camel-ai 0.1.6.2__py3-none-any.whl → 0.1.6.5__py3-none-any.whl

camel/__init__.py

@@ -12,7 +12,7 @@
 # limitations under the License.
 # =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
 
-__version__ = '0.1.6.2'
+__version__ = '0.1.6.5'
 
 __all__ = [
     '__version__',

camel/configs/gemini_config.py

@@ -81,7 +81,6 @@ class GeminiConfig(BaseConfig):
     response_mime_type: Optional[str] = None
     response_schema: Optional[Any] = None
     safety_settings: Optional[Any] = None
-    tools: Optional[Any] = None
     tool_config: Optional[Any] = None
     request_options: Optional[Any] = None
 

camel/configs/groq_config.py

@@ -99,7 +99,7 @@ class GroqConfig(BaseConfig):
     response_format: Union[dict, NotGiven] = NOT_GIVEN
     frequency_penalty: float = 0.0
     user: str = ""
-    tool_choice: Optional[Union[dict[str, str], str]] = "none"
+    tool_choice: Optional[Union[dict[str, str], str]] = "auto"
 
 
 GROQ_API_PARAMS = {param for param in GroqConfig.model_fields.keys()}

camel/configs/mistral_config.py

@@ -26,23 +26,26 @@ class MistralConfig(BaseConfig):
 
     reference: https://github.com/mistralai/client-python/blob/9d238f88c41689821d7b08570f13b43426f97fd6/src/mistralai/client.py#L195
 
+    #TODO: Support stream mode
+
     Args:
         temperature (Optional[float], optional): temperature the temperature
             to use for sampling, e.g. 0.5.
-        max_tokens (Optional[int], optional): the maximum number of tokens to
-            generate, e.g. 100. Defaults to None.
         top_p (Optional[float], optional): the cumulative probability of
             tokens to generate, e.g. 0.9. Defaults to None.
+        max_tokens (Optional[int], optional): the maximum number of tokens to
+            generate, e.g. 100. Defaults to None.
+        min_tokens (Optional[int], optional): the minimum number of tokens to
+            generate, e.g. 100. Defaults to None.
+        stop (Optional[Union[str,list[str]]]): Stop generation if this token
+            is detected. Or if one of these tokens is detected when providing
+            a string list.
         random_seed (Optional[int], optional): the random seed to use for
             sampling, e.g. 42. Defaults to None.
-        safe_mode (bool, optional): deprecated, use safe_prompt instead.
-            Defaults to False.
         safe_prompt (bool, optional): whether to use safe prompt, e.g. true.
             Defaults to False.
         response_format (Union[Dict[str, str], ResponseFormat): format of the
             response.
-        tools (Optional[list[OpenAIFunction]], optional): a list of tools to
-            use.
         tool_choice (str, optional): Controls which (if
             any) tool is called by the model. :obj:`"none"` means the model
             will not call any tool and instead generates a message.
@@ -53,10 +56,11 @@ class MistralConfig(BaseConfig):
     """
 
     temperature: Optional[float] = None
-    max_tokens: Optional[int] = None
     top_p: Optional[float] = None
+    max_tokens: Optional[int] = None
+    min_tokens: Optional[int] = None
+    stop: Optional[Union[str, list[str]]] = None
     random_seed: Optional[int] = None
-    safe_mode: bool = False
     safe_prompt: bool = False
     response_format: Optional[Union[Dict[str, str], Any]] = None
     tool_choice: Optional[str] = "auto"
@@ -65,12 +69,12 @@ class MistralConfig(BaseConfig):
     @classmethod
     def fields_type_checking(cls, response_format):
         if response_format and not isinstance(response_format, dict):
-            from mistralai.models.chat_completion import ResponseFormat
+            from mistralai.models import ResponseFormat
 
             if not isinstance(response_format, ResponseFormat):
                 raise ValueError(
                     f"The tool {response_format} should be an instance "
-                    "of `mistralai.models.chat_completion.ResponseFormat`."
+                    "of `mistralai.models.ResponseFormat`."
                 )
         return response_format
 

camel/embeddings/mistral_embedding.py

@@ -43,7 +43,7 @@ class MistralEmbedding(BaseEmbedding[str]):
         api_key: str | None = None,
         dimensions: int | None = None,
     ) -> None:
-        from mistralai.client import MistralClient
+        from mistralai import Mistral
 
         if not model_type.is_mistral:
             raise ValueError("Invalid Mistral embedding model type.")
@@ -54,7 +54,7 @@ class MistralEmbedding(BaseEmbedding[str]):
             assert isinstance(dimensions, int)
             self.output_dim = dimensions
         self._api_key = api_key or os.environ.get("MISTRAL_API_KEY")
-        self._client = MistralClient(api_key=self._api_key)
+        self._client = Mistral(api_key=self._api_key)
 
     @api_keys_required("MISTRAL_API_KEY")
     def embed_list(
@@ -73,12 +73,12 @@ class MistralEmbedding(BaseEmbedding[str]):
                 as a list of floating-point numbers.
         """
         # TODO: count tokens
-        response = self._client.embeddings(
-            input=objs,
+        response = self._client.embeddings.create(
+            inputs=objs,
             model=self.model_type.value,
             **kwargs,
         )
-        return [data.embedding for data in response.data]
+        return [data.embedding for data in response.data]  # type: ignore[misc,union-attr]
 
     def get_output_dim(self) -> int:
         r"""Returns the output dimension of the embeddings.

camel/interpreters/docker_interpreter.py

@@ -130,7 +130,7 @@ class DockerInterpreter(BaseInterpreter):
         code_type = self._check_code_type(code_type)
         commands = shlex.split(
             self._CODE_EXECUTE_CMD_MAPPING[code_type].format(
-                file_name=str(file)
+                file_name=file.as_posix()
             )
         )
         if self._container is None:

camel/loaders/__init__.py

@@ -12,14 +12,13 @@
 # limitations under the License.
 # =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
 
-from .base_io import File, read_file
+from .base_io import File
 from .firecrawl_reader import Firecrawl
 from .jina_url_reader import JinaURLReader
 from .unstructured_io import UnstructuredIO
 
 __all__ = [
     'File',
-    'read_file',
     'UnstructuredIO',
     'JinaURLReader',
     'Firecrawl',

camel/loaders/base_io.py

@@ -23,52 +23,113 @@ from camel.utils import dependencies_required
 
 
 class File(ABC):
-    r"""Represents an uploaded file comprised of Documents"""
+    r"""Represents an uploaded file comprised of Documents.
+
+    Args:
+        name (str): The name of the file.
+        file_id (str): The unique identifier of the file.
+        metadata (Dict[str, Any], optional): Additional metadata
+            associated with the file. Defaults to None.
+        docs (List[Dict[str, Any]], optional): A list of documents
+            contained within the file. Defaults to None.
+        raw_bytes (bytes, optional): The raw bytes content of the file.
+            Defaults to b"".
+    """
 
     def __init__(
         self,
         name: str,
-        id: str,
+        file_id: str,
         metadata: Optional[Dict[str, Any]] = None,
         docs: Optional[List[Dict[str, Any]]] = None,
+        raw_bytes: bytes = b"",
     ):
-        r"""
-
-        Args:
-            name (str): The name of the file.
-            id (str): The unique identifier of the file.
-            metadata (Dict[str, Any], optional): Additional metadata
-                associated with the file. Defaults to None.
-            docs (List[Dict[str, Any]], optional): A list of documents
-                contained within the file. Defaults to None.
-        """
         self.name = name
-        self.id = id
+        self.file_id = file_id
         self.metadata = metadata or {}
         self.docs = docs or []
+        self.raw_bytes = raw_bytes
 
     @classmethod
     @abstractmethod
-    def from_bytes(cls, file: BytesIO) -> "File":
+    def from_bytes(cls, file: BytesIO, filename: str) -> "File":
         r"""Creates a File object from a BytesIO object.
 
         Args:
             file (BytesIO): A BytesIO object representing the contents of the
                 file.
+            filename (str): The name of the file.
+
+        Returns:
+            File: A File object.
+        """
+        pass
+
+    @classmethod
+    def from_raw_bytes(cls, raw_bytes: bytes, filename: str) -> "File":
+        r"""Creates a File object from raw bytes.
+
+        Args:
+            raw_bytes (bytes): The raw bytes content of the file.
+            filename (str): The name of the file.
 
         Returns:
             File: A File object.
         """
+        file = BytesIO(raw_bytes)
+        return cls.from_bytes(file, filename)
+
+    @staticmethod
+    def create_file(file: BytesIO, filename: str) -> "File":
+        r"""Reads an uploaded file and returns a File object.
+
+        Args:
+            file (BytesIO): A BytesIO object representing the contents of the
+                file.
+            filename (str): The name of the file.
+
+        Returns:
+            File: A File object.
+        """
+        ext_to_cls = {
+            "docx": DocxFile,
+            "pdf": PdfFile,
+            "txt": TxtFile,
+            "json": JsonFile,
+            "html": HtmlFile,
+        }
+
+        ext = filename.split(".")[-1].lower()
+        if ext not in ext_to_cls:
+            raise NotImplementedError(f"File type {ext} not supported")
+
+        out_file = ext_to_cls[ext].from_bytes(file, filename)
+        return out_file
+
+    @staticmethod
+    def create_file_from_raw_bytes(raw_bytes: bytes, filename: str) -> "File":
+        r"""Reads raw bytes and returns a File object.
+
+        Args:
+            raw_bytes (bytes): The raw bytes content of the file.
+            filename (str): The name of the file.
+
+        Returns:
+            File: A File object.
+        """
+        file = BytesIO(raw_bytes)
+        return File.create_file(file, filename)
 
     def __repr__(self) -> str:
         return (
-            f"File(name={self.name}, id={self.id}, "
+            f"File(name={self.name}, id={self.file_id}, "
             f"metadata={self.metadata}, docs={self.docs})"
         )
 
     def __str__(self) -> str:
         return (
-            f"File(name={self.name}, id={self.id}, metadata={self.metadata})"
+            f"File(name={self.name}, id={self.file_id}, metadata="
+            f"{self.metadata})"
         )
 
     def copy(self) -> "File":
@@ -76,9 +137,10 @@ class File(ABC):
 
         return self.__class__(
             name=self.name,
-            id=self.id,
+            file_id=self.file_id,
             metadata=deepcopy(self.metadata),
             docs=deepcopy(self.docs),
+            raw_bytes=self.raw_bytes,
         )
 
 
@@ -97,12 +159,13 @@ def strip_consecutive_newlines(text: str) -> str:
 class DocxFile(File):
     @classmethod
     @dependencies_required('docx2txt')
-    def from_bytes(cls, file: BytesIO) -> "DocxFile":
+    def from_bytes(cls, file: BytesIO, filename: str) -> "DocxFile":
         r"""Creates a DocxFile object from a BytesIO object.
 
         Args:
             file (BytesIO): A BytesIO object representing the contents of the
                 docx file.
+            filename (str): The name of the file.
 
         Returns:
             DocxFile: A DocxFile object.
@@ -117,17 +180,23 @@ class DocxFile(File):
         file_id = md5(file.getvalue()).hexdigest()
         # Reset the file pointer to the beginning
         file.seek(0)
-        return cls(name=file.name, id=file_id, docs=[doc])
+        return cls(
+            name=filename,
+            file_id=file_id,
+            docs=[doc],
+            raw_bytes=file.getvalue(),
+        )
 
 
 class PdfFile(File):
     @classmethod
-    def from_bytes(cls, file: BytesIO) -> "PdfFile":
+    def from_bytes(cls, file: BytesIO, filename: str) -> "PdfFile":
         r"""Creates a PdfFile object from a BytesIO object.
 
         Args:
             file (BytesIO): A BytesIO object representing the contents of the
                 pdf file.
+            filename (str): The name of the file.
 
         Returns:
             PdfFile: A PdfFile object.
@@ -153,17 +222,23 @@ class PdfFile(File):
         file_id = md5(file.getvalue()).hexdigest()
         # Reset the file pointer to the beginning
         file.seek(0)
-        return cls(name=file.name, id=file_id, docs=docs)
+        return cls(
+            name=filename,
+            file_id=file_id,
+            docs=docs,
+            raw_bytes=file.getvalue(),
+        )
 
 
 class TxtFile(File):
     @classmethod
-    def from_bytes(cls, file: BytesIO) -> "TxtFile":
+    def from_bytes(cls, file: BytesIO, filename: str) -> "TxtFile":
         r"""Creates a TxtFile object from a BytesIO object.
 
         Args:
             file (BytesIO): A BytesIO object representing the contents of the
                 txt file.
+            filename (str): The name of the file.
 
         Returns:
             TxtFile: A TxtFile object.
@@ -177,17 +252,23 @@ class TxtFile(File):
         file_id = md5(file.getvalue()).hexdigest()
         # Reset the file pointer to the beginning
         file.seek(0)
-        return cls(name=file.name, id=file_id, docs=[doc])
+        return cls(
+            name=filename,
+            file_id=file_id,
+            docs=[doc],
+            raw_bytes=file.getvalue(),
+        )
 
 
 class JsonFile(File):
     @classmethod
-    def from_bytes(cls, file: BytesIO) -> "JsonFile":
+    def from_bytes(cls, file: BytesIO, filename: str) -> "JsonFile":
         r"""Creates a JsonFile object from a BytesIO object.
 
         Args:
             file (BytesIO): A BytesIO object representing the contents of the
                 json file.
+            filename (str): The name of the file.
 
         Returns:
             JsonFile: A JsonFile object.
@@ -200,17 +281,23 @@ class JsonFile(File):
         file_id = md5(file.getvalue()).hexdigest()
         # Reset the file pointer to the beginning
         file.seek(0)
-        return cls(name=file.name, id=file_id, docs=[doc])
+        return cls(
+            name=filename,
+            file_id=file_id,
+            docs=[doc],
+            raw_bytes=file.getvalue(),
+        )
 
 
 class HtmlFile(File):
     @classmethod
-    def from_bytes(cls, file: BytesIO) -> "HtmlFile":
+    def from_bytes(cls, file: BytesIO, filename: str) -> "HtmlFile":
         r"""Creates a HtmlFile object from a BytesIO object.
 
         Args:
             file (BytesIO): A BytesIO object representing the contents of the
                 html file.
+            filename (str): The name of the file.
 
         Returns:
             HtmlFile: A HtmlFile object.
@@ -233,30 +320,9 @@ class HtmlFile(File):
         file_id = md5(file.getvalue()).hexdigest()
         # Reset the file pointer to the beginning
         file.seek(0)
-        return cls(name=file.name, id=file_id, docs=[doc])
-
-
-def read_file(file: BytesIO) -> File:
-    r"""Reads an uploaded file and returns a File object.
-
-    Args:
-        file (BytesIO): A BytesIO object representing the contents of the file.
-
-    Returns:
-        File: A File object.
-    """
-    # Determine the file type based on the file extension
-    if file.name.lower().endswith(".docx"):
-        return DocxFile.from_bytes(file)
-    elif file.name.lower().endswith(".pdf"):
-        return PdfFile.from_bytes(file)
-    elif file.name.lower().endswith(".txt"):
-        return TxtFile.from_bytes(file)
-    elif file.name.lower().endswith(".json"):
-        return JsonFile.from_bytes(file)
-    elif file.name.lower().endswith(".html"):
-        return HtmlFile.from_bytes(file)
-    else:
-        raise NotImplementedError(
-            f"File type {file.name.split('.')[-1]} not supported"
+        return cls(
+            name=filename,
+            file_id=file_id,
+            docs=[doc],
+            raw_bytes=file.getvalue(),
         )

camel/loaders/jina_url_reader.py

@@ -14,6 +14,7 @@
 
 import os
 from typing import Any, Optional
+from warnings import warn
 
 from camel.types.enums import JinaReturnFormat
 
@@ -54,11 +55,10 @@ class JinaURLReader:
         **kwargs: Any,
     ) -> None:
         api_key = api_key or os.getenv('JINA_API_KEY')
-        if api_key is None:
-            print(
-                "[JinaURLReader] JINA_API_KEY not set. This will result in a "
-                "low rate limit of Jina URL Reader. Get API key here: "
-                "https://jina.ai/reader."
+        if not api_key:
+            warn(
+                "JINA_API_KEY not set. This will result in a low rate limit "
+                "of Jina URL Reader. Get API key here: https://jina.ai/reader."
             )
 
         # if the following field not provided, it will be None
@@ -94,6 +94,6 @@ class JinaURLReader:
             resp = requests.get(full_url, headers=self._headers)
             resp.raise_for_status()
         except Exception as e:
-            raise Exception(f"Failed to read content from {url}: {e}") from e
+            raise ValueError(f"Failed to read content from {url}: {e}") from e
 
         return resp.text