chore: sglang doc, logger setting, version release (#1317)

Co-authored-by: Wendong <[email protected]>
Co-authored-by: Wendong-Fan <[email protected]>

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -26,7 +26,7 @@ body:
     attributes:
       label: What version of camel are you using?
       description: Run command `python3 -c 'print(__import__("camel").__version__)'` in your shell and paste the output here.
-      placeholder: E.g., 0.2.15a0
+      placeholder: E.g., 0.2.15
     validations:
       required: true
 

README.md

@@ -144,7 +144,7 @@ conda create --name camel python=3.10
 conda activate camel
 
 # Clone github repo
-git clone -b v0.2.15a0 https://github.com/camel-ai/camel.git
+git clone -b v0.2.15 https://github.com/camel-ai/camel.git
 
 # Change directory into project directory
 cd camel

camel/__init__.py

@@ -14,7 +14,7 @@
 
 from camel.logger import disable_logging, enable_logging, set_log_level
 
-__version__ = '0.2.15a0'
+__version__ = '0.2.15'
 
 __all__ = [
     '__version__',

camel/logger.py

@@ -26,18 +26,24 @@ def _configure_library_logging():
 
     if not logging.root.handlers and not _logger.handlers:
         logging.basicConfig(
-            level=os.environ.get('LOGLEVEL', 'INFO').upper(),
+            level=os.environ.get('CAMEL_LOGGING_LEVEL', 'WARNING').upper(),
             format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
             stream=sys.stdout,
         )
         logging.setLoggerClass(logging.Logger)
-        _logger.info("CAMEL library logging has been configured.")
+        _logger.info(
+            f"CAMEL library logging has been configured "
+            f"(level: {_logger.getEffectiveLevel()}). "
+            f"To change level, use set_log_level() or "
+            "set CAMEL_LOGGING_LEVEL env var. To disable logging, "
+            "set CAMEL_LOGGING_DISABLED=true or use disable_logging()"
+        )
     else:
         _logger.debug("Existing logger configuration found, using that.")
 
 
 def disable_logging():
-    r"""Disable all logging for the Camel library.
+    r"""Disable all logging for the CAMEL library.
 
     This function sets the log level to a value higher than CRITICAL,
     effectively disabling all log messages, and adds a NullHandler to
@@ -55,7 +61,7 @@ def disable_logging():
 
 
 def enable_logging():
-    r"""Enable logging for the Camel library.
+    r"""Enable logging for the CAMEL library.
 
     This function re-enables logging if it was previously disabled,
     and configures the library logging using the default settings.
@@ -67,7 +73,7 @@ def enable_logging():
 
 
 def set_log_level(level):
-    r"""Set the logging level for the Camel library.
+    r"""Set the logging level for the CAMEL library.
 
     Args:
         level (Union[str, int]): The logging level to set. This can be a string

docs/cookbooks/cot_data_gen_sft_qwen_unsolth_upload_huggingface.ipynb

@@ -71,7 +71,7 @@
       "outputs": [],
       "source": [
         "%%capture\n",
-        "!pip install camel-ai==0.2.15a0"
+        "!pip install camel-ai==0.2.15"
       ]
     },
     {

docs/cookbooks/cot_data_gen_upload_to_huggingface.py.ipynb

@@ -71,7 +71,7 @@
       "outputs": [],
       "source": [
         "%%capture\n",
-        "!pip install camel-ai==0.2.15a0"
+        "!pip install camel-ai==0.2.15"
       ]
     },
     {

docs/cookbooks/customer_service_Discord_bot_using_local_model_with_agentic_RAG.ipynb

@@ -51,7 +51,7 @@
     "outputId": "72f5cfe5-60ea-48ba-e1e1-a0cdc4eb87ec"
    },
    "source": [
-    "!pip install \"camel-ai[all]==0.2.15a0\"\n",
+    "!pip install \"camel-ai[all]==0.2.15\"\n",
     "!pip install starlette\n",
     "!pip install nest_asyncio"
    ],

docs/get_started/installation.md

@@ -60,7 +60,7 @@ conda create --name camel python=3.10
 conda activate camel
 
 # Clone github repo
-git clone -b v0.2.15a0 https://github.com/camel-ai/camel.git
+git clone -b v0.2.15 https://github.com/camel-ai/camel.git
 
 # Change directory into project directory
 cd camel

docs/key_modules/models.md

@@ -81,6 +81,7 @@ The following table lists currently supported model platforms by CAMEL.
 | vLLM | https://docs.vllm.ai/en/latest/models/supported_models.html | ----- |
 | Together AI | https://docs.together.ai/docs/chat-models | ----- |
 | LiteLLM | https://docs.litellm.ai/docs/providers | ----- |
+| SGLang | https://sgl-project.github.io/references/supported_models.html | ----- |
 
 ## 3. Using Models by API calling
 
@@ -222,6 +223,35 @@ assistant_response = agent.step(user_msg)
 print(assistant_response.msg.content)
 ```
 
+### 4.3 Using SGLang to Set meta-llama/Llama Locally
+
+Install [SGLang](https://sgl-project.github.io/start/install.html) first.
+
+Create and run following script (more details please refer to this [example](https://github.com/camel-ai/camel/blob/master/examples/models/sglang_model_example.py)):
+
+```python
+from camel.agents import ChatAgent
+from camel.messages import BaseMessage
+from camel.models import ModelFactory
+from camel.types import ModelPlatformType
+
+sglang_model = ModelFactory.create(
+    model_platform=ModelPlatformType.SGLANG,
+    model_type="meta-llama/Llama-3.2-1B-Instruct",
+    model_config_dict={"temperature": 0.0},
+    api_key="sglang",
+)
+
+agent_sys_msg = "You are a helpful assistant."
+
+agent = ChatAgent(agent_sys_msg, model=sglang_model, token_limit=4096)
+
+user_msg = "Say hi to CAMEL AI"
+
+assistant_response = agent.step(user_msg)
+print(assistant_response.msg.content)
+```
+
 ## 5. About Model Speed
 Model speed is a crucial factor in AI application performance. It affects both user experience and system efficiency, especially in real-time or interactive tasks. In [this notebook](../cookbooks/model_speed_comparison.ipynb), we compared several models, including OpenAI’s GPT-4O Mini, GPT-4O, O1 Preview, and SambaNova's Llama series, by measuring the number of tokens each model processes per second.
 
@@ -233,6 +263,8 @@ The chart below illustrates the tokens per second achieved by each model during
 
 ![Model Speed Comparison](https://i.postimg.cc/4xByytyZ/model-speed.png)
 
+For local inference, we conducted a straightforward comparison locally between vLLM and SGLang. SGLang demonstrated superior performance, with `meta-llama/Llama-3.2-1B-Instruct` reaching a peak speed of 220.98 tokens per second, compared to vLLM, which capped at 107.2 tokens per second.
+
 ## 6. Conclusion
 In conclusion, CAMEL empowers developers to explore and integrate these diverse models, unlocking new possibilities for innovative AI applications. The world of large language models offers a rich tapestry of options beyond just the well-known proprietary solutions. By guiding users through model selection, environment setup, and integration, CAMEL bridges the gap between cutting-edge AI research and practical implementation. Its hybrid approach, combining in-house implementations with third-party integrations, offers unparalleled flexibility and comprehensive support for LLM-based development. Don't just watch this transformation that is happening from the sidelines.
 

examples/models/sglang_model_example.py

@@ -31,15 +31,17 @@
 
 Please load HF_token in your environment variable.
 export HF_TOKEN=""
+When using the OpenAI interface to run SGLang model server, 
+the base model may fail to recognize  huggingface default
+chat template, switching to the Instruct model resolves the issue.
 """
 load_dotenv()
 sglang_model = ModelFactory.create(
     model_platform=ModelPlatformType.SGLANG,
-    model_type="meta-llama/Llama-3.2-1B",
+    model_type="meta-llama/Llama-3.2-1B-Instruct",
     model_config_dict={"temperature": 0.0},
     api_key="sglang",
 )
-
 assistant_sys_msg = "You are a helpful assistant."
 
 agent = ChatAgent(assistant_sys_msg, model=sglang_model, token_limit=4096)