feat: tablegpt kernel setups

collect_script.py

@@ -1,49 +1,50 @@
 import platform
-import sys
 import subprocess
-import traceback
+import sys
+
 
 def get_os_info():
     return {
-        'system': platform.system(),
-        'node': platform.node(),
-        'release': platform.release(),
-        'version': platform.version(),
-        'machine': platform.machine(),
-        'processor': platform.processor(),
+        "system": platform.system(),
+        "node": platform.node(),
+        "release": platform.release(),
+        "version": platform.version(),
+        "machine": platform.machine(),
+        "processor": platform.processor(),
     }
 
+
 def get_python_info():
     return {
-        'implementation': platform.python_implementation(),
-        'version': platform.python_version(),
-        'compiler': platform.python_compiler(),
+        "implementation": platform.python_implementation(),
+        "version": platform.python_version(),
+        "compiler": platform.python_compiler(),
     }
 
+
 def get_pip_list():
-    try:
-        result = subprocess.run([sys.executable, '-m', 'pip', 'list'], capture_output=True, text=True)
-        if result.returncode == 0:
-            return result.stdout
-        else:
-            return f"Failed to get pip list: {result.stderr}"
-    except Exception as e:
-        return f"An error occurred: {str(e)}"
-
-def write_to_log_file(content, filename='env_output.log'):
-    try:
-        with open(filename, 'w') as file:
-            file.write(content)
-    except Exception as e:
-        print(f"Error writing to file {filename}: {e}")
-        traceback.print_exc()
+    result = subprocess.run(
+        [sys.executable, "-m", "pip", "list"],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    if result.returncode == 0:
+        return result.stdout
+
+    return f"Failed to get pip list: {result.stderr}"
+
+
+def write_to_log_file(content, filename="env_output.log"):
+    with open(filename, "w") as file:
+        file.write(content)
+
 
 def main():
     os_info = get_os_info()
     python_info = get_python_info()
     pip_list = get_pip_list()
 
-
     content = "Operating System Information:\n"
     for key, value in os_info.items():
         content += f"{key}: {value}\n"
@@ -56,10 +57,11 @@ def main():
     content += pip_list
 
     # stdout
-    print(content)
+    print(content)  # noqa: T201
 
     # file
     write_to_log_file(content)
 
+
 if __name__ == "__main__":
-    main()
+    main()

docs/tutorials/quickstart.md

@@ -11,15 +11,15 @@ pip install tablegpt-agent
 This package depends on [pybox](https://github.com/edwardzjl/pybox), a Python code sandbox delegator. By default, `pybox` operates in an in-cluster mode. If you wish to run `tablegpt-agent` in a local environment, you need to install an optional dependency:
 
 ```sh
-pip install pppybox[local]
+pip install tablegpt-agent[local]
 ```
 
 ## Setup LLM Service
 
 Before using `tablegpt-agent`, ensure that you have an OpenAI-compatible server set up to host TableGPT2. We recommend using [vllm](https://github.com/vllm-project/vllm) for this:
 
 > **Note:**  If you need to use `tablegpt-agent` to analyze tabular data, please ensure your `vllm>=0.5.5`
-```sh 
+```sh
 pip install 'vllm>=0.5.5'
 ```
 
@@ -33,6 +33,10 @@ python -m vllm.entrypoints.openai.api_server --served-model-name TableGPT2-7B --
 ## Chat with TableGPT Agent
 
 To create a `TablegptAgent`, you'll need both an `LLM` and a `PyBoxManager` instance:
+> **NOTE** The `llm` is created using `langchain-openai`, please install it first.
+```sh
+pip install langchain-openai
+```
 
 ```pycon
 >>> from langchain_openai import ChatOpenAI

examples/data_analysis.py

@@ -6,6 +6,7 @@
 from langchain_openai import ChatOpenAI
 from langgraph.checkpoint.memory import MemorySaver
 from pybox import LocalPyBoxManager
+from tablegpt import DEFAULT_TABLEGPT_IPYKERNEL_PROFILE_DIR
 from tablegpt.agent import create_tablegpt_graph
 from tablegpt.agent.file_reading import Stage
 
@@ -19,10 +20,14 @@ class Attachment(TypedDict):
 
 # tablegpt-agent fully supports async invocation
 async def main() -> None:
-    llm = ChatOpenAI(openai_api_base="YOUR_VLLM_URL", openai_api_key="whatever", model_name="TableGPT2-7B")
+    llm = ChatOpenAI(
+        openai_api_base="YOUR_VLLM_URL",
+        openai_api_key="whatever",
+        model_name="TableGPT2-7B",
+    )
 
     # Use local pybox manager for development and testing
-    pybox_manager = LocalPyBoxManager()
+    pybox_manager = LocalPyBoxManager(profile_dir=DEFAULT_TABLEGPT_IPYKERNEL_PROFILE_DIR)
 
     agent = create_tablegpt_graph(
         llm=llm,
@@ -37,7 +42,7 @@ async def main() -> None:
     attachment_msg = HumanMessage(
         content="",
         # The dataset can be viewed in examples/datasets/titanic.csv.
-        additional_kwargs={"attachments": [Attachment(filename="titanic.csv")]},
+        additional_kwargs={"attachments": [Attachment(filename="examples/datasets/titanic.csv")]},
     )
     await agent.ainvoke(
         input={

pyproject.toml

@@ -29,17 +29,38 @@ dependencies = [
   "langchain-qdrant>=0.1.4,<1.0.0",
   "langgraph>=0.0.68,<1.0.0",
   "pandas>=2.2,<3.0.0",
-  "pppybox>=0.0.13",
+  "pppybox>=0.0.14"
 ]
 
 [project.urls]
 Documentation = "https://github.com/tablegpt/tablegpt/blob/main/README.md"
 Issues = "https://github.com/tablegpt/tablegpt/issues"
 Source = "https://github.com/tablegpt/tablegpt"
 
+[project.optional-dependencies]
+local = [
+  "pandas >=2.2,<3.0.0",
+  "scipy >=1.13.0,<2.0.0",
+  "tabulate >=0.9.0,<1.0.0",
+  "scikit-learn >=1.0.0,<2.0.0",
+  "statsmodels >=0.10.0,<1.0.0",
+  "matplotlib >=3.8.4,<4.0.0",
+  "seaborn >=0.13.1,<1.0.0",
+  "mplfonts >=0.0.8,<1.0.0",
+  "numexpr >=2.8.4",
+  "openpyxl >=3.1.2,<4.0.0",
+  "xlrd >= 2.0.1",
+  "odfpy",
+  "pppybox[local]>=0.0.14"
+]
+
+
 [tool.hatch.build.targets.wheel]
 packages = ["src/tablegpt"]
 
+[tool.hatch.build.targets.wheel.shared-data]
+"ipython/ipython-startup-scripts" = "share/ipykernel/profile/tablegpt/startup"
+
 [tool.hatch.version]
 path = "src/tablegpt/__about__.py"
 
@@ -75,3 +96,11 @@ exclude_lines = [
   "if __name__ == .__main__.:",
   "if TYPE_CHECKING:",
 ]
+
+[tool.ruff]
+# Exclude a variety of commonly ignored directories.
+exclude = [
+  "ipython"
+]
+# Allow lines to be as long as 120.
+line-length = 120

src/tablegpt/__init__.py

@@ -0,0 +1,4 @@
+import os
+import sys
+
+DEFAULT_TABLEGPT_IPYKERNEL_PROFILE_DIR = os.path.join(sys.prefix, "share/ipykernel/profile/tablegpt")