AIModelEntity](./schema.md#aimodelentity)编写。
+- 编写测试代码，确保功能可用。
+
+### 开始吧
+
+增加一个新的供应商需要先确定供应商的英文标识，如 `anthropic`，使用该标识在 `model_providers` 创建以此为名称的 `module`。
+
+在此 `module` 下，我们需要先准备供应商的 YAML 配置。
+
+#### 准备供应商 YAML
+
+此处以 `Anthropic` 为例，预设了供应商基础信息、支持的模型类型、配置方式、凭据规则。
+
+```YAML
+provider: anthropic  # 供应商标识
+label:  # 供应商展示名称，可设置 en_US 英文、zh_Hans 中文两种语言，zh_Hans 不设置将默认使用 en_US。
+  en_US: Anthropic
+icon_small:  # 供应商小图标，存储在对应供应商实现目录下的 _assets 目录，中英文策略同 label
+  en_US: icon_s_en.png
+icon_large:  # 供应商大图标，存储在对应供应商实现目录下的 _assets 目录，中英文策略同 label
+  en_US: icon_l_en.png
+supported_model_types:  # 支持的模型类型，Anthropic 仅支持 LLM
+- llm
+configurate_methods:  # 支持的配置方式，Anthropic 仅支持预定义模型
+- predefined-model
+provider_credential_schema:  # 供应商凭据规则，由于 Anthropic 仅支持预定义模型，则需要定义统一供应商凭据规则
+  credential_form_schemas:  # 凭据表单项列表
+  - variable: anthropic_api_key  # 凭据参数变量名
+    label:  # 展示名称
+      en_US: API Key
+    type: secret-input  # 表单类型，此处 secret-input 代表加密信息输入框，编辑时只展示屏蔽后的信息。
+    required: true  # 是否必填
+    placeholder:  # PlaceHolder 信息
+      zh_Hans: 在此输入您的 API Key
+      en_US: Enter your API Key
+  - variable: anthropic_api_url
+    label:
+      en_US: API URL
+    type: text-input  # 表单类型，此处 text-input 代表文本输入框
+    required: false
+    placeholder:
+      zh_Hans: 在此输入您的 API URL
+      en_US: Enter your API URL
+```
+
+如果接入的供应商提供自定义模型，比如`OpenAI`提供微调模型，那么我们就需要添加[`model_credential_schema`](./schema.md#modelcredentialschema)，以`OpenAI`为例：
+
+```yaml
+model_credential_schema:
+  model: # 微调模型名称
+    label:
+      en_US: Model Name
+      zh_Hans: 模型名称
+    placeholder:
+      en_US: Enter your model name
+      zh_Hans: 输入模型名称
+  credential_form_schemas:
+  - variable: openai_api_key
+    label:
+      en_US: API Key
+    type: secret-input
+    required: true
+    placeholder:
+      zh_Hans: 在此输入您的 API Key
+      en_US: Enter your API Key
+  - variable: openai_organization
+    label:
+        zh_Hans: 组织 ID
+        en_US: Organization
+    type: text-input
+    required: false
+    placeholder:
+      zh_Hans: 在此输入您的组织 ID
+      en_US: Enter your Organization ID
+  - variable: openai_api_base
+    label:
+      zh_Hans: API Base
+      en_US: API Base
+    type: text-input
+    required: false
+    placeholder:
+      zh_Hans: 在此输入您的 API Base
+      en_US: Enter your API Base
+```
+
+也可以参考  `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#provider)。
+
+#### 实现供应商代码
+
+我们需要在`model_providers`下创建一个同名的python文件，如`anthropic.py`，并实现一个`class`，继承`__base.provider.Provider`基类，如`AnthropicProvider`。
+
+##### 自定义模型供应商
+
+当供应商为Xinference等自定义模型供应商时，可跳过该步骤，仅创建一个空的`XinferenceProvider`类即可，并实现一个空的`validate_provider_credentials`方法，该方法并不会被实际使用，仅用作避免抽象类无法实例化。
+
+```python
+class XinferenceProvider(Provider):
+    def validate_provider_credentials(self, credentials: dict) -> None:
+        pass
+```
+
+##### 预定义模型供应商
+
+供应商需要继承 `__base.model_provider.ModelProvider` 基类，实现 `validate_provider_credentials` 供应商统一凭据校验方法即可，可参考 [AnthropicProvider](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/anthropic.py)。
+
+```python
+def validate_provider_credentials(self, credentials: dict) -> None:
+    """
+    Validate provider credentials
+    You can choose any validate_credentials method of model type or implement validate method by yourself,
+    such as: get model list api
+
+    if validate failed, raise exception
+
+    :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
+    """
+```
+
+当然也可以先预留 `validate_provider_credentials` 实现，在模型凭据校验方法实现后直接复用。
+
+#### 增加模型
+
+#### [增加预定义模型 👈🏻](./predefined_model_scale_out.md)
+对于预定义模型，我们可以通过简单定义一个yaml，并通过实现调用代码来接入。
+
+#### [增加自定义模型 👈🏻](./customizable_model_scale_out.md)
+对于自定义模型，我们只需要实现调用代码即可接入，但是它需要处理的参数可能会更加复杂。
+
+---
+
+### 测试
+
+为了保证接入供应商/模型的可用性，编写后的每个方法均需要在 `tests` 目录中编写对应的集成测试代码。
+
+依旧以 `Anthropic` 为例。
+
+在编写测试代码前，需要先在 `.env.example` 新增测试供应商所需要的凭据环境变量，如：`ANTHROPIC_API_KEY`。
+
+在执行前需要将 `.env.example` 复制为 `.env` 再执行。
+
+#### 编写测试代码
+
+在 `tests` 目录下创建供应商同名的 `module`: `anthropic`，继续在此模块中创建 `test_provider.py` 以及对应模型类型的 test py 文件，如下所示：
+
+```shell
+.
+├── __init__.py
+├── anthropic
+│   ├── __init__.py
+│   ├── test_llm.py       # LLM 测试
+│   └── test_provider.py  # 供应商测试
+```
+
+针对上面实现的代码的各种情况进行测试代码编写，并测试通过后提交代码。

api/core/model_runtime/docs/zh_Hans/schema.md

@@ -0,0 +1,208 @@
+# 配置规则
+
+- 供应商规则基于 [Provider](#Provider) 实体。
+
+- 模型规则基于 [AIModelEntity](#AIModelEntity) 实体。
+
+> 以下所有实体均基于 `Pydantic BaseModel`，可在 `entities` 模块中找到对应实体。
+
+### Provider
+
+- `provider` (string) 供应商标识，如：`openai`
+- `label` (object) 供应商展示名称，i18n，可设置 `en_US` 英文、`zh_Hans` 中文两种语言
+  - `zh_Hans ` (string) [optional] 中文标签名，`zh_Hans` 不设置将默认使用 `en_US`。
+  - `en_US` (string) 英文标签名
+- `description` (object) [optional] 供应商描述，i18n
+  - `zh_Hans` (string) [optional] 中文描述
+  - `en_US` (string) 英文描述
+- `icon_small` (string) [optional] 供应商小 ICON，存储在对应供应商实现目录下的 `_assets` 目录，中英文策略同 `label`
+  - `zh_Hans` (string)  [optional] 中文 ICON
+  - `en_US` (string) 英文 ICON
+- `icon_large` (string) [optional] 供应商大 ICON，存储在对应供应商实现目录下的 _assets 目录，中英文策略同 label
+  - `zh_Hans `(string) [optional] 中文 ICON
+  - `en_US` (string) 英文 ICON
+- `background` (string) [optional] 背景颜色色值，例：#FFFFFF，为空则展示前端默认色值。
+- `help` (object) [optional] 帮助信息
+  - `title` (object) 帮助标题，i18n
+    - `zh_Hans` (string) [optional] 中文标题
+    - `en_US` (string) 英文标题
+  - `url` (object) 帮助链接，i18n
+    - `zh_Hans` (string) [optional] 中文链接
+    - `en_US` (string) 英文链接
+- `supported_model_types` (array[[ModelType](#ModelType)]) 支持的模型类型
+- `configurate_methods` (array[[ConfigurateMethod](#ConfigurateMethod)]) 配置方式
+- `provider_credential_schema` ([ProviderCredentialSchema](#ProviderCredentialSchema)) 供应商凭据规格
+- `model_credential_schema` ([ModelCredentialSchema](#ModelCredentialSchema)) 模型凭据规格
+
+### AIModelEntity
+
+- `model` (string) 模型标识，如：`gpt-3.5-turbo`
+- `label` (object) [optional] 模型展示名称，i18n，可设置 `en_US` 英文、`zh_Hans` 中文两种语言
+  - `zh_Hans `(string) [optional] 中文标签名
+  - `en_US` (string) 英文标签名
+- `model_type` ([ModelType](#ModelType)) 模型类型
+- `features` (array[[ModelFeature](#ModelFeature)]) [optional] 支持功能列表
+- `model_properties` (object) 模型属性
+  - `mode` ([LLMMode](#LLMMode)) 模式 (模型类型 `llm` 可用)
+  - `context_size` (int) 上下文大小 (模型类型 `llm` `text-embedding` 可用)
+  - `max_chunks` (int) 最大分块数量 (模型类型 `text-embedding ` `moderation` 可用)
+  - `file_upload_limit` (int) 文件最大上传限制，单位：MB。（模型类型 `speech2text` 可用）
+  - `supported_file_extensions` (string)  支持文件扩展格式，如：mp3,mp4（模型类型 `speech2text` 可用）
+  - `default_voice` (string)  缺省音色，必选：alloy,echo,fable,onyx,nova,shimmer（模型类型 `tts` 可用）
+  - `voices` (list)  可选音色列表。
+    - `mode` (string)  音色模型。（模型类型 `tts` 可用）
+    - `name` (string)  音色模型显示名称。（模型类型 `tts` 可用）
+    - `language` (string)  音色模型支持语言。（模型类型 `tts` 可用）
+  - `word_limit` (int)  单次转换字数限制，默认按段落分段（模型类型 `tts` 可用）
+  - `audio_type` (string)  支持音频文件扩展格式，如：mp3,wav（模型类型 `tts` 可用）
+  - `max_workers` (int)  支持文字音频转换并发任务数（模型类型 `tts` 可用）
+  - `max_characters_per_chunk` (int) 每块最大字符数 (模型类型  `moderation` 可用)
+- `parameter_rules` (array[[ParameterRule](#ParameterRule)]) [optional] 模型调用参数规则
+- `pricing` ([PriceConfig](#PriceConfig)) [optional] 价格信息
+- `deprecated` (bool) 是否废弃。若废弃，模型列表将不再展示，但已经配置的可以继续使用，默认 False。
+
+### ModelType
+
+- `llm` 文本生成模型
+- `text-embedding` 文本 Embedding 模型
+- `rerank` Rerank 模型
+- `speech2text` 语音转文字
+- `tts` 文字转语音
+- `moderation` 审查
+
+### ConfigurateMethod
+
+- `predefined-model  ` 预定义模型
+
+  表示用户只需要配置统一的供应商凭据即可使用供应商下的预定义模型。
+- `customizable-model` 自定义模型
+
+  用户需要新增每个模型的凭据配置。
+
+- `fetch-from-remote` 从远程获取
+
+  与 `predefined-model` 配置方式一致，只需要配置统一的供应商凭据即可，模型通过凭据信息从供应商获取。
+
+### ModelFeature
+
+- `agent-thought` Agent 推理，一般超过 70B 有思维链能力。
+- `vision` 视觉，即：图像理解。
+- `tool-call` 工具调用
+- `multi-tool-call` 多工具调用
+- `stream-tool-call` 流式工具调用
+
+### FetchFrom
+
+- `predefined-model` 预定义模型
+- `fetch-from-remote` 远程模型
+
+### LLMMode
+
+- `completion` 文本补全
+- `chat` 对话
+
+### ParameterRule
+
+- `name` (string) 调用模型实际参数名
+
+- `use_template` (string) [optional] 使用模板
+  
+  默认预置了 5 种变量内容配置模板：
+
+  - `temperature`
+  - `top_p`
+  - `frequency_penalty`
+  - `presence_penalty`
+  - `max_tokens`
+  
+  可在 use_template 中直接设置模板变量名，将会使用 entities.defaults.PARAMETER_RULE_TEMPLATE 中的默认配置
+  不用设置除 `name` 和 `use_template` 之外的所有参数，若设置了额外的配置参数，将覆盖默认配置。
+  可参考 `openai/llm/gpt-3.5-turbo.yaml`。
+
+- `label` (object) [optional] 标签，i18n
+
+  - `zh_Hans`(string) [optional] 中文标签名
+  - `en_US` (string) 英文标签名
+
+- `type`(string) [optional] 参数类型
+
+  - `int` 整数
+  - `float` 浮点数
+  - `string` 字符串
+  - `boolean` 布尔型
+
+- `help` (string) [optional] 帮助信息
+
+  - `zh_Hans` (string) [optional] 中文帮助信息
+  - `en_US` (string) 英文帮助信息
+
+- `required` (bool) 是否必填，默认 False。
+
+- `default`(int/float/string/bool) [optional] 默认值
+
+- `min`(int/float) [optional] 最小值，仅数字类型适用
+
+- `max`(int/float) [optional] 最大值，仅数字类型适用
+
+- `precision`(int) [optional] 精度，保留小数位数，仅数字类型适用
+
+- `options` (array[string]) [optional] 下拉选项值，仅当 `type` 为 `string` 时适用，若不设置或为 null 则不限制选项值
+
+### PriceConfig
+
+- `input` (float) 输入单价，即 Prompt 单价
+- `output` (float) 输出单价，即返回内容单价
+- `unit` (float) 价格单位，如以 1M tokens 计价，则单价对应的单位 token 数为 `0.000001`
+- `currency` (string) 货币单位
+
+### ProviderCredentialSchema
+
+- `credential_form_schemas` (array[[CredentialFormSchema](#CredentialFormSchema)]) 凭据表单规范
+
+### ModelCredentialSchema
+
+- `model` (object) 模型标识，变量名默认 `model`
+  - `label` (object) 模型表单项展示名称
+    - `en_US` (string) 英文
+    - `zh_Hans`(string) [optional] 中文
+  - `placeholder` (object) 模型提示内容
+    - `en_US`(string) 英文
+    - `zh_Hans`(string) [optional] 中文
+- `credential_form_schemas` (array[[CredentialFormSchema](#CredentialFormSchema)]) 凭据表单规范
+
+### CredentialFormSchema
+
+- `variable` (string) 表单项变量名
+- `label` (object) 表单项标签名
+  - `en_US`(string) 英文
+  - `zh_Hans` (string) [optional] 中文
+- `type` ([FormType](#FormType)) 表单项类型
+- `required` (bool) 是否必填
+- `default`(string) 默认值
+- `options` (array[[FormOption](#FormOption)]) 表单项为 `select` 或 `radio` 专有属性，定义下拉内容
+- `placeholder`(object) 表单项为 `text-input `专有属性，表单项 PlaceHolder
+  - `en_US`(string) 英文
+  - `zh_Hans` (string) [optional] 中文
+- `max_length` (int) 表单项为`text-input`专有属性，定义输入最大长度，0 为不限制。
+- `show_on` (array[[FormShowOnObject](#FormShowOnObject)]) 当其他表单项值符合条件时显示，为空则始终显示。
+
+### FormType
+
+- `text-input` 文本输入组件
+- `secret-input` 密码输入组件
+- `select` 单选下拉
+- `radio` Radio 组件
+- `switch` 开关组件，仅支持 `true` 和 `false`
+
+### FormOption
+
+- `label` (object) 标签
+  - `en_US`(string) 英文
+  - `zh_Hans`(string) [optional] 中文
+- `value` (string) 下拉选项值
+- `show_on` (array[[FormShowOnObject](#FormShowOnObject)]) 当其他表单项值符合条件时显示，为空则始终显示。
+
+### FormShowOnObject
+
+- `variable` (string) 其他表单项变量名
+- `value` (string) 其他表单项变量值

api/core/model_runtime/entities/__init__.py

@@ -0,0 +1,45 @@
+from .llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from .message_entities import (
+    AssistantPromptMessage,
+    AudioPromptMessageContent,
+    DocumentPromptMessageContent,
+    ImagePromptMessageContent,
+    MultiModalPromptMessageContent,
+    PromptMessage,
+    PromptMessageContent,
+    PromptMessageContentType,
+    PromptMessageRole,
+    PromptMessageTool,
+    SystemPromptMessage,
+    TextPromptMessageContent,
+    ToolPromptMessage,
+    UserPromptMessage,
+    VideoPromptMessageContent,
+)
+from .model_entities import ModelPropertyKey
+
+__all__ = [
+    "AssistantPromptMessage",
+    "AudioPromptMessageContent",
+    "DocumentPromptMessageContent",
+    "ImagePromptMessageContent",
+    "LLMMode",
+    "LLMResult",
+    "LLMResultChunk",
+    "LLMResultChunkDelta",
+    "LLMUsage",
+    "ModelPropertyKey",
+    "MultiModalPromptMessageContent",
+    "PromptMessage",
+    "PromptMessage",
+    "PromptMessageContent",
+    "PromptMessageContentType",
+    "PromptMessageRole",
+    "PromptMessageRole",
+    "PromptMessageTool",
+    "SystemPromptMessage",
+    "TextPromptMessageContent",
+    "ToolPromptMessage",
+    "UserPromptMessage",
+    "VideoPromptMessageContent",
+]

api/core/model_runtime/entities/common_entities.py

@@ -0,0 +1,17 @@
+from typing import Optional
+
+from pydantic import BaseModel
+
+
+class I18nObject(BaseModel):
+    """
+    Model class for i18n object.
+    """
+
+    zh_Hans: Optional[str] = None
+    en_US: str
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        if not self.zh_Hans:
+            self.zh_Hans = self.en_US

api/core/model_runtime/entities/defaults.py

@@ -0,0 +1,130 @@
+from core.model_runtime.entities.model_entities import DefaultParameterName
+
+PARAMETER_RULE_TEMPLATE: dict[DefaultParameterName, dict] = {
+    DefaultParameterName.TEMPERATURE: {
+        "label": {
+            "en_US": "Temperature",
+            "zh_Hans": "温度",
+        },
+        "type": "float",
+        "help": {
+            "en_US": "Controls randomness. Lower temperature results in less random completions."
+            " As the temperature approaches zero, the model will become deterministic and repetitive."
+            " Higher temperature results in more random completions.",
+            "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。"
+            "较高的温度会导致更多的随机完成。",
+        },
+        "required": False,
+        "default": 0.0,
+        "min": 0.0,
+        "max": 1.0,
+        "precision": 2,
+    },
+    DefaultParameterName.TOP_P: {
+        "label": {
+            "en_US": "Top P",
+            "zh_Hans": "Top P",
+        },
+        "type": "float",
+        "help": {
+            "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options"
+            " are considered.",
+            "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。",
+        },
+        "required": False,
+        "default": 1.0,
+        "min": 0.0,
+        "max": 1.0,
+        "precision": 2,
+    },
+    DefaultParameterName.TOP_K: {
+        "label": {
+            "en_US": "Top K",
+            "zh_Hans": "Top K",
+        },
+        "type": "int",
+        "help": {
+            "en_US": "Limits the number of tokens to consider for each step by keeping only the k most likely tokens.",
+            "zh_Hans": "通过只保留每一步中最可能的 k 个标记来限制要考虑的标记数量。",
+        },
+        "required": False,
+        "default": 50,
+        "min": 1,
+        "max": 100,
+        "precision": 0,
+    },
+    DefaultParameterName.PRESENCE_PENALTY: {
+        "label": {
+            "en_US": "Presence Penalty",
+            "zh_Hans": "存在惩罚",
+        },
+        "type": "float",
+        "help": {
+            "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
+            "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。",
+        },
+        "required": False,
+        "default": 0.0,
+        "min": 0.0,
+        "max": 1.0,
+        "precision": 2,
+    },
+    DefaultParameterName.FREQUENCY_PENALTY: {
+        "label": {
+            "en_US": "Frequency Penalty",
+            "zh_Hans": "频率惩罚",
+        },
+        "type": "float",
+        "help": {
+            "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
+            "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。",
+        },
+        "required": False,
+        "default": 0.0,
+        "min": 0.0,
+        "max": 1.0,
+        "precision": 2,
+    },
+    DefaultParameterName.MAX_TOKENS: {
+        "label": {
+            "en_US": "Max Tokens",
+            "zh_Hans": "最大标记",
+        },
+        "type": "int",
+        "help": {
+            "en_US": "Specifies the upper limit on the length of generated results."
+            " If the generated results are truncated, you can increase this parameter.",
+            "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。",
+        },
+        "required": False,
+        "default": 64,
+        "min": 1,
+        "max": 2048,
+        "precision": 0,
+    },
+    DefaultParameterName.RESPONSE_FORMAT: {
+        "label": {
+            "en_US": "Response Format",
+            "zh_Hans": "回复格式",
+        },
+        "type": "string",
+        "help": {
+            "en_US": "Set a response format, ensure the output from llm is a valid code block as possible,"
+            " such as JSON, XML, etc.",
+            "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等",
+        },
+        "required": False,
+        "options": ["JSON", "XML"],
+    },
+    DefaultParameterName.JSON_SCHEMA: {
+        "label": {
+            "en_US": "JSON Schema",
+        },
+        "type": "text",
+        "help": {
+            "en_US": "Set a response json schema will ensure LLM to adhere it.",
+            "zh_Hans": "设置返回的json schema，llm将按照它返回",
+        },
+        "required": False,
+    },
+}

api/core/model_runtime/entities/llm_entities.py

@@ -0,0 +1,143 @@
+from decimal import Decimal
+from enum import StrEnum
+from typing import Optional
+
+from pydantic import BaseModel
+
+from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage
+from core.model_runtime.entities.model_entities import ModelUsage, PriceInfo
+
+
+class LLMMode(StrEnum):
+    """
+    Enum class for large language model mode.
+    """
+
+    COMPLETION = "completion"
+    CHAT = "chat"
+
+    @classmethod
+    def value_of(cls, value: str) -> "LLMMode":
+        """
+        Get value of given mode.
+
+        :param value: mode value
+        :return: mode
+        """
+        for mode in cls:
+            if mode.value == value:
+                return mode
+        raise ValueError(f"invalid mode value {value}")
+
+
+class LLMUsage(ModelUsage):
+    """
+    Model class for llm usage.
+    """
+
+    prompt_tokens: int
+    prompt_unit_price: Decimal
+    prompt_price_unit: Decimal
+    prompt_price: Decimal
+    completion_tokens: int
+    completion_unit_price: Decimal
+    completion_price_unit: Decimal
+    completion_price: Decimal
+    total_tokens: int
+    total_price: Decimal
+    currency: str
+    latency: float
+
+    @classmethod
+    def empty_usage(cls):
+        return cls(
+            prompt_tokens=0,
+            prompt_unit_price=Decimal("0.0"),
+            prompt_price_unit=Decimal("0.0"),
+            prompt_price=Decimal("0.0"),
+            completion_tokens=0,
+            completion_unit_price=Decimal("0.0"),
+            completion_price_unit=Decimal("0.0"),
+            completion_price=Decimal("0.0"),
+            total_tokens=0,
+            total_price=Decimal("0.0"),
+            currency="USD",
+            latency=0.0,
+        )
+
+    def plus(self, other: "LLMUsage") -> "LLMUsage":
+        """
+        Add two LLMUsage instances together.
+
+        :param other: Another LLMUsage instance to add
+        :return: A new LLMUsage instance with summed values
+        """
+        if self.total_tokens == 0:
+            return other
+        else:
+            return LLMUsage(
+                prompt_tokens=self.prompt_tokens + other.prompt_tokens,
+                prompt_unit_price=other.prompt_unit_price,
+                prompt_price_unit=other.prompt_price_unit,
+                prompt_price=self.prompt_price + other.prompt_price,
+                completion_tokens=self.completion_tokens + other.completion_tokens,
+                completion_unit_price=other.completion_unit_price,
+                completion_price_unit=other.completion_price_unit,
+                completion_price=self.completion_price + other.completion_price,
+                total_tokens=self.total_tokens + other.total_tokens,
+                total_price=self.total_price + other.total_price,
+                currency=other.currency,
+                latency=self.latency + other.latency,
+            )
+
+    def __add__(self, other: "LLMUsage") -> "LLMUsage":
+        """
+        Overload the + operator to add two LLMUsage instances.
+
+        :param other: Another LLMUsage instance to add
+        :return: A new LLMUsage instance with summed values
+        """
+        return self.plus(other)
+
+
+class LLMResult(BaseModel):
+    """
+    Model class for llm result.
+    """
+
+    id: Optional[str] = None
+    model: str
+    prompt_messages: list[PromptMessage]
+    message: AssistantPromptMessage
+    usage: LLMUsage
+    system_fingerprint: Optional[str] = None
+
+
+class LLMResultChunkDelta(BaseModel):
+    """
+    Model class for llm result chunk delta.
+    """
+
+    index: int
+    message: AssistantPromptMessage
+    usage: Optional[LLMUsage] = None
+    finish_reason: Optional[str] = None
+
+
+class LLMResultChunk(BaseModel):
+    """
+    Model class for llm result chunk.
+    """
+
+    model: str
+    prompt_messages: list[PromptMessage]
+    system_fingerprint: Optional[str] = None
+    delta: LLMResultChunkDelta
+
+
+class NumTokensResult(PriceInfo):
+    """
+    Model class for number of tokens result.
+    """
+
+    tokens: int

api/core/model_runtime/entities/message_entities.py

@@ -0,0 +1,218 @@
+from abc import ABC
+from collections.abc import Sequence
+from enum import Enum, StrEnum
+from typing import Optional
+
+from pydantic import BaseModel, Field, field_validator
+
+
+class PromptMessageRole(Enum):
+    """
+    Enum class for prompt message.
+    """
+
+    SYSTEM = "system"
+    USER = "user"
+    ASSISTANT = "assistant"
+    TOOL = "tool"
+
+    @classmethod
+    def value_of(cls, value: str) -> "PromptMessageRole":
+        """
+        Get value of given mode.
+
+        :param value: mode value
+        :return: mode
+        """
+        for mode in cls:
+            if mode.value == value:
+                return mode
+        raise ValueError(f"invalid prompt message type value {value}")
+
+
+class PromptMessageTool(BaseModel):
+    """
+    Model class for prompt message tool.
+    """
+
+    name: str
+    description: str
+    parameters: dict
+
+
+class PromptMessageFunction(BaseModel):
+    """
+    Model class for prompt message function.
+    """
+
+    type: str = "function"
+    function: PromptMessageTool
+
+
+class PromptMessageContentType(StrEnum):
+    """
+    Enum class for prompt message content type.
+    """
+
+    TEXT = "text"
+    IMAGE = "image"
+    AUDIO = "audio"
+    VIDEO = "video"
+    DOCUMENT = "document"
+
+
+class PromptMessageContent(BaseModel):
+    """
+    Model class for prompt message content.
+    """
+
+    type: PromptMessageContentType
+
+
+class TextPromptMessageContent(PromptMessageContent):
+    """
+    Model class for text prompt message content.
+    """
+
+    type: PromptMessageContentType = PromptMessageContentType.TEXT
+    data: str
+
+
+class MultiModalPromptMessageContent(PromptMessageContent):
+    """
+    Model class for multi-modal prompt message content.
+    """
+
+    type: PromptMessageContentType
+    format: str = Field(default=..., description="the format of multi-modal file")
+    base64_data: str = Field(default="", description="the base64 data of multi-modal file")
+    url: str = Field(default="", description="the url of multi-modal file")
+    mime_type: str = Field(default=..., description="the mime type of multi-modal file")
+
+    @property
+    def data(self):
+        return self.url or f"data:{self.mime_type};base64,{self.base64_data}"
+
+
+class VideoPromptMessageContent(MultiModalPromptMessageContent):
+    type: PromptMessageContentType = PromptMessageContentType.VIDEO
+
+
+class AudioPromptMessageContent(MultiModalPromptMessageContent):
+    type: PromptMessageContentType = PromptMessageContentType.AUDIO
+
+
+class ImagePromptMessageContent(MultiModalPromptMessageContent):
+    """
+    Model class for image prompt message content.
+    """
+
+    class DETAIL(StrEnum):
+        LOW = "low"
+        HIGH = "high"
+
+    type: PromptMessageContentType = PromptMessageContentType.IMAGE
+    detail: DETAIL = DETAIL.LOW
+
+
+class DocumentPromptMessageContent(MultiModalPromptMessageContent):
+    type: PromptMessageContentType = PromptMessageContentType.DOCUMENT
+
+
+class PromptMessage(ABC, BaseModel):
+    """
+    Model class for prompt message.
+    """
+
+    role: PromptMessageRole
+    content: Optional[str | Sequence[PromptMessageContent]] = None
+    name: Optional[str] = None
+
+    def is_empty(self) -> bool:
+        """
+        Check if prompt message is empty.
+
+        :return: True if prompt message is empty, False otherwise
+        """
+        return not self.content
+
+
+class UserPromptMessage(PromptMessage):
+    """
+    Model class for user prompt message.
+    """
+
+    role: PromptMessageRole = PromptMessageRole.USER
+
+
+class AssistantPromptMessage(PromptMessage):
+    """
+    Model class for assistant prompt message.
+    """
+
+    class ToolCall(BaseModel):
+        """
+        Model class for assistant prompt message tool call.
+        """
+
+        class ToolCallFunction(BaseModel):
+            """
+            Model class for assistant prompt message tool call function.
+            """
+
+            name: str
+            arguments: str
+
+        id: str
+        type: str
+        function: ToolCallFunction
+
+        @field_validator("id", mode="before")
+        @classmethod
+        def transform_id_to_str(cls, value) -> str:
+            if not isinstance(value, str):
+                return str(value)
+            else:
+                return value
+
+    role: PromptMessageRole = PromptMessageRole.ASSISTANT
+    tool_calls: list[ToolCall] = []
+
+    def is_empty(self) -> bool:
+        """
+        Check if prompt message is empty.
+
+        :return: True if prompt message is empty, False otherwise
+        """
+        if not super().is_empty() and not self.tool_calls:
+            return False
+
+        return True
+
+
+class SystemPromptMessage(PromptMessage):
+    """
+    Model class for system prompt message.
+    """
+
+    role: PromptMessageRole = PromptMessageRole.SYSTEM
+
+
+class ToolPromptMessage(PromptMessage):
+    """
+    Model class for tool prompt message.
+    """
+
+    role: PromptMessageRole = PromptMessageRole.TOOL
+    tool_call_id: str
+
+    def is_empty(self) -> bool:
+        """
+        Check if prompt message is empty.
+
+        :return: True if prompt message is empty, False otherwise
+        """
+        if not super().is_empty() and not self.tool_call_id:
+            return False
+
+        return True

api/core/model_runtime/entities/model_entities.py

@@ -0,0 +1,227 @@
+from decimal import Decimal
+from enum import Enum, StrEnum
+from typing import Any, Optional
+
+from pydantic import BaseModel, ConfigDict
+
+from core.model_runtime.entities.common_entities import I18nObject
+
+
+class ModelType(Enum):
+    """
+    Enum class for model type.
+    """
+
+    LLM = "llm"
+    TEXT_EMBEDDING = "text-embedding"
+    RERANK = "rerank"
+    SPEECH2TEXT = "speech2text"
+    MODERATION = "moderation"
+    TTS = "tts"
+    TEXT2IMG = "text2img"
+
+    @classmethod
+    def value_of(cls, origin_model_type: str) -> "ModelType":
+        """
+        Get model type from origin model type.
+
+        :return: model type
+        """
+        if origin_model_type in {"text-generation", cls.LLM.value}:
+            return cls.LLM
+        elif origin_model_type in {"embeddings", cls.TEXT_EMBEDDING.value}:
+            return cls.TEXT_EMBEDDING
+        elif origin_model_type in {"reranking", cls.RERANK.value}:
+            return cls.RERANK
+        elif origin_model_type in {"speech2text", cls.SPEECH2TEXT.value}:
+            return cls.SPEECH2TEXT
+        elif origin_model_type in {"tts", cls.TTS.value}:
+            return cls.TTS
+        elif origin_model_type in {"text2img", cls.TEXT2IMG.value}:
+            return cls.TEXT2IMG
+        elif origin_model_type == cls.MODERATION.value:
+            return cls.MODERATION
+        else:
+            raise ValueError(f"invalid origin model type {origin_model_type}")
+
+    def to_origin_model_type(self) -> str:
+        """
+        Get origin model type from model type.
+
+        :return: origin model type
+        """
+        if self == self.LLM:
+            return "text-generation"
+        elif self == self.TEXT_EMBEDDING:
+            return "embeddings"
+        elif self == self.RERANK:
+            return "reranking"
+        elif self == self.SPEECH2TEXT:
+            return "speech2text"
+        elif self == self.TTS:
+            return "tts"
+        elif self == self.MODERATION:
+            return "moderation"
+        elif self == self.TEXT2IMG:
+            return "text2img"
+        else:
+            raise ValueError(f"invalid model type {self}")
+
+
+class FetchFrom(Enum):
+    """
+    Enum class for fetch from.
+    """
+
+    PREDEFINED_MODEL = "predefined-model"
+    CUSTOMIZABLE_MODEL = "customizable-model"
+
+
+class ModelFeature(Enum):
+    """
+    Enum class for llm feature.
+    """
+
+    TOOL_CALL = "tool-call"
+    MULTI_TOOL_CALL = "multi-tool-call"
+    AGENT_THOUGHT = "agent-thought"
+    VISION = "vision"
+    STREAM_TOOL_CALL = "stream-tool-call"
+    DOCUMENT = "document"
+    VIDEO = "video"
+    AUDIO = "audio"
+
+
+class DefaultParameterName(StrEnum):
+    """
+    Enum class for parameter template variable.
+    """
+
+    TEMPERATURE = "temperature"
+    TOP_P = "top_p"
+    TOP_K = "top_k"
+    PRESENCE_PENALTY = "presence_penalty"
+    FREQUENCY_PENALTY = "frequency_penalty"
+    MAX_TOKENS = "max_tokens"
+    RESPONSE_FORMAT = "response_format"
+    JSON_SCHEMA = "json_schema"
+
+    @classmethod
+    def value_of(cls, value: Any) -> "DefaultParameterName":
+        """
+        Get parameter name from value.
+
+        :param value: parameter value
+        :return: parameter name
+        """
+        for name in cls:
+            if name.value == value:
+                return name
+        raise ValueError(f"invalid parameter name {value}")
+
+
+class ParameterType(Enum):
+    """
+    Enum class for parameter type.
+    """
+
+    FLOAT = "float"
+    INT = "int"
+    STRING = "string"
+    BOOLEAN = "boolean"
+    TEXT = "text"
+
+
+class ModelPropertyKey(Enum):
+    """
+    Enum class for model property key.
+    """
+
+    MODE = "mode"
+    CONTEXT_SIZE = "context_size"
+    MAX_CHUNKS = "max_chunks"
+    FILE_UPLOAD_LIMIT = "file_upload_limit"
+    SUPPORTED_FILE_EXTENSIONS = "supported_file_extensions"
+    MAX_CHARACTERS_PER_CHUNK = "max_characters_per_chunk"
+    DEFAULT_VOICE = "default_voice"
+    VOICES = "voices"
+    WORD_LIMIT = "word_limit"
+    AUDIO_TYPE = "audio_type"
+    MAX_WORKERS = "max_workers"
+
+
+class ProviderModel(BaseModel):
+    """
+    Model class for provider model.
+    """
+
+    model: str
+    label: I18nObject
+    model_type: ModelType
+    features: Optional[list[ModelFeature]] = None
+    fetch_from: FetchFrom
+    model_properties: dict[ModelPropertyKey, Any]
+    deprecated: bool = False
+    model_config = ConfigDict(protected_namespaces=())
+
+
+class ParameterRule(BaseModel):
+    """
+    Model class for parameter rule.
+    """
+
+    name: str
+    use_template: Optional[str] = None
+    label: I18nObject
+    type: ParameterType
+    help: Optional[I18nObject] = None
+    required: bool = False
+    default: Optional[Any] = None
+    min: Optional[float] = None
+    max: Optional[float] = None
+    precision: Optional[int] = None
+    options: list[str] = []
+
+
+class PriceConfig(BaseModel):
+    """
+    Model class for pricing info.
+    """
+
+    input: Decimal
+    output: Optional[Decimal] = None
+    unit: Decimal
+    currency: str
+
+
+class AIModelEntity(ProviderModel):
+    """
+    Model class for AI model.
+    """
+
+    parameter_rules: list[ParameterRule] = []
+    pricing: Optional[PriceConfig] = None
+
+
+class ModelUsage(BaseModel):
+    pass
+
+
+class PriceType(Enum):
+    """
+    Enum class for price type.
+    """
+
+    INPUT = "input"
+    OUTPUT = "output"
+
+
+class PriceInfo(BaseModel):
+    """
+    Model class for price info.
+    """
+
+    unit_price: Decimal
+    unit: Decimal
+    total_amount: Decimal
+    currency: str

api/core/model_runtime/entities/provider_entities.py

@@ -0,0 +1,159 @@
+from collections.abc import Sequence
+from enum import Enum
+from typing import Optional
+
+from pydantic import BaseModel, ConfigDict
+
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.model_entities import ModelType, ProviderModel
+
+
+class ConfigurateMethod(Enum):
+    """
+    Enum class for configurate method of provider model.
+    """
+
+    PREDEFINED_MODEL = "predefined-model"
+    CUSTOMIZABLE_MODEL = "customizable-model"
+
+
+class FormType(Enum):
+    """
+    Enum class for form type.
+    """
+
+    TEXT_INPUT = "text-input"
+    SECRET_INPUT = "secret-input"
+    SELECT = "select"
+    RADIO = "radio"
+    SWITCH = "switch"
+
+
+class FormShowOnObject(BaseModel):
+    """
+    Model class for form show on.
+    """
+
+    variable: str
+    value: str
+
+
+class FormOption(BaseModel):
+    """
+    Model class for form option.
+    """
+
+    label: I18nObject
+    value: str
+    show_on: list[FormShowOnObject] = []
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        if not self.label:
+            self.label = I18nObject(en_US=self.value)
+
+
+class CredentialFormSchema(BaseModel):
+    """
+    Model class for credential form schema.
+    """
+
+    variable: str
+    label: I18nObject
+    type: FormType
+    required: bool = True
+    default: Optional[str] = None
+    options: Optional[list[FormOption]] = None
+    placeholder: Optional[I18nObject] = None
+    max_length: int = 0
+    show_on: list[FormShowOnObject] = []
+
+
+class ProviderCredentialSchema(BaseModel):
+    """
+    Model class for provider credential schema.
+    """
+
+    credential_form_schemas: list[CredentialFormSchema]
+
+
+class FieldModelSchema(BaseModel):
+    label: I18nObject
+    placeholder: Optional[I18nObject] = None
+
+
+class ModelCredentialSchema(BaseModel):
+    """
+    Model class for model credential schema.
+    """
+
+    model: FieldModelSchema
+    credential_form_schemas: list[CredentialFormSchema]
+
+
+class SimpleProviderEntity(BaseModel):
+    """
+    Simple model class for provider.
+    """
+
+    provider: str
+    label: I18nObject
+    icon_small: Optional[I18nObject] = None
+    icon_large: Optional[I18nObject] = None
+    supported_model_types: Sequence[ModelType]
+    models: list[ProviderModel] = []
+
+
+class ProviderHelpEntity(BaseModel):
+    """
+    Model class for provider help.
+    """
+
+    title: I18nObject
+    url: I18nObject
+
+
+class ProviderEntity(BaseModel):
+    """
+    Model class for provider.
+    """
+
+    provider: str
+    label: I18nObject
+    description: Optional[I18nObject] = None
+    icon_small: Optional[I18nObject] = None
+    icon_large: Optional[I18nObject] = None
+    background: Optional[str] = None
+    help: Optional[ProviderHelpEntity] = None
+    supported_model_types: Sequence[ModelType]
+    configurate_methods: list[ConfigurateMethod]
+    models: list[ProviderModel] = []
+    provider_credential_schema: Optional[ProviderCredentialSchema] = None
+    model_credential_schema: Optional[ModelCredentialSchema] = None
+
+    # pydantic configs
+    model_config = ConfigDict(protected_namespaces=())
+
+    def to_simple_provider(self) -> SimpleProviderEntity:
+        """
+        Convert to simple provider.
+
+        :return: simple provider
+        """
+        return SimpleProviderEntity(
+            provider=self.provider,
+            label=self.label,
+            icon_small=self.icon_small,
+            icon_large=self.icon_large,
+            supported_model_types=self.supported_model_types,
+            models=self.models,
+        )
+
+
+class ProviderConfig(BaseModel):
+    """
+    Model class for provider config.
+    """
+
+    provider: str
+    credentials: dict

api/core/model_runtime/entities/rerank_entities.py

@@ -0,0 +1,20 @@
+from pydantic import BaseModel
+
+
+class RerankDocument(BaseModel):
+    """
+    Model class for rerank document.
+    """
+
+    index: int
+    text: str
+    score: float
+
+
+class RerankResult(BaseModel):
+    """
+    Model class for rerank result.
+    """
+
+    model: str
+    docs: list[RerankDocument]

api/core/model_runtime/entities/text_embedding_entities.py

@@ -0,0 +1,29 @@
+from decimal import Decimal
+
+from pydantic import BaseModel
+
+from core.model_runtime.entities.model_entities import ModelUsage
+
+
+class EmbeddingUsage(ModelUsage):
+    """
+    Model class for embedding usage.
+    """
+
+    tokens: int
+    total_tokens: int
+    unit_price: Decimal
+    price_unit: Decimal
+    total_price: Decimal
+    currency: str
+    latency: float
+
+
+class TextEmbeddingResult(BaseModel):
+    """
+    Model class for text embedding result.
+    """
+
+    model: str
+    embeddings: list[list[float]]
+    usage: EmbeddingUsage

api/core/model_runtime/errors/invoke.py

@@ -0,0 +1,43 @@
+from typing import Optional
+
+
+class InvokeError(ValueError):
+    """Base class for all LLM exceptions."""
+
+    description: Optional[str] = None
+
+    def __init__(self, description: Optional[str] = None) -> None:
+        self.description = description
+
+    def __str__(self):
+        return self.description or self.__class__.__name__
+
+
+class InvokeConnectionError(InvokeError):
+    """Raised when the Invoke returns connection error."""
+
+    description = "Connection Error"
+
+
+class InvokeServerUnavailableError(InvokeError):
+    """Raised when the Invoke returns server unavailable error."""
+
+    description = "Server Unavailable Error"
+
+
+class InvokeRateLimitError(InvokeError):
+    """Raised when the Invoke returns rate limit error."""
+
+    description = "Rate Limit Error"
+
+
+class InvokeAuthorizationError(InvokeError):
+    """Raised when the Invoke returns authorization error."""
+
+    description = "Incorrect model credentials provided, please check and try again. "
+
+
+class InvokeBadRequestError(InvokeError):
+    """Raised when the Invoke returns bad request."""
+
+    description = "Bad Request Error"

api/core/model_runtime/errors/validate.py

@@ -0,0 +1,6 @@
+class CredentialsValidateFailedError(ValueError):
+    """
+    Credentials validate failed error
+    """
+
+    pass