camel-ai 0.1.5.2__tar.gz → 0.1.5.4__tar.gz

{camel_ai-0.1.5.2 → camel_ai-0.1.5.4}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.1
 Name: camel-ai
-Version: 0.1.5.2
+Version: 0.1.5.4
 Summary: Communicative Agents for AI Society Study
 Home-page: https://www.camel-ai.org/
 License: Apache-2.0
 Keywords: communicative-ai,ai-societies,artificial-intelligence,deep-learning,multi-agent-systems,cooperative-ai,natural-language-processing,large-language-models
 Author: CAMEL-AI.org
-Requires-Python: >=3.8.1,<3.12
+Requires-Python: >=3.9.0,<3.12
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
@@ -23,7 +23,7 @@ Provides-Extra: tools
 Provides-Extra: vector-databases
 Requires-Dist: PyMuPDF (>=1.22.5,<2.0.0) ; extra == "tools" or extra == "all"
 Requires-Dist: accelerate (>=0,<1) ; extra == "huggingface-agent" or extra == "all"
-Requires-Dist: anthropic (>=0.28.0,<0.29.0)
+Requires-Dist: anthropic (>=0.29.0,<0.30.0)
 Requires-Dist: beautifulsoup4 (>=4,<5) ; extra == "tools" or extra == "all"
 Requires-Dist: cohere (>=4.56,<5.0) ; extra == "retrievers" or extra == "all"
 Requires-Dist: colorama (>=0,<1)
@@ -35,7 +35,7 @@ Requires-Dist: docstring-parser (>=0.15,<0.16)
 Requires-Dist: docx2txt (>=0.8,<0.9) ; extra == "tools" or extra == "all"
 Requires-Dist: duckduckgo-search (>=6.1.0,<7.0.0) ; extra == "tools" or extra == "all"
 Requires-Dist: googlemaps (>=4.10.0,<5.0.0) ; extra == "tools" or extra == "all"
-Requires-Dist: imageio (>=2.34.1,<3.0.0) ; extra == "tools" or extra == "all"
+Requires-Dist: imageio[pyav] (>=2.34.2,<3.0.0) ; extra == "tools" or extra == "all"
 Requires-Dist: jsonschema (>=4,<5)
 Requires-Dist: litellm (>=1.38.1,<2.0.0) ; extra == "model-platforms" or extra == "all"
 Requires-Dist: mock (>=5,<6) ; extra == "test"
@@ -60,7 +60,7 @@ Requires-Dist: pytest-asyncio (>=0.23.0,<0.24.0) ; extra == "test"
 Requires-Dist: qdrant-client (>=1.9.0,<2.0.0) ; extra == "vector-databases" or extra == "all"
 Requires-Dist: rank-bm25 (>=0.2.2,<0.3.0) ; extra == "retrievers" or extra == "all"
 Requires-Dist: requests_oauthlib (>=1.3.1,<2.0.0) ; extra == "tools" or extra == "all"
-Requires-Dist: sentence-transformers (>=2.2.2,<3.0.0) ; extra == "encoders" or extra == "all"
+Requires-Dist: sentence-transformers (>=3.0.1,<4.0.0) ; extra == "encoders" or extra == "all"
 Requires-Dist: sentencepiece (>=0,<1) ; extra == "huggingface-agent" or extra == "all"
 Requires-Dist: slack-sdk (>=3.27.2,<4.0.0) ; extra == "tools" or extra == "all"
 Requires-Dist: soundfile (>=0,<1) ; extra == "huggingface-agent" or extra == "all"
@@ -180,13 +180,13 @@ exit
 Install `CAMEL` from source with conda and pip:
 ```sh
 # Create a conda virtual environment
-conda create --name camel python=3.10
+conda create --name camel python=3.9
 
 # Activate CAMEL conda environment
 conda activate camel
 
 # Clone github repo
-git clone -b v0.1.5.2 https://github.com/camel-ai/camel.git
+git clone -b v0.1.5.4 https://github.com/camel-ai/camel.git
 
 # Change directory into project directory
 cd camel
@@ -246,54 +246,67 @@ python examples/ai_society/role_playing.py
 Please note that the environment variable is session-specific. If you open a new terminal window or tab, you will need to set the API key again in that new session.
 
 
-## Use Open-Source Models as Backends
+## Use Open-Source Models as Backends (ex. using Ollama to set Llama 3 locally)
 
-The basic workflow of using an open-sourced model as the backend is based on an external server running LLM inference service, e.g. during the development we chose [FastChat](https://github.com/lm-sys/FastChat) to run the service.
-
-We do not fix the choice of server to decouple the implementation of any specific LLM inference server with CAMEL (indicating the server needs to be deployed by the user himself). But the server to be deployed must satisfy that **it supports OpenAI-compatible APIs, especially the method `openai.ChatCompletion.create`**.
-
-Here are some instructions for enabling open-source backends, where we use the [FastChat](https://github.com/lm-sys/FastChat) and a LLaMA2-based model ([`meta-llama/Llama-2-7b-chat-hf`](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)) in the example. Please install FastChat in advance following their installation guidance.
-
-1. Before running CAMEL, we should firstly launch FastChat server following the guidance on https://github.com/lm-sys/FastChat/blob/main/docs/openai_api.md. The instructions summarized below should be kept running **in separate processes**:
-
-```sh
-# Launch the controller
-python -m fastchat.serve.controller
-
-# Launch the model worker(s)
-python3 -m fastchat.serve.model_worker --model-path meta-llama/Llama-2-7b-chat-hf
-
-# Launch the RESTful API server
-python3 -m fastchat.serve.openai_api_server --host localhost --port 8000
-```
+- Download [Ollama](https://ollama.com/download).
+- After setting up Ollama, pull the Llama3 model by typing the following command into the terminal:
+    ```bash
+    ollama pull llama3
+    ```
+- Create a ModelFile similar the one below in your project directory.
+    ```bash
+    FROM llama3
 
-2. After observing the controller successfully receiving the heart beat signal from the worker, the server should be ready for use at http://localhost:8000/v1.
+    # Set parameters
+    PARAMETER temperature 0.8
+    PARAMETER stop Result
 
-3. Then we can try on running `role_playing_with_open_source_model.py`, where each agent in this example is initialized with specifying the `model_path` and `server_url`, similar to the example code below:
+    # Sets a custom system message to specify the behavior of the chat assistant
 
-```python
-system_message = # ...
+    # Leaving it blank for now.
 
-agent_kwargs = dict(
-    model=model_type,
-    model_config=OpenSourceConfig(
-        model_path="meta-llama/Llama-2-7b-chat-hf",
-        server_url="http://localhost:8000/v1",
-    ),
-)
+    SYSTEM """ """
+    ```
+- Create a script to get the base model (llama3) and create a custom model using the ModelFile above. Save this as a .sh file:
+    ```bash
+    #!/bin/zsh
 
-agent = ChatAgent(
-    system_message,
-    **agent_kwargs,
-)
-```
+    # variables
+    model_name="llama3"
+    custom_model_name="camel-llama3"
 
-### Supported Models
+    #get the base model
+    ollama pull $model_name
 
-- LLaMA2-based models
-  - example: [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
-- Vicuna-based models
-  - example: [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5)
+    #create the model file
+    ollama create $custom_model_name -f ./Llama3ModelFile
+    ```
+- Navigate to the directory where the script and ModelFile are located and run the script. Enjoy your Llama3 model, enhanced by CAMEL's excellent agents.
+    ```python
+    from camel.agents import ChatAgent
+    from camel.messages import BaseMessage
+    from camel.models import ModelFactory
+    from camel.types import ModelPlatformType
+
+    ollama_model = ModelFactory.create(
+        model_platform=ModelPlatformType.OLLAMA,
+        model_type="llama3",
+        url="http://localhost:11434/v1",
+        model_config_dict={"temperature": 0.4},
+    )
+
+    assistant_sys_msg = BaseMessage.make_assistant_message(
+        role_name="Assistant",
+        content="You are a helpful assistant.",
+    )
+    agent = ChatAgent(assistant_sys_msg, model=ollama_model, token_limit=4096)
+
+    user_msg = BaseMessage.make_user_message(
+        role_name="User", content="Say hi to CAMEL"
+    )
+    assistant_response = agent.step(user_msg)
+    print(assistant_response.msg.content)
+    ```
 
 ## Data (Hosted on Hugging Face)
 | Dataset        | Chat format                                                                                         | Instruction format                                                                                               | Chat format (translated)                                                                   |

{camel_ai-0.1.5.2 → camel_ai-0.1.5.4}/README.md

@@ -104,13 +104,13 @@ exit
 Install `CAMEL` from source with conda and pip:
 ```sh
 # Create a conda virtual environment
-conda create --name camel python=3.10
+conda create --name camel python=3.9
 
 # Activate CAMEL conda environment
 conda activate camel
 
 # Clone github repo
-git clone -b v0.1.5.2 https://github.com/camel-ai/camel.git
+git clone -b v0.1.5.4 https://github.com/camel-ai/camel.git
 
 # Change directory into project directory
 cd camel
@@ -170,54 +170,67 @@ python examples/ai_society/role_playing.py
 Please note that the environment variable is session-specific. If you open a new terminal window or tab, you will need to set the API key again in that new session.
 
 
-## Use Open-Source Models as Backends
+## Use Open-Source Models as Backends (ex. using Ollama to set Llama 3 locally)
 
-The basic workflow of using an open-sourced model as the backend is based on an external server running LLM inference service, e.g. during the development we chose [FastChat](https://github.com/lm-sys/FastChat) to run the service.
-
-We do not fix the choice of server to decouple the implementation of any specific LLM inference server with CAMEL (indicating the server needs to be deployed by the user himself). But the server to be deployed must satisfy that **it supports OpenAI-compatible APIs, especially the method `openai.ChatCompletion.create`**.
-
-Here are some instructions for enabling open-source backends, where we use the [FastChat](https://github.com/lm-sys/FastChat) and a LLaMA2-based model ([`meta-llama/Llama-2-7b-chat-hf`](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)) in the example. Please install FastChat in advance following their installation guidance.
-
-1. Before running CAMEL, we should firstly launch FastChat server following the guidance on https://github.com/lm-sys/FastChat/blob/main/docs/openai_api.md. The instructions summarized below should be kept running **in separate processes**:
-
-```sh
-# Launch the controller
-python -m fastchat.serve.controller
-
-# Launch the model worker(s)
-python3 -m fastchat.serve.model_worker --model-path meta-llama/Llama-2-7b-chat-hf
-
-# Launch the RESTful API server
-python3 -m fastchat.serve.openai_api_server --host localhost --port 8000
-```
+- Download [Ollama](https://ollama.com/download).
+- After setting up Ollama, pull the Llama3 model by typing the following command into the terminal:
+    ```bash
+    ollama pull llama3
+    ```
+- Create a ModelFile similar the one below in your project directory.
+    ```bash
+    FROM llama3
 
-2. After observing the controller successfully receiving the heart beat signal from the worker, the server should be ready for use at http://localhost:8000/v1.
+    # Set parameters
+    PARAMETER temperature 0.8
+    PARAMETER stop Result
 
-3. Then we can try on running `role_playing_with_open_source_model.py`, where each agent in this example is initialized with specifying the `model_path` and `server_url`, similar to the example code below:
+    # Sets a custom system message to specify the behavior of the chat assistant
 
-```python
-system_message = # ...
+    # Leaving it blank for now.
 
-agent_kwargs = dict(
-    model=model_type,
-    model_config=OpenSourceConfig(
-        model_path="meta-llama/Llama-2-7b-chat-hf",
-        server_url="http://localhost:8000/v1",
-    ),
-)
+    SYSTEM """ """
+    ```
+- Create a script to get the base model (llama3) and create a custom model using the ModelFile above. Save this as a .sh file:
+    ```bash
+    #!/bin/zsh
 
-agent = ChatAgent(
-    system_message,
-    **agent_kwargs,
-)
-```
+    # variables
+    model_name="llama3"
+    custom_model_name="camel-llama3"
 
-### Supported Models
+    #get the base model
+    ollama pull $model_name
 
-- LLaMA2-based models
-  - example: [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
-- Vicuna-based models
-  - example: [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5)
+    #create the model file
+    ollama create $custom_model_name -f ./Llama3ModelFile
+    ```
+- Navigate to the directory where the script and ModelFile are located and run the script. Enjoy your Llama3 model, enhanced by CAMEL's excellent agents.
+    ```python
+    from camel.agents import ChatAgent
+    from camel.messages import BaseMessage
+    from camel.models import ModelFactory
+    from camel.types import ModelPlatformType
+
+    ollama_model = ModelFactory.create(
+        model_platform=ModelPlatformType.OLLAMA,
+        model_type="llama3",
+        url="http://localhost:11434/v1",
+        model_config_dict={"temperature": 0.4},
+    )
+
+    assistant_sys_msg = BaseMessage.make_assistant_message(
+        role_name="Assistant",
+        content="You are a helpful assistant.",
+    )
+    agent = ChatAgent(assistant_sys_msg, model=ollama_model, token_limit=4096)
+
+    user_msg = BaseMessage.make_user_message(
+        role_name="User", content="Say hi to CAMEL"
+    )
+    assistant_response = agent.step(user_msg)
+    print(assistant_response.msg.content)
+    ```
 
 ## Data (Hosted on Hugging Face)
 | Dataset        | Chat format                                                                                         | Instruction format                                                                                               | Chat format (translated)                                                                   |

{camel_ai-0.1.5.2 → camel_ai-0.1.5.4}/camel/agents/chat_agent.py

@@ -32,6 +32,7 @@ from camel.responses import ChatAgentResponse
 from camel.types import (
     ChatCompletion,
     ChatCompletionChunk,
+    ModelPlatformType,
     ModelType,
     OpenAIBackendRole,
     RoleType,
@@ -41,7 +42,6 @@ from camel.utils import get_model_encoding
 if TYPE_CHECKING:
     from openai import Stream
 
-    from camel.configs import BaseConfig
     from camel.functions import OpenAIFunction
     from camel.terminators import ResponseTerminator
 
@@ -80,10 +80,9 @@ class ChatAgent(BaseAgent):
 
     Args:
         system_message (BaseMessage): The system message for the chat agent.
-        model_type (ModelType, optional): The LLM model to use for generating
-            responses. (default :obj:`ModelType.GPT_3_5_TURBO`)
-        model_config (BaseConfig, optional): Configuration options for the
-            LLM model. (default: :obj:`None`)
+        model (BaseModelBackend, optional): The model backend to use for
+            generating responses. (default: :obj:`OpenAIModel` with
+            `GPT_3_5_TURBO`)
         api_key (str, optional): The API key for authenticating with the
             LLM service. Only OpenAI and Anthropic model supported (default:
             :obj:`None`)
@@ -109,8 +108,7 @@ class ChatAgent(BaseAgent):
     def __init__(
         self,
         system_message: BaseMessage,
-        model_type: Optional[ModelType] = None,
-        model_config: Optional[BaseConfig] = None,
+        model: Optional[BaseModelBackend] = None,
         api_key: Optional[str] = None,
         memory: Optional[AgentMemory] = None,
         message_window_size: Optional[int] = None,
@@ -123,24 +121,30 @@ class ChatAgent(BaseAgent):
         self.system_message = system_message
         self.role_name: str = system_message.role_name
         self.role_type: RoleType = system_message.role_type
+        self._api_key = api_key
+        self.model_backend: BaseModelBackend = (
+            model
+            if model is not None
+            else ModelFactory.create(
+                model_platform=ModelPlatformType.OPENAI,
+                model_type=ModelType.GPT_3_5_TURBO,
+                model_config_dict=ChatGPTConfig().__dict__,
+                api_key=self._api_key,
+            )
+        )
         self.output_language: Optional[str] = output_language
         if self.output_language is not None:
             self.set_output_language(self.output_language)
 
-        self.model_type: ModelType = (
-            model_type if model_type is not None else ModelType.GPT_3_5_TURBO
-        )
+        self.model_type: ModelType = self.model_backend.model_type
 
         self.func_dict: Dict[str, Callable] = {}
         if tools is not None:
             for func in tools:
                 self.func_dict[func.get_function_name()] = func.func
 
-        self.model_config = model_config or ChatGPTConfig()
-        self._api_key = api_key
-        self.model_backend: BaseModelBackend = ModelFactory.create(
-            self.model_type, self.model_config.__dict__, self._api_key
-        )
+        self.model_config_dict = self.model_backend.model_config_dict
+
         self.model_token_limit = token_limit or self.model_backend.token_limit
         context_creator = ScoreBasedContextCreator(
             self.model_backend.token_counter,
@@ -643,7 +647,7 @@ class ChatAgent(BaseAgent):
         func = self.func_dict[func_name]
 
         args_str: str = choice.message.tool_calls[0].function.arguments
-        args = json.loads(args_str.replace("'", "\""))
+        args = json.loads(args_str)
 
         # Pass the extracted arguments to the indicated function
         try:
@@ -702,7 +706,7 @@ class ChatAgent(BaseAgent):
         func = self.func_dict[func_name]
 
         args_str: str = choice.message.tool_calls[0].function.arguments
-        args = json.loads(args_str.replace("'", "\""))
+        args = json.loads(args_str)
 
         # Pass the extracted arguments to the indicated function
         try:

{camel_ai-0.1.5.2 → camel_ai-0.1.5.4}/camel/agents/critic_agent.py

@@ -20,8 +20,8 @@ from colorama import Fore
 from camel.agents.chat_agent import ChatAgent
 from camel.memories import AgentMemory
 from camel.messages import BaseMessage
+from camel.models import BaseModelBackend
 from camel.responses import ChatAgentResponse
-from camel.types import ModelType
 from camel.utils import get_first_int, print_text_animated
 
 
@@ -31,10 +31,9 @@ class CriticAgent(ChatAgent):
     Args:
         system_message (BaseMessage): The system message for the critic
             agent.
-        model_type (ModelType, optional): The LLM model to use for generating
-            responses. (default :obj:`ModelType.GPT_3_5_TURBO`)
-        model_config (Any, optional): Configuration options for the LLM model.
-            (default: :obj:`None`)
+        model (BaseModelBackend, optional): The model backend to use for
+            generating responses. (default: :obj:`OpenAIModel` with
+            `GPT_3_5_TURBO`)
         message_window_size (int, optional): The maximum number of previous
             messages to include in the context window. If `None`, no windowing
             is performed. (default: :obj:`6`)
@@ -48,8 +47,7 @@ class CriticAgent(ChatAgent):
     def __init__(
         self,
         system_message: BaseMessage,
-        model_type: ModelType = ModelType.GPT_3_5_TURBO,
-        model_config: Optional[Any] = None,
+        model: Optional[BaseModelBackend] = None,
         memory: Optional[AgentMemory] = None,
         message_window_size: int = 6,
         retry_attempts: int = 2,
@@ -58,8 +56,7 @@ class CriticAgent(ChatAgent):
     ) -> None:
         super().__init__(
             system_message,
-            model_type=model_type,
-            model_config=model_config,
+            model=model,
             memory=memory,
             message_window_size=message_window_size,
         )

{camel_ai-0.1.5.2 → camel_ai-0.1.5.4}/camel/agents/deductive_reasoner_agent.py

@@ -15,10 +15,10 @@ import re
 from typing import Dict, List, Optional, Union
 
 from camel.agents.chat_agent import ChatAgent
-from camel.configs import BaseConfig
 from camel.messages import BaseMessage
+from camel.models import BaseModelBackend
 from camel.prompts import TextPrompt
-from camel.types import ModelType, RoleType
+from camel.types import RoleType
 
 
 class DeductiveReasonerAgent(ChatAgent):
@@ -33,16 +33,14 @@ class DeductiveReasonerAgent(ChatAgent):
         - L represents the path or process from A to B.
 
     Args:
-        model_type (ModelType, optional): The type of model to use for the
-            agent. (default: :obj: `None`)
-        model_config (BaseConfig, optional): The configuration for the model.
-            (default: :obj:`None`)
+        model (BaseModelBackend, optional): The model backend to use for
+            generating responses. (default: :obj:`OpenAIModel` with
+            `GPT_3_5_TURBO`)
     """
 
     def __init__(
         self,
-        model_type: Optional[ModelType] = None,
-        model_config: Optional[BaseConfig] = None,
+        model: Optional[BaseModelBackend] = None,
     ) -> None:
         system_message = BaseMessage(
             role_name="Insight Agent",
@@ -50,7 +48,7 @@ class DeductiveReasonerAgent(ChatAgent):
             meta_dict=None,
             content="You assign roles based on tasks.",
         )
-        super().__init__(system_message, model_type, model_config)
+        super().__init__(system_message, model=model)
 
     def deduce_conditions_and_quality(
         self,

{camel_ai-0.1.5.2 → camel_ai-0.1.5.4}/camel/agents/embodied_agent.py

@@ -23,8 +23,8 @@ from camel.interpreters import (
     SubprocessInterpreter,
 )
 from camel.messages import BaseMessage
+from camel.models import BaseModelBackend
 from camel.responses import ChatAgentResponse
-from camel.types import ModelType
 from camel.utils import print_text_animated
 
 
@@ -33,10 +33,9 @@ class EmbodiedAgent(ChatAgent):
 
     Args:
         system_message (BaseMessage): The system message for the chat agent.
-        model_type (ModelType, optional): The LLM model to use for generating
-            responses. (default :obj:`ModelType.GPT_4`)
-        model_config (Any, optional): Configuration options for the LLM model.
-            (default: :obj:`None`)
+        model (BaseModelBackend, optional): The model backend to use for
+            generating responses. (default: :obj:`OpenAIModel` with
+            `GPT_3_5_TURBO`)
         message_window_size (int, optional): The maximum number of previous
             messages to include in the context window. If `None`, no windowing
             is performed. (default: :obj:`None`)
@@ -55,8 +54,7 @@ class EmbodiedAgent(ChatAgent):
     def __init__(
         self,
         system_message: BaseMessage,
-        model_type: ModelType = ModelType.GPT_4,
-        model_config: Optional[Any] = None,
+        model: Optional[BaseModelBackend] = None,
         message_window_size: Optional[int] = None,
         tool_agents: Optional[List[BaseToolAgent]] = None,
         code_interpreter: Optional[BaseInterpreter] = None,
@@ -78,8 +76,7 @@ class EmbodiedAgent(ChatAgent):
         self.logger_color = logger_color
         super().__init__(
             system_message=system_message,
-            model_type=model_type,
-            model_config=model_config,
+            model=model,
             message_window_size=message_window_size,
         )
 

{camel_ai-0.1.5.2 → camel_ai-0.1.5.4}/camel/agents/knowledge_graph_agent.py

@@ -11,19 +11,23 @@
 # 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, Optional, Union
+from typing import Optional, Union
 
-from unstructured.documents.elements import Element
+try:
+    from unstructured.documents.elements import Element
+except ImportError:
+    Element = None
 
 from camel.agents import ChatAgent
 from camel.messages import BaseMessage
+from camel.models import BaseModelBackend
 from camel.prompts import TextPrompt
 from camel.storages.graph_storages.graph_element import (
     GraphElement,
     Node,
     Relationship,
 )
-from camel.types import ModelType, RoleType
+from camel.types import RoleType
 
 text_prompt = """
 You are tasked with extracting nodes and relationships from given content and 
@@ -105,16 +109,14 @@ class KnowledgeGraphAgent(ChatAgent):
 
     def __init__(
         self,
-        model_type: ModelType = ModelType.GPT_3_5_TURBO,
-        model_config: Optional[Any] = None,
+        model: Optional[BaseModelBackend] = None,
     ) -> None:
         r"""Initialize the `KnowledgeGraphAgent`.
 
         Args:
-            model_type (ModelType, optional): The type of model to use for the
-                agent. Defaults to `ModelType.GPT_3_5_TURBO`.
-            model_config (Any, optional): The configuration for the model.
-                Defaults to `None`.
+        model (BaseModelBackend, optional): The model backend to use for
+            generating responses. (default: :obj:`OpenAIModel` with
+            `GPT_3_5_TURBO`)
         """
         system_message = BaseMessage(
             role_name="Graphify",
@@ -126,7 +128,7 @@ class KnowledgeGraphAgent(ChatAgent):
             "illuminate the hidden connections within the chaos of "
             "information.",
         )
-        super().__init__(system_message, model_type, model_config)
+        super().__init__(system_message, model=model)
 
     def run(
         self,

{camel_ai-0.1.5.2 → camel_ai-0.1.5.4}/camel/agents/role_assignment_agent.py

@@ -12,32 +12,31 @@
 # limitations under the License.
 # =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
 import re
-from typing import Any, Dict, Optional, Union
+from typing import Dict, Optional, Union
 
 from camel.agents.chat_agent import ChatAgent
 from camel.messages import BaseMessage
+from camel.models import BaseModelBackend
 from camel.prompts import TextPrompt
-from camel.types import ModelType, RoleType
+from camel.types import RoleType
 
 
 class RoleAssignmentAgent(ChatAgent):
     r"""An agent that generates role names based on the task prompt.
 
+    Args:
+        model (BaseModelBackend, optional): The model backend to use for
+            generating responses. (default: :obj:`OpenAIModel` with
+            `GPT_3_5_TURBO`)
+
     Attributes:
         role_assignment_prompt (TextPrompt): A prompt for the agent to generate
         role names.
-
-    Args:
-        model_type (ModelType, optional): The type of model to use for the
-            agent. (default: :obj:`ModelType.GPT_3_5_TURBO`)
-        model_config (Any, optional): The configuration for the model.
-            (default: :obj:`None`)
     """
 
     def __init__(
         self,
-        model_type: ModelType = ModelType.GPT_3_5_TURBO,
-        model_config: Optional[Any] = None,
+        model: Optional[BaseModelBackend] = None,
     ) -> None:
         system_message = BaseMessage(
             role_name="Role Assigner",
@@ -45,7 +44,7 @@ class RoleAssignmentAgent(ChatAgent):
             meta_dict=None,
             content="You assign roles based on tasks.",
         )
-        super().__init__(system_message, model_type, model_config)
+        super().__init__(system_message, model=model)
 
     def run(
         self,

{camel_ai-0.1.5.2 → camel_ai-0.1.5.4}/camel/agents/search_agent.py

@@ -11,12 +11,13 @@
 # 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, Optional
+from typing import Optional
 
 from camel.agents.chat_agent import ChatAgent
 from camel.messages import BaseMessage
+from camel.models import BaseModelBackend
 from camel.prompts import TextPrompt
-from camel.types import ModelType, RoleType
+from camel.types import RoleType
 from camel.utils import create_chunks
 
 
@@ -33,8 +34,7 @@ class SearchAgent(ChatAgent):
 
     def __init__(
         self,
-        model_type: ModelType = ModelType.GPT_3_5_TURBO,
-        model_config: Optional[Any] = None,
+        model: Optional[BaseModelBackend] = None,
     ) -> None:
         system_message = BaseMessage(
             role_name="Assistant",
@@ -42,7 +42,7 @@ class SearchAgent(ChatAgent):
             meta_dict=None,
             content="You are a helpful assistant.",
         )
-        super().__init__(system_message, model_type, model_config)
+        super().__init__(system_message, model=model)
 
     def summarize_text(self, text: str, query: str) -> str:
         r"""Summarize the information from the text, base on the query.