camel.schemas package

Submodules

camel.schemas.base module

class camel.schemas.base.BaseConverter

Bases: ABC

A base class for schema outputs that includes functionality for managing the response format.

Parameters:

output_schema (Optional[Type[BaseModel]], optional) – The expected format of the response. (default: None)

abstract convert(content: str, *args: Any, **kwargs: Dict[str, Any]) → Any

Structures the input text into the expected response format.

Parameters:

• text (str) – The input text to be structured.

• output_schema (Optional[Type[BaseModel]], optional) – The expected format of the response. Defaults to None.

• prompt (Optional[str], optional) – The prompt to be used.

Returns:

The converted response.

Return type:

Any

camel.schemas.openai_converter module

class camel.schemas.openai_converter.OpenAISchemaConverter(model_type: ~<unknown>.ModelType = ModelType.GPT_4O_MINI, model_config_dict: ~typing.Dict[str, ~typing.Any] | None = None, api_key: str | None = None)

Bases: BaseConverter

OpenAISchemaConverter is a class that converts a string or a function into a BaseModel schema.

Parameters:

• model_type (ModelType, optional) – The model type to be used. (default: ModelType.GPT_4O_MINI)

• model_config_dict (Optional[Dict[str, Any]], optional) – A dictionary that will be fed into:obj:openai.ChatCompletion.create(). If None, ChatGPTConfig().as_dict() will be used. (default: None)

• api_key (Optional[str], optional) – The API key for authenticating with the OpenAI service. (default: None)

• output_schema (Optional[Type[BaseModel]], optional) – The expected format of the response. (default: None)

• prompt (Optional[str], optional) – The prompt to be used. (default: None)

convert(content: str, output_schema: Type[BaseModel] | str | Callable, prompt: str | None = '\n    Extract key entities and attributes from the user \n    provided text, and convert them into a structured JSON format.\n') → BaseModel

Formats the input content into the expected BaseModel

Parameters:

• content (str) – The content to be formatted.

• output_schema (Union[Type[BaseModel], str, Callable]) – The expected format of the response.

Returns:

The formatted response.

Return type:

BaseModel

camel.schemas.outlines_converter module

class camel.schemas.outlines_converter.OutlinesConverter(model_type: str, platform: Literal['vllm', 'transformers', 'mamba', 'llamacpp', 'mlx'] = 'transformers', **kwargs: Any)

Bases: BaseConverter

OutlinesConverter is a class that converts a string or a function into a BaseModel schema.

Parameters:

• model_type (str, optional) – The model type to be used.

• platform (str, optional) – The platform to be used. 1. transformers 2. mamba 3. vllm 4. llamacpp 5. mlx (default: “transformers”)

• **kwargs – The keyword arguments to be used. See the outlines documentation for more details. See https://dottxt-ai.github.io/outlines/latest/reference/models/models/

convert(content: str, type: Literal['regex', 'json', 'type', 'choice', 'grammar'], **kwargs) → Any

Formats the input content into the expected BaseModel.

Parameters:

• type (Literal["regex", "json", "type", "choice", "grammar"]) –

  The type of conversion to perform. Options are:

  • ”regex”: Match the content against a regex pattern.

  • ”pydantic”: Convert the content into a pydantic model.

  • ”json”: Convert the content into a JSON based on a schema.

  • ”type”: Convert the content into a specified type.

  • ”choice”: Match the content against a list of valid choices.

  • ”grammar”: Convert the content using a specified grammar.

• content (str) – The content to be formatted.

• **kwargs – Additional keyword arguments specific to the conversion type.

• "regex" (- For) – regex_pattern (str): The regex pattern to use for matching.

• "pydantic" (- For) –

  output_schema (Type[BaseModel]): The schema to validate and

  format the pydantic model.

• "json" (- For) –

  output_schema (Union[str, Callable]): The schema to validate

  and format the JSON object.

• "type" (- For) – type_name (str): The target type name for the conversion.

• "choice" (- For) – choices (List[str]): A list of valid choices to match against.

• "grammar" (- For) –

  grammar (str): The grammar definition to use for content

  conversion.

convert_choice(content: str, choices: List[str]) → str

Convert the content to the specified choice.

Parameters:

• content (str) – The content to be converted.

• choices (List[str]) – The choices to be used.

Returns:

The converted content.

Return type:

str

convert_grammar(content: str, grammar: str) → str

Convert the content to the specified grammar.

Parameters:

• content (str) – The content to be converted.

• grammar (str) – The grammar to be used.

Returns:

The converted content.

Return type:

str

convert_json(content: str, output_schema: str | Callable) → dict

Convert the content to the specified JSON schema given by output_schema.

Parameters:

• content (str) – The content to be converted.

• output_schema (Union[str, Callable]) – The expected format of the response.

Returns:

The converted content in JSON format.

Return type:

dict

convert_pydantic(content: str, output_schema: Type[BaseModel]) → BaseModel

Convert the content to the specified Pydantic schema.

Parameters:

• content (str) – The content to be converted.

• output_schema (Type[BaseModel]) – The expected format of the response.

Returns:

The converted content in pydantic model format.

Return type:

BaseModel

convert_regex(content: str, regex_pattern: str) → str

Convert the content to the specified regex pattern.

Parameters:

• content (str) – The content to be converted.

• regex_pattern (str) – The regex pattern to be used.

Returns:

The converted content.

Return type:

str

convert_type(content: str, type_name: type) → str

Convert the content to the specified type.

The following types are currently available:

1. int

2. float

3. bool

4. datetime.date

5. datetime.time

6. datetime.datetime

7. custom types (https://dottxt-ai.github.io/outlines/latest/reference/generation/types/)

Parameters:

• content (str) – The content to be converted.

• type_name (type) – The type to be used.

Returns:

The converted content.

Return type:

str

Module contents

class camel.schemas.OpenAISchemaConverter(model_type: ~<unknown>.ModelType = ModelType.GPT_4O_MINI, model_config_dict: ~typing.Dict[str, ~typing.Any] | None = None, api_key: str | None = None)

Bases: BaseConverter

OpenAISchemaConverter is a class that converts a string or a function into a BaseModel schema.

Parameters:

• model_type (ModelType, optional) – The model type to be used. (default: ModelType.GPT_4O_MINI)

• model_config_dict (Optional[Dict[str, Any]], optional) – A dictionary that will be fed into:obj:openai.ChatCompletion.create(). If None, ChatGPTConfig().as_dict() will be used. (default: None)

• api_key (Optional[str], optional) – The API key for authenticating with the OpenAI service. (default: None)

• output_schema (Optional[Type[BaseModel]], optional) – The expected format of the response. (default: None)

• prompt (Optional[str], optional) – The prompt to be used. (default: None)

convert(content: str, output_schema: Type[BaseModel] | str | Callable, prompt: str | None = '\n    Extract key entities and attributes from the user \n    provided text, and convert them into a structured JSON format.\n') → BaseModel

Formats the input content into the expected BaseModel

Parameters:

• content (str) – The content to be formatted.

• output_schema (Union[Type[BaseModel], str, Callable]) – The expected format of the response.

Returns:

The formatted response.

Return type:

BaseModel

class camel.schemas.OutlinesConverter(model_type: str, platform: Literal['vllm', 'transformers', 'mamba', 'llamacpp', 'mlx'] = 'transformers', **kwargs: Any)

Bases: BaseConverter

OutlinesConverter is a class that converts a string or a function into a BaseModel schema.

Parameters:

• model_type (str, optional) – The model type to be used.

• platform (str, optional) – The platform to be used. 1. transformers 2. mamba 3. vllm 4. llamacpp 5. mlx (default: “transformers”)

• **kwargs – The keyword arguments to be used. See the outlines documentation for more details. See https://dottxt-ai.github.io/outlines/latest/reference/models/models/

convert(content: str, type: Literal['regex', 'json', 'type', 'choice', 'grammar'], **kwargs) → Any

Formats the input content into the expected BaseModel.

Parameters:

• type (Literal["regex", "json", "type", "choice", "grammar"]) –

  The type of conversion to perform. Options are:

  • ”regex”: Match the content against a regex pattern.

  • ”pydantic”: Convert the content into a pydantic model.

  • ”json”: Convert the content into a JSON based on a schema.

  • ”type”: Convert the content into a specified type.

  • ”choice”: Match the content against a list of valid choices.

  • ”grammar”: Convert the content using a specified grammar.

• content (str) – The content to be formatted.

• **kwargs – Additional keyword arguments specific to the conversion type.

• "regex" (- For) – regex_pattern (str): The regex pattern to use for matching.

• "pydantic" (- For) –

  output_schema (Type[BaseModel]): The schema to validate and

  format the pydantic model.

• "json" (- For) –

  output_schema (Union[str, Callable]): The schema to validate

  and format the JSON object.

• "type" (- For) – type_name (str): The target type name for the conversion.

• "choice" (- For) – choices (List[str]): A list of valid choices to match against.

• "grammar" (- For) –

  grammar (str): The grammar definition to use for content

  conversion.

convert_choice(content: str, choices: List[str]) → str

Convert the content to the specified choice.

Parameters:

• content (str) – The content to be converted.

• choices (List[str]) – The choices to be used.

Returns:

The converted content.

Return type:

str

convert_grammar(content: str, grammar: str) → str

Convert the content to the specified grammar.

Parameters:

• content (str) – The content to be converted.

• grammar (str) – The grammar to be used.

Returns:

The converted content.

Return type:

str

convert_json(content: str, output_schema: str | Callable) → dict

Convert the content to the specified JSON schema given by output_schema.

Parameters:

• content (str) – The content to be converted.

• output_schema (Union[str, Callable]) – The expected format of the response.

Returns:

The converted content in JSON format.

Return type:

dict

convert_pydantic(content: str, output_schema: Type[BaseModel]) → BaseModel

Convert the content to the specified Pydantic schema.

Parameters:

• content (str) – The content to be converted.

• output_schema (Type[BaseModel]) – The expected format of the response.

Returns:

The converted content in pydantic model format.

Return type:

BaseModel

convert_regex(content: str, regex_pattern: str) → str

Convert the content to the specified regex pattern.

Parameters:

• content (str) – The content to be converted.

• regex_pattern (str) – The regex pattern to be used.

Returns:

The converted content.

Return type:

str

convert_type(content: str, type_name: type) → str

Convert the content to the specified type.

The following types are currently available:

1. int

2. float

3. bool

4. datetime.date

5. datetime.time

6. datetime.datetime

7. custom types (https://dottxt-ai.github.io/outlines/latest/reference/generation/types/)

Parameters:

• content (str) – The content to be converted.

• type_name (type) – The type to be used.

Returns:

The converted content.

Return type:

str