langchain/docs/extras/integrations/toolkits/jira.ipynb
2023-07-23 23:23:16 -07:00

166 lines
4.6 KiB
Plaintext

{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "245a954a",
"metadata": {},
"source": [
"# Jira\n",
"\n",
"This notebook goes over how to use the Jira tool.\n",
"The Jira tool allows agents to interact with a given Jira instance, performing actions such as searching for issues and creating issues, the tool wraps the atlassian-python-api library, for more see: https://atlassian-python-api.readthedocs.io/jira.html\n",
"\n",
"To use this tool, you must first set as environment variables:\n",
" JIRA_API_TOKEN\n",
" JIRA_USERNAME\n",
" JIRA_INSTANCE_URL"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "961b3689",
"metadata": {
"vscode": {
"languageId": "shellscript"
},
"ExecuteTime": {
"start_time": "2023-04-17T10:21:18.698672Z",
"end_time": "2023-04-17T10:21:20.168639Z"
}
},
"outputs": [],
"source": [
"%pip install atlassian-python-api"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "34bb5968",
"metadata": {
"ExecuteTime": {
"start_time": "2023-04-17T10:21:22.911233Z",
"end_time": "2023-04-17T10:21:23.730922Z"
}
},
"outputs": [],
"source": [
"import os\n",
"from langchain.agents import AgentType\n",
"from langchain.agents import initialize_agent\n",
"from langchain.agents.agent_toolkits.jira.toolkit import JiraToolkit\n",
"from langchain.llms import OpenAI\n",
"from langchain.utilities.jira import JiraAPIWrapper"
]
},
{
"cell_type": "code",
"execution_count": 4,
"outputs": [],
"source": [
"os.environ[\"JIRA_API_TOKEN\"] = \"abc\"\n",
"os.environ[\"JIRA_USERNAME\"] = \"123\"\n",
"os.environ[\"JIRA_INSTANCE_URL\"] = \"https://jira.atlassian.com\"\n",
"os.environ[\"OPENAI_API_KEY\"] = \"xyz\""
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"start_time": "2023-04-17T10:22:42.499447Z",
"end_time": "2023-04-17T10:22:42.505412Z"
}
},
"id": "b3050b55"
},
{
"cell_type": "code",
"execution_count": 5,
"id": "ac4910f8",
"metadata": {
"ExecuteTime": {
"start_time": "2023-04-17T10:22:44.664481Z",
"end_time": "2023-04-17T10:22:44.720538Z"
}
},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"jira = JiraAPIWrapper()\n",
"toolkit = JiraToolkit.from_jira_api_wrapper(jira)\n",
"agent = initialize_agent(\n",
" toolkit.get_tools(), llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"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 create an issue in project PW\n",
"Action: Create Issue\n",
"Action Input: {\"summary\": \"Make more fried rice\", \"description\": \"Reminder to make more fried rice\", \"issuetype\": {\"name\": \"Task\"}, \"priority\": {\"name\": \"Low\"}, \"project\": {\"key\": \"PW\"}}\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mNone\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: A new issue has been created in project PW with the summary \"Make more fried rice\" and description \"Reminder to make more fried rice\".\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": "'A new issue has been created in project PW with the summary \"Make more fried rice\" and description \"Reminder to make more fried rice\".'"
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"make a new issue in project PW to remind me to make more fried rice\")"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"start_time": "2023-04-17T10:23:33.662454Z",
"end_time": "2023-04-17T10:23:38.121883Z"
}
},
"id": "d5461370"
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"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": "3.9.7"
},
"vscode": {
"interpreter": {
"hash": "53f3bc57609c7a84333bb558594977aa5b4026b1d6070b93987956689e367341"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}