camel-ai 0.1.1__py3-none-any.whl

camel/configs.py

@@ -0,0 +1,159 @@
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+# Licensed under the Apache License, Version 2.0 (the “License”);
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an “AS IS” BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+from abc import ABC
+from dataclasses import asdict, dataclass, field
+from typing import Any, Dict, List, Optional, Sequence, Union
+
+from camel.functions import OpenAIFunction
+
+
+@dataclass(frozen=True)
+class BaseConfig(ABC):
+    pass
+
+
+@dataclass(frozen=True)
+class ChatGPTConfig(BaseConfig):
+    r"""Defines the parameters for generating chat completions using the
+    OpenAI API.
+
+    Args:
+        temperature (float, optional): Sampling temperature to use, between
+            :obj:`0` and :obj:`2`. Higher values make the output more random,
+            while lower values make it more focused and deterministic.
+            (default: :obj:`0.2`)
+        top_p (float, optional): An alternative to sampling with temperature,
+            called nucleus sampling, where the model considers the results of
+            the tokens with top_p probability mass. So :obj:`0.1` means only
+            the tokens comprising the top 10% probability mass are considered.
+            (default: :obj:`1.0`)
+        n (int, optional): How many chat completion choices to generate for
+            each input message. (default: :obj:`1`)
+        stream (bool, optional): If True, partial message deltas will be sent
+            as data-only server-sent events as they become available.
+            (default: :obj:`False`)
+        stop (str or list, optional): Up to :obj:`4` sequences where the API
+            will stop generating further tokens. (default: :obj:`None`)
+        max_tokens (int, optional): The maximum number of tokens to generate
+            in the chat completion. The total length of input tokens and
+            generated tokens is limited by the model's context length.
+            (default: :obj:`None`)
+        presence_penalty (float, optional): Number between :obj:`-2.0` and
+            :obj:`2.0`. Positive values penalize new tokens based on whether
+            they appear in the text so far, increasing the model's likelihood
+            to talk about new topics. See more information about frequency and
+            presence penalties. (default: :obj:`0.0`)
+        frequency_penalty (float, optional): Number between :obj:`-2.0` and
+            :obj:`2.0`. Positive values penalize new tokens based on their
+            existing frequency in the text so far, decreasing the model's
+            likelihood to repeat the same line verbatim. See more information
+            about frequency and presence penalties. (default: :obj:`0.0`)
+        logit_bias (dict, optional): Modify the likelihood of specified tokens
+            appearing in the completion. Accepts a json object that maps tokens
+            (specified by their token ID in the tokenizer) to an associated
+            bias value from :obj:`-100` to :obj:`100`. Mathematically, the bias
+            is added to the logits generated by the model prior to sampling.
+            The exact effect will vary per model, but values between:obj:` -1`
+            and :obj:`1` should decrease or increase likelihood of selection;
+            values like :obj:`-100` or :obj:`100` should result in a ban or
+            exclusive selection of the relevant token. (default: :obj:`{}`)
+        user (str, optional): A unique identifier representing your end-user,
+            which can help OpenAI to monitor and detect abuse.
+            (default: :obj:`""`)
+    """
+    temperature: float = 0.2  # openai default: 1.0
+    top_p: float = 1.0
+    n: int = 1
+    stream: bool = False
+    stop: Optional[Union[str, Sequence[str]]] = None
+    max_tokens: Optional[int] = None
+    presence_penalty: float = 0.0
+    frequency_penalty: float = 0.0
+    logit_bias: Dict = field(default_factory=dict)
+    user: str = ""
+
+
+@dataclass(frozen=True)
+class FunctionCallingConfig(ChatGPTConfig):
+    r"""Defines the parameters for generating chat completions using the
+    OpenAI API with functions included.
+
+    Args:
+        functions (List[Dict[str, Any]]): A list of functions the model may
+            generate JSON inputs for.
+        function_call (Union[Dict[str, str], str], optional): Controls how the
+            model responds to function calls. :obj:`"none"` means the model
+            does not call a function, and responds to the end-user.
+            :obj:`"auto"` means the model can pick between an end-user or
+            calling a function. Specifying a particular function via
+            :obj:`{"name": "my_function"}` forces the model to call that
+            function. (default: :obj:`"auto"`)
+    """
+    functions: List[Dict[str, Any]] = field(default_factory=list)
+    function_call: Union[Dict[str, str], str] = "auto"
+
+    @classmethod
+    def from_openai_function_list(
+        cls,
+        function_list: List[OpenAIFunction],
+        function_call: Union[Dict[str, str], str] = "auto",
+        kwargs: Optional[Dict[str, Any]] = None,
+    ):
+        r"""Class method for creating an instance given the function-related
+        arguments.
+
+        Args:
+            function_list (List[OpenAIFunction]): The list of function objects
+                to be loaded into this configuration and passed to the model.
+            function_call (Union[Dict[str, str], str], optional): Controls how
+                the model responds to function calls, as specified in the
+                creator's documentation.
+            kwargs (Optional[Dict[str, Any]]): The extra modifications to be
+                made on the original settings defined in :obj:`ChatGPTConfig`.
+
+        Return:
+            FunctionCallingConfig: A new instance which loads the given
+                function list into a list of dictionaries and the input
+                :obj:`function_call` argument.
+        """
+        return cls(
+            functions=[func.as_dict() for func in function_list],
+            function_call=function_call,
+            **(kwargs or {}),
+        )
+
+
+@dataclass(frozen=True)
+class OpenSourceConfig(BaseConfig):
+    r"""Defines parameters for setting up open-source models and includes
+    parameters to be passed to chat completion function of OpenAI API.
+
+    Args:
+        model_path (str): The path to a local folder containing the model
+            files or the model card in HuggingFace hub.
+        server_url (str): The URL to the server running the model inference
+            which will be used as the API base of OpenAI API.
+        api_params (ChatGPTConfig): An instance of :obj:ChatGPTConfig to
+            contain the arguments to be passed to OpenAI API.
+    """
+    model_path: str
+    server_url: str
+    api_params: ChatGPTConfig = ChatGPTConfig()
+
+
+OPENAI_API_PARAMS = {param for param in asdict(ChatGPTConfig()).keys()}
+OPENAI_API_PARAMS_WITH_FUNCTIONS = {
+    param
+    for param in asdict(FunctionCallingConfig()).keys()
+}

camel/embeddings/__init__.py

@@ -0,0 +1,20 @@
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+# Licensed under the Apache License, Version 2.0 (the “License”);
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an “AS IS” BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+from .base import BaseEmbedding
+from .openai_embedding import OpenAIEmbedding
+
+__all__ = [
+    "BaseEmbedding",
+    "OpenAIEmbedding",
+]

camel/embeddings/base.py

@@ -0,0 +1,65 @@
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+# Licensed under the Apache License, Version 2.0 (the “License”);
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an “AS IS” BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+from abc import ABC, abstractmethod
+from typing import Any, Generic, List, TypeVar
+
+T = TypeVar('T')
+
+
+class BaseEmbedding(ABC, Generic[T]):
+    r"""Abstract base class for text embedding functionalities."""
+
+    @abstractmethod
+    def embed_list(
+        self,
+        objs: List[T],
+        **kwargs: Any,
+    ) -> List[List[float]]:
+        r"""Generates embeddings for the given texts.
+
+        Args:
+            objs (List[T]): The objects for which to generate the embeddings.
+            **kwargs (Any): Extra kwargs passed to the embedding API.
+
+        Returns:
+            List[List[float]]: A list that represents the generated embedding
+                as a list of floating-point numbers.
+        """
+        pass
+
+    def embed(
+        self,
+        obj: T,
+        **kwargs: Any,
+    ) -> List[float]:
+        r"""Generates an embedding for the given text.
+
+        Args:
+            obj (T): The object for which to generate the embedding.
+            **kwargs (Any): Extra kwargs passed to the embedding API.
+
+        Returns:
+            List[float]: A list of floating-point numbers representing the
+                generated embedding.
+        """
+        return self.embed_list([obj], **kwargs)[0]
+
+    @abstractmethod
+    def get_output_dim(self) -> int:
+        r"""Returns the output dimension of the embeddings.
+
+        Returns:
+            int: The dimensionality of the embedding for the current model.
+        """
+        pass

camel/embeddings/openai_embedding.py

@@ -0,0 +1,74 @@
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+# Licensed under the Apache License, Version 2.0 (the “License”);
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an “AS IS” BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+from typing import Any, List
+
+from openai import OpenAI
+
+from camel.embeddings import BaseEmbedding
+from camel.types import EmbeddingModelType
+from camel.utils import openai_api_key_required
+
+
+class OpenAIEmbedding(BaseEmbedding[str]):
+    r"""Provides text embedding functionalities using OpenAI's models.
+
+    Args:
+        model (OpenAiEmbeddingModel, optional): The model type to be used for
+            generating embeddings. (default: :obj:`ModelType.ADA_2`)
+
+    Raises:
+        RuntimeError: If an unsupported model type is specified.
+    """
+
+    def __init__(
+        self,
+        model_type: EmbeddingModelType = EmbeddingModelType.ADA_2,
+    ) -> None:
+        if not model_type.is_openai:
+            raise ValueError("Invalid OpenAI embedding model type.")
+        self.model_type = model_type
+        self.output_dim = model_type.output_dim
+        self.client = OpenAI()
+
+    @openai_api_key_required
+    def embed_list(
+        self,
+        objs: List[str],
+        **kwargs: Any,
+    ) -> List[List[float]]:
+        r"""Generates embeddings for the given texts.
+
+        Args:
+            objs (List[str]): The texts for which to generate the embeddings.
+            **kwargs (Any): Extra kwargs passed to the embedding API.
+
+        Returns:
+            List[List[float]]: A list that represents the generated embedding
+                as a list of floating-point numbers.
+        """
+        # TODO: count tokens
+        response = self.client.embeddings.create(
+            input=objs,
+            model=self.model_type.value,
+            **kwargs,
+        )
+        return [data.embedding for data in response.data]
+
+    def get_output_dim(self) -> int:
+        r"""Returns the output dimension of the embeddings.
+
+        Returns:
+            int: The dimensionality of the embedding for the current model.
+        """
+        return self.output_dim

camel/functions/__init__.py

@@ -0,0 +1,27 @@
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+# Licensed under the Apache License, Version 2.0 (the “License”);
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an “AS IS” BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+
+from .math_functions import MATH_FUNCS
+from .openai_function import OpenAIFunction
+from .search_functions import SEARCH_FUNCS
+from .weather_functions import WEATHER_FUNCS
+from .unstructured_io_fuctions import UnstructuredModules
+
+__all__ = [
+    'OpenAIFunction',
+    'MATH_FUNCS',
+    'SEARCH_FUNCS',
+    'WEATHER_FUNCS',
+    'UnstructuredModules',
+]

camel/functions/base_io_functions.py

@@ -0,0 +1,261 @@
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+# Licensed under the Apache License, Version 2.0 (the “License”);
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an “AS IS” BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+import json
+import re
+from abc import ABC, abstractmethod
+from copy import deepcopy
+from hashlib import md5
+from io import BytesIO
+from typing import Any, Dict, List, Optional
+
+
+class File(ABC):
+    r"""Represents an uploaded file comprised of Documents"""
+
+    def __init__(
+        self,
+        name: str,
+        id: str,
+        metadata: Optional[Dict[str, Any]] = None,
+        docs: Optional[List[Dict[str, Any]]] = None,
+    ):
+        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.metadata = metadata or {}
+        self.docs = docs or []
+
+    @classmethod
+    @abstractmethod
+    def from_bytes(cls, file: BytesIO) -> "File":
+        r"""Creates a File object from a BytesIO object.
+
+        Args:
+            file (BytesIO):
+            A BytesIO object representing the contents of the file.
+
+        Returns:
+            File: A File object.
+        """
+
+    def __repr__(self) -> str:
+        return (f"File(name={self.name}, id={self.id}, "
+                f"metadata={self.metadata}, docs={self.docs})")
+
+    def __str__(self) -> str:
+        return (
+            f"File(name={self.name}, id={self.id}, metadata={self.metadata})")
+
+    def copy(self) -> "File":
+        r"""Create a deep copy of this File"""
+
+        return self.__class__(
+            name=self.name,
+            id=self.id,
+            metadata=deepcopy(self.metadata),
+            docs=deepcopy(self.docs),
+        )
+
+
+def strip_consecutive_newlines(text: str) -> str:
+    r"""Strips consecutive newlines from a string.
+
+    Args:
+        text (str): The string to strip.
+
+    Returns:
+        str: The string with consecutive newlines stripped.
+    """
+    return re.sub(r"\s*\n\s*", "\n", text)
+
+
+class DocxFile(File):
+
+    @classmethod
+    def from_bytes(cls, file: BytesIO) -> "DocxFile":
+        r"""Creates a DocxFile object from a BytesIO object.
+
+        Args:
+            file (BytesIO):
+            A BytesIO object representing the contents of the docx file.
+
+        Returns:
+            DocxFile: A DocxFile object.
+        """
+        # Use docx2txt to extract text from docx files
+        try:
+            import docx2txt
+        except ImportError:
+            raise ImportError("Please install `docx2txt` first. "
+                              "You can install it by running "
+                              "`pip install docx2txt`.")
+        text = docx2txt.process(file)
+        text = strip_consecutive_newlines(text)
+        # Create a dictionary with the extracted text
+        doc = {"page_content": text.strip()}
+        # Calculate a unique identifier for the 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])
+
+
+class PdfFile(File):
+
+    @classmethod
+    def from_bytes(cls, file: BytesIO) -> "PdfFile":
+        r"""Creates a PdfFile object from a BytesIO object.
+
+        Args:
+            file (BytesIO):
+            A BytesIO object representing the contents of the pdf file.
+
+        Returns:
+            PdfFile: A PdfFile object.
+        """
+        # Use fitz to extract text from pdf files
+        try:
+            import fitz
+        except ImportError:
+            raise ImportError("Please install `PyMuPDF` first. "
+                              "You can install it by running "
+                              "`pip install PyMuPDF`.")
+        pdf = fitz.open(stream=file.read(), filetype="pdf")
+        docs = []
+        for i, page in enumerate(pdf):
+            text = page.get_text(sort=True)
+            text = strip_consecutive_newlines(text)
+            # Create a dictionary with the extracted text
+            doc = {"page_content": text.strip(), "page": i + 1}
+            docs.append(doc)
+        # Calculate a unique identifier for the 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)
+
+
+class TxtFile(File):
+
+    @classmethod
+    def from_bytes(cls, file: BytesIO) -> "TxtFile":
+        r"""Creates a TxtFile object from a BytesIO object.
+
+        Args:
+            file (BytesIO):
+            A BytesIO object representing the contents of the txt file.
+
+        Returns:
+            TxtFile: A TxtFile object.
+        """
+        # Read the text from the file
+        text = file.read().decode("utf-8")
+        text = strip_consecutive_newlines(text)
+        # Create a dictionary with the extracted text
+        doc = {"page_content": text.strip()}
+        # Calculate a unique identifier for the 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])
+
+
+class JsonFile(File):
+
+    @classmethod
+    def from_bytes(cls, file: BytesIO) -> "JsonFile":
+        r"""Creates a JsonFile object from a BytesIO object.
+
+        Args:
+            file (BytesIO):
+            A BytesIO object representing the contents of the json file.
+
+        Returns:
+            JsonFile: A JsonFile object.
+        """
+        # Parse the JSON data from the file
+        data = json.load(file)
+        # Create a dictionary with the parsed data
+        doc = {"page_content": json.dumps(data)}
+        # Calculate a unique identifier for the 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])
+
+
+class HtmlFile(File):
+
+    @classmethod
+    def from_bytes(cls, file: BytesIO) -> "HtmlFile":
+        r"""Creates a HtmlFile object from a BytesIO object.
+
+        Args:
+            file (BytesIO):
+            A BytesIO object representing the contents of the html file.
+
+        Returns:
+            HtmlFile: A HtmlFile object.
+        """
+        # Parse the HTML data from the file
+        try:
+            from bs4 import BeautifulSoup
+        except ImportError:
+            raise ImportError("Please install `beautifulsoup4` first. "
+                              "You can install it by running "
+                              "`pip install beautifulsoup4`.")
+        soup = BeautifulSoup(file, "html.parser")
+        text = soup.get_text()
+        text = strip_consecutive_newlines(text)
+        # Create a dictionary with the parsed data
+        doc = {"page_content": text.strip()}
+        # Calculate a unique identifier for the 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")

camel/functions/math_functions.py

@@ -0,0 +1,61 @@
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+# Licensed under the Apache License, Version 2.0 (the “License”);
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an “AS IS” BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
+
+from typing import List
+
+from .openai_function import OpenAIFunction
+
+
+def add(a: int, b: int) -> int:
+    r"""Adds two numbers.
+
+    Args:
+        a (integer): The first number to be added.
+        b (integer): The second number to be added.
+
+    Returns:
+        integer: The sum of the two numbers.
+    """
+    return a + b
+
+
+def sub(a: int, b: int) -> int:
+    r"""Do subtraction between two numbers.
+
+    Args:
+        a (integer): The minuend in subtraction.
+        b (integer): The subtrahend in subtraction.
+
+    Returns:
+        integer: The result of subtracting :obj:`b` from :obj:`a`.
+    """
+    return a - b
+
+
+def mul(a: int, b: int) -> int:
+    r"""Multiplies two integers.
+
+    Args:
+        a (integer): The multiplier in the multiplication.
+        b (integer): The multiplicand in the multiplication.
+
+    Returns:
+        integer: The product of the two numbers.
+    """
+    return a * b
+
+
+MATH_FUNCS: List[OpenAIFunction] = [
+    OpenAIFunction(func) for func in [add, sub, mul]
+]