mirror of
https://github.com/hwchase17/langchain
synced 2024-11-11 19:11:02 +00:00
168 lines
5.4 KiB
Plaintext
168 lines
5.4 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# GitHub\n",
|
|
"\n",
|
|
"This notebook goes over how to use the GitHub tool.\n",
|
|
"The GitHub tool allows agents to interact with a given GitHub repository. It implements CRUD operations for modifying files and can read/comment on Issues. The tool wraps the [PyGitHub](https://github.com/PyGithub/PyGithub) library.\n",
|
|
"\n",
|
|
"In order to interact with the GitHub API you must create a [GitHub app](https://docs.github.com/en/apps/creating-github-apps/about-creating-github-apps/about-creating-github-apps). Next, you must set the following environment variables:\n",
|
|
"```\n",
|
|
"GITHUB_APP_ID\n",
|
|
"GITHUB_APP_PRIVATE_KEY\n",
|
|
"GITHUB_REPOSITORY\n",
|
|
"GITHUB_BRANCH\n",
|
|
"```"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"vscode": {
|
|
"languageId": "shellscript"
|
|
}
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%pip install pygithub"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"from langchain.agents import AgentType\n",
|
|
"from langchain.agents import initialize_agent\n",
|
|
"from langchain.agents.agent_toolkits.github.toolkit import GitHubToolkit\n",
|
|
"from langchain.llms import OpenAI\n",
|
|
"from langchain.utilities.github import GitHubAPIWrapper"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"os.environ[\"GITHUB_APP_ID\"] = \"your-github-app-id\"\n",
|
|
"os.environ[\"GITHUB_APP_PRIVATE_KEY\"] = \"/path/to/your/private/key\"\n",
|
|
"os.environ[\"GITHUB_REPOSITORY\"] = \"user/repo\"\n",
|
|
"os.environ[\"GITHUB_BRANCH\"] = \"branch-name\"\n",
|
|
"os.environ[\"OPENAI_API_KEY\"] = \"your-openai-api-key\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"llm = OpenAI(temperature=0)\n",
|
|
"github = GitHubAPIWrapper()\n",
|
|
"toolkit = GitHubToolkit.from_github_api_wrapper(github)\n",
|
|
"agent = initialize_agent(\n",
|
|
" toolkit.get_tools(), llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n",
|
|
"\n",
|
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
|
"\u001b[32;1m\u001b[1;3m I need to figure out what issues need to be completed and how to complete them.\n",
|
|
"Action: Get Issues\n",
|
|
"Action Input: N/A\u001b[0m\n",
|
|
"Observation: \u001b[36;1m\u001b[1;3mFound 1 issues:\n",
|
|
"[{'title': 'Change the main script to print Hello AI!', 'number': 1}]\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3m I need to get more information about this issue.\n",
|
|
"Action: Get Issue\n",
|
|
"Action Input: 1\u001b[0m\n",
|
|
"Observation: \u001b[33;1m\u001b[1;3m{'title': 'Change the main script to print Hello AI!', 'body': None, 'comments': '[]'}\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3m I need to update the main script to print Hello AI!\n",
|
|
"Action: Update File\n",
|
|
"Action Input: main.py\n",
|
|
"OLD <<<<\n",
|
|
"print(\"Hello World!\")\n",
|
|
">>>> OLD\n",
|
|
"NEW <<<<\n",
|
|
"print(\"Hello AI!\")\n",
|
|
">>>> NEW\u001b[0m\n",
|
|
"Observation: \u001b[38;5;200m\u001b[1;3mFile content was not updated because the old content was not found. It may be helpful to use the read_file action to get the current file contents.\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3m I need to read the current file contents.\n",
|
|
"Action: Read File\n",
|
|
"Action Input: main.py\u001b[0m\n",
|
|
"Observation: \u001b[33;1m\u001b[1;3mprint(\"Hello world!\")\n",
|
|
"\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3m I need to update the main script to print Hello AI!\n",
|
|
"Action: Update File\n",
|
|
"Action Input: main.py\n",
|
|
"OLD <<<<\n",
|
|
"print(\"Hello world!\")\n",
|
|
">>>> OLD\n",
|
|
"NEW <<<<\n",
|
|
"print(\"Hello AI!\")\n",
|
|
">>>> NEW\u001b[0m\n",
|
|
"Observation: \u001b[38;5;200m\u001b[1;3mUpdated file main.py\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
|
"Final Answer: The main script has been updated to print \"Hello AI!\"\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'The main script has been updated to print \"Hello AI!\"'"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent.run(\n",
|
|
" \"You have the software engineering capabilities of a Google Principle engineer. You are tasked with completing issues on a github repository. Please look at the existing issues and complete them.\"\n",
|
|
")"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"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": "3.11.4"
|
|
},
|
|
"orig_nbformat": 4
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|