Spaces:
Running
Running
File size: 15,260 Bytes
cfd3735 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 |
{
"cells": [
{
"cell_type": "markdown",
"id": "16763ed3",
"metadata": {},
"source": [
"# Zapier Natural Language Actions API\n",
"\\\n",
"Full docs here: https://nla.zapier.com/api/v1/docs\n",
"\n",
"**Zapier Natural Language Actions** gives you access to the 5k+ apps, 20k+ actions on Zapier's platform through a natural language API interface.\n",
"\n",
"NLA supports apps like Gmail, Salesforce, Trello, Slack, Asana, HubSpot, Google Sheets, Microsoft Teams, and thousands more apps: https://zapier.com/apps\n",
"\n",
"Zapier NLA handles ALL the underlying API auth and translation from natural language --> underlying API call --> return simplified output for LLMs. The key idea is you, or your users, expose a set of actions via an oauth-like setup window, which you can then query and execute via a REST API.\n",
"\n",
"NLA offers both API Key and OAuth for signing NLA API requests.\n",
"\n",
"1. Server-side (API Key): for quickly getting started, testing, and production scenarios where LangChain will only use actions exposed in the developer's Zapier account (and will use the developer's connected accounts on Zapier.com)\n",
"\n",
"2. User-facing (Oauth): for production scenarios where you are deploying an end-user facing application and LangChain needs access to end-user's exposed actions and connected accounts on Zapier.com\n",
"\n",
"This quick start will focus on the server-side use case for brevity. Review [full docs](https://nla.zapier.com/api/v1/docs) or reach out to [email protected] for user-facing oauth developer support.\n",
"\n",
"This example goes over how to use the Zapier integration with a `SimpleSequentialChain`, then an `Agent`.\n",
"In code, below:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "a363309c",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "5cf33377",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"# get from https://platform.openai.com/\n",
"os.environ[\"OPENAI_API_KEY\"] = os.environ.get(\"OPENAI_API_KEY\", \"\")\n",
"\n",
"# get from https://nla.zapier.com/demo/provider/debug (under User Information, after logging in): \n",
"os.environ[\"ZAPIER_NLA_API_KEY\"] = os.environ.get(\"ZAPIER_NLA_API_KEY\", \"\")"
]
},
{
"cell_type": "markdown",
"id": "4881b484-1b97-478f-b206-aec407ceff66",
"metadata": {},
"source": [
"## Example with Agent\n",
"Zapier tools can be used with an agent. See the example below."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "b2044b17-c941-4ffb-8a03-027a35e2df81",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.agents import initialize_agent\n",
"from langchain.agents.agent_toolkits import ZapierToolkit\n",
"from langchain.agents import AgentType\n",
"from langchain.utilities.zapier import ZapierNLAWrapper"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "7b505eeb",
"metadata": {},
"outputs": [],
"source": [
"## step 0. expose gmail 'find email' and slack 'send channel message' actions\n",
"\n",
"# first go here, log in, expose (enable) the two actions: https://nla.zapier.com/demo/start -- for this example, can leave all fields \"Have AI guess\"\n",
"# in an oauth scenario, you'd get your own <provider> id (instead of 'demo') which you route your users through first"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "cab18227-c232-4214-9256-bb8dd352266c",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"zapier = ZapierNLAWrapper()\n",
"toolkit = ZapierToolkit.from_zapier_nla_wrapper(zapier)\n",
"agent = initialize_agent(toolkit.get_tools(), llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "f94713de-b64d-465f-a087-00288b5f80ec",
"metadata": {
"tags": []
},
"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 find the email and summarize it.\n",
"Action: Gmail: Find Email\n",
"Action Input: Find the latest email from Silicon Valley Bank\u001b[0m\n",
"Observation: \u001b[31;1m\u001b[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"[email protected]\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"[email protected]\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"[email protected]\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to summarize the email and send it to the #test-zapier channel in Slack.\n",
"Action: Slack: Send Channel Message\n",
"Action Input: Send a slack message to the #test-zapier channel with the text \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m{\"message__text\": \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\", \"message__permalink\": \"https://langchain.slack.com/archives/C04TSGU0RA7/p1678859932375259\", \"channel\": \"C04TSGU0RA7\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:58:52Z\", \"message__bot_profile__icons__image_36\": \"https://avatars.slack-edge.com/2022-08-02/3888649620612_f864dc1bb794cf7d82b0_36.png\", \"message__blocks[]block_id\": \"kdZZ\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Summarize the last email I received regarding Silicon Valley Bank. Send the summary to the #test-zapier channel in slack.\")"
]
},
{
"cell_type": "markdown",
"id": "bcdea831",
"metadata": {},
"source": [
"# Example with SimpleSequentialChain\n",
"If you need more explicit control, use a chain, like below."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "10a46e7e",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.chains import LLMChain, TransformChain, SimpleSequentialChain\n",
"from langchain.prompts import PromptTemplate\n",
"from langchain.tools.zapier.tool import ZapierNLARunAction\n",
"from langchain.utilities.zapier import ZapierNLAWrapper"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "b9358048",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"## step 0. expose gmail 'find email' and slack 'send direct message' actions\n",
"\n",
"# first go here, log in, expose (enable) the two actions: https://nla.zapier.com/demo/start -- for this example, can leave all fields \"Have AI guess\"\n",
"# in an oauth scenario, you'd get your own <provider> id (instead of 'demo') which you route your users through first\n",
"\n",
"actions = ZapierNLAWrapper().list()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "4e80f461",
"metadata": {},
"outputs": [],
"source": [
"## step 1. gmail find email\n",
"\n",
"GMAIL_SEARCH_INSTRUCTIONS = \"Grab the latest email from Silicon Valley Bank\"\n",
"\n",
"def nla_gmail(inputs):\n",
" action = next((a for a in actions if a[\"description\"].startswith(\"Gmail: Find Email\")), None)\n",
" return {\"email_data\": ZapierNLARunAction(action_id=action[\"id\"], zapier_description=action[\"description\"], params_schema=action[\"params\"]).run(inputs[\"instructions\"])}\n",
"gmail_chain = TransformChain(input_variables=[\"instructions\"], output_variables=[\"email_data\"], transform=nla_gmail)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "46893233",
"metadata": {},
"outputs": [],
"source": [
"## step 2. generate draft reply\n",
"\n",
"template = \"\"\"You are an assisstant who drafts replies to an incoming email. Output draft reply in plain text (not JSON).\n",
"\n",
"Incoming email:\n",
"{email_data}\n",
"\n",
"Draft email reply:\"\"\"\n",
"\n",
"prompt_template = PromptTemplate(input_variables=[\"email_data\"], template=template)\n",
"reply_chain = LLMChain(llm=OpenAI(temperature=.7), prompt=prompt_template)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "cd85c4f8",
"metadata": {},
"outputs": [],
"source": [
"## step 3. send draft reply via a slack direct message\n",
"\n",
"SLACK_HANDLE = \"@Ankush Gola\"\n",
"\n",
"def nla_slack(inputs):\n",
" action = next((a for a in actions if a[\"description\"].startswith(\"Slack: Send Direct Message\")), None)\n",
" instructions = f'Send this to {SLACK_HANDLE} in Slack: {inputs[\"draft_reply\"]}'\n",
" return {\"slack_data\": ZapierNLARunAction(action_id=action[\"id\"], zapier_description=action[\"description\"], params_schema=action[\"params\"]).run(instructions)}\n",
"slack_chain = TransformChain(input_variables=[\"draft_reply\"], output_variables=[\"slack_data\"], transform=nla_slack)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "4829cab4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
"\u001b[36;1m\u001b[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"[email protected]\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"[email protected]\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"[email protected]\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001b[0m\n",
"\u001b[33;1m\u001b[1;3m\n",
"Dear Silicon Valley Bridge Bank, \n",
"\n",
"Thank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \n",
"\n",
"Best regards, \n",
"[Your Name]\u001b[0m\n",
"\u001b[38;5;200m\u001b[1;3m{\"message__text\": \"Dear Silicon Valley Bridge Bank, \\n\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\n\\nBest regards, \\n[Your Name]\", \"message__permalink\": \"https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629\", \"channel\": \"D04TKF5BBHU\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:59:28Z\", \"message__blocks[]block_id\": \"p7i\", \"message__blocks[]elements[]elements[]type\": \"[['text']]\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'{\"message__text\": \"Dear Silicon Valley Bridge Bank, \\\\n\\\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\\\n\\\\nBest regards, \\\\n[Your Name]\", \"message__permalink\": \"https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629\", \"channel\": \"D04TKF5BBHU\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:59:28Z\", \"message__blocks[]block_id\": \"p7i\", \"message__blocks[]elements[]elements[]type\": \"[[\\'text\\']]\", \"message__blocks[]elements[]type\": \"[\\'rich_text_section\\']\"}'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"## finally, execute\n",
"\n",
"overall_chain = SimpleSequentialChain(chains=[gmail_chain, reply_chain, slack_chain], verbose=True)\n",
"overall_chain.run(GMAIL_SEARCH_INSTRUCTIONS)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "09ff954e-45f2-4595-92ea-91627abde4a0",
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|