forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
122 lines
2.7 KiB
Plaintext
122 lines
2.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "c350765d",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Python Code\n",
|
|
"\n",
|
|
"`PythonCodeTextSplitter` splits text along python class and method definitions. It's implemented as a simple subclass of `RecursiveCharacterSplitter` with Python-specific separators. See the source code to see the Python syntax expected by default.\n",
|
|
"\n",
|
|
"1. How the text is split: by list of python specific separators\n",
|
|
"2. How the chunk size is measured: by number of characters"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "1703463f",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.text_splitter import PythonCodeTextSplitter"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "f17a1854",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"python_text = \"\"\"\n",
|
|
"class Foo:\n",
|
|
"\n",
|
|
" def bar():\n",
|
|
" \n",
|
|
" \n",
|
|
"def foo():\n",
|
|
"\n",
|
|
"def testing_func_with_long_name():\n",
|
|
"\n",
|
|
"def bar():\n",
|
|
"\"\"\"\n",
|
|
"python_splitter = PythonCodeTextSplitter(chunk_size=40, chunk_overlap=0)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "8cc33770",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"docs = python_splitter.create_documents([python_text])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "f5f70775",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[Document(page_content='class Foo:\\n\\n def bar():', metadata={}),\n",
|
|
" Document(page_content='def foo():', metadata={}),\n",
|
|
" Document(page_content='def testing_func_with_long_name():', metadata={}),\n",
|
|
" Document(page_content='def bar():', metadata={})]"
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"docs"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "6e096d42",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.9.1"
|
|
},
|
|
"vscode": {
|
|
"interpreter": {
|
|
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
|
|
}
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|