github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-25 08:03:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update Slack agent toolkit (#16732)

Browse Source 
Co-authored-by: taimoOptTech <132860814+taimo3810@users.noreply.github.com>
This commit is contained in:
Lance Martin 2024-01-29 08:03:44 -08:00 committed by GitHub
parent 22d90800c8
commit 1bfadecdd2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 160 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

202
docs/docs/integrations/toolkits/slack.ipynb
View File

@ -13,30 +13,65 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 8,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.2\u001b[0m\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
"Note: you may need to restart the kernel to use updated packages.\n",
"\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.2\u001b[0m\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
"Note: you may need to restart the kernel to use updated packages.\n",
"\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.2\u001b[0m\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"%pip install --upgrade --quiet slack_sdk > /dev/null\n",
"%pip install --upgrade --quiet beautifulsoup4 > /dev/null # This is optional but is useful for parsing HTML messages"
"%pip install --upgrade --quiet beautifulsoup4 > /dev/null # This is optional but is useful for parsing HTML messages\n",
"%pip install --upgrade --quiet python-dotenv > /dev/null # This is for loading environmental variables from a .env file"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Assign Environmental Variables\n",
"## Set Environmental Variables\n",
"\n",
"The toolkit will read the SLACK_USER_TOKEN environmental variable to authenticate the user so you need to set them here. You will also need to set your OPENAI_API_KEY to use the agent later."
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 9,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Set environmental variables here"
"# Set environmental variables here\n",
"# In this example, you set environmental variables by loading a .env file.\n",
"import dotenv\n",
"\n",
"dotenv.load_dotenv()"
]
},
{
@ -50,9 +85,23 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 10,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"[SlackGetChannel(client=<slack_sdk.web.client.WebClient object at 0x11eba6a00>),\n",
" SlackGetMessage(client=<slack_sdk.web.client.WebClient object at 0x11eba69d0>),\n",
" SlackScheduleMessage(client=<slack_sdk.web.client.WebClient object at 0x11eba65b0>),\n",
" SlackSendMessage(client=<slack_sdk.web.client.WebClient object at 0x11eba6790>)]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_community.agent_toolkits import SlackToolkit\n",
"\n",
@ -65,31 +114,122 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## Use within an Agent"
"## Use within an ReAct Agent"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import AgentType, initialize_agent\n",
"from langchain_openai import OpenAI"
"from langchain import hub\n",
"from langchain.agents import AgentExecutor, create_react_agent\n",
"from langchain_openai import ChatOpenAI"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"agent = initialize_agent(\n",
"llm = ChatOpenAI(temperature=0, model=\"gpt-4\")\n",
"prompt = hub.pull(\"hwchase17/react\")\n",
"agent = create_react_agent(\n",
" tools=toolkit.get_tools(),\n",
" llm=llm,\n",
" verbose=False,\n",
" agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,\n",
" prompt=prompt,\n",
")\n",
"agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"agent_executor.invoke(\n",
" {\"input\": \"Send a greeting to my coworkers in the #general channel.\"}\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mI need to get the list of channels in the workspace.\n",
"Action: get_channelid_name_dict\n",
"Action Input: {}\u001b[0m\u001b[36;1m\u001b[1;3m[{\"id\": \"C052SCUP4UD\", \"name\": \"general\", \"created\": 1681297313, \"num_members\": 1}, {\"id\": \"C052VBBU4M8\", \"name\": \"test-bots\", \"created\": 1681297343, \"num_members\": 2}, {\"id\": \"C053805TNUR\", \"name\": \"random\", \"created\": 1681297313, \"num_members\": 2}]\u001b[0m\u001b[32;1m\u001b[1;3mI now have the list of channels and their names.\n",
"Final Answer: There are 3 channels in the workspace. Their names are \"general\", \"test-bots\", and \"random\".\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'input': 'How many channels are in the workspace? Please list out their names.',\n",
" 'output': 'There are 3 channels in the workspace. Their names are \"general\", \"test-bots\", and \"random\".'}"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.invoke(\n",
" {\"input\": \"How many channels are in the workspace? Please list out their names.\"}\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mFirst, I need to identify the channel ID for the #introductions channel.\n",
"Action: get_channelid_name_dict\n",
"Action Input: None\u001b[0m\u001b[36;1m\u001b[1;3m[{\"id\": \"C052SCUP4UD\", \"name\": \"general\", \"created\": 1681297313, \"num_members\": 1}, {\"id\": \"C052VBBU4M8\", \"name\": \"test-bots\", \"created\": 1681297343, \"num_members\": 2}, {\"id\": \"C053805TNUR\", \"name\": \"random\", \"created\": 1681297313, \"num_members\": 2}]\u001b[0m\u001b[32;1m\u001b[1;3mThe #introductions channel is not listed in the observed channels. I need to inform the user that the #introductions channel does not exist or is not accessible.\n",
"Final Answer: The #introductions channel does not exist or is not accessible.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'input': 'Tell me the number of messages sent in the #introductions channel from the past month.',\n",
" 'output': 'The #introductions channel does not exist or is not accessible.'}"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.invoke(\n",
" {\n",
" \"input\": \"Tell me the number of messages sent in the #introductions channel from the past month.\"\n",
" }\n",
")"
]
},
@ -98,29 +238,7 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"agent.run(\"Send a greeting to my coworkers in the #general channel.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"agent.run(\"How many channels are in the workspace? Please list out their names.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"agent.run(\n",
" \"Tell me the number of messages sent in the #introductions channel from the past month.\"\n",
")"
]
"source": []
}
],
"metadata": {
@ -139,7 +257,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.6"
"version": "3.9.6"
}
},
"nbformat": 4,