docs: update cookbook example for SalesGPT - include Stripe Payment Link Generation (#19622)

Thank you for contributing to LangChain!

- [ ] **cookbook** - update example for SalesGPT - include Stripe
Payment Link Generation

- **Description:** We updated the Jupyter notebook example with the
ability of the AI Agent to negotiate with customers and then close the
deal by generating a custom Stripe payment link.
    - **Issue:** N/A
    - **Dependencies:** N/a
    - **Twitter handle:** @FilipMichalsky @0xtotaylor


If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.

---------

Co-authored-by: Filip Michalsky <filip_michalsky@g.harvard.edu>
Co-authored-by: Bagatur <baskaryan@gmail.com>
pull/18991/head^2
Filip Michalsky 2 months ago committed by GitHub
parent 33fa8cfcd0
commit 2fceec3771
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

@ -1,28 +1,32 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# SalesGPT - Your Context-Aware AI Sales Assistant With Knowledge Base\n",
"# SalesGPT - Context-Aware AI Sales Assistant With Knowledge Base and Ability Generate Stripe Payment Links\n",
"\n",
"This notebook demonstrates an implementation of a **Context-Aware** AI Sales agent with a Product Knowledge Base. \n",
"This notebook demonstrates an implementation of a **Context-Aware** AI Sales agent with a Product Knowledge Base which can actually close sales. \n",
"\n",
"This notebook was originally published at [filipmichalsky/SalesGPT](https://github.com/filip-michalsky/SalesGPT) by [@FilipMichalsky](https://twitter.com/FilipMichalsky).\n",
"\n",
"SalesGPT is context-aware, which means it can understand what section of a sales conversation it is in and act accordingly.\n",
" \n",
"As such, this agent can have a natural sales conversation with a prospect and behaves based on the conversation stage. Hence, this notebook demonstrates how we can use AI to automate sales development representatives activities, such as outbound sales calls. \n",
"As such, this agent can have a natural sales conversation with a prospect and behaves based on the conversation stage. Hence, this notebook demonstrates how we can use AI to automate sales development representatives activites, such as outbound sales calls. \n",
"\n",
"Additionally, the AI Sales agent has access to tools, which allow it to interact with other systems.\n",
"\n",
"Here, we show how the AI Sales Agent can use a **Product Knowledge Base** to speak about a particular's company offerings,\n",
"hence increasing relevance and reducing hallucinations.\n",
"\n",
"We leverage the [`langchain`](https://github.com/langchain-ai/langchain) library in this implementation, specifically [Custom Agent Configuration](https://langchain-langchain.vercel.app/docs/modules/agents/how_to/custom_agent_with_tool_retrieval) and are inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) architecture ."
"Furthermore, we show how our AI Sales Agent can **generate sales** by integration with the AI Agent Highway called [Mindware](https://www.mindware.co/). In practice, this allows the agent to autonomously generate a payment link for your customers **to pay for your products via Stripe**.\n",
"\n",
"We leverage the [`langchain`](https://github.com/hwchase17/langchain) library in this implementation, specifically [Custom Agent Configuration](https://langchain-langchain.vercel.app/docs/modules/agents/how_to/custom_agent_with_tool_retrieval) and are inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) architecture ."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@ -38,9 +42,10 @@
"import os\n",
"import re\n",
"\n",
"# import your OpenAI key\n",
"OPENAI_API_KEY = \"sk-xx\"\n",
"os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY\n",
"# make sure you have .env file saved locally with your API keys\n",
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()\n",
"\n",
"from typing import Any, Callable, Dict, List, Union\n",
"\n",
@ -49,27 +54,18 @@
"from langchain.agents.conversational.prompt import FORMAT_INSTRUCTIONS\n",
"from langchain.chains import LLMChain, RetrievalQA\n",
"from langchain.chains.base import Chain\n",
"from langchain.llms import BaseLLM\n",
"from langchain.prompts import PromptTemplate\n",
"from langchain.prompts.base import StringPromptTemplate\n",
"from langchain_community.llms import BaseLLM\n",
"from langchain_community.vectorstores import Chroma\n",
"from langchain_core.agents import AgentAction, AgentFinish\n",
"from langchain_openai import ChatOpenAI, OpenAI, OpenAIEmbeddings\n",
"from langchain_text_splitters import CharacterTextSplitter\n",
"from langchain.schema import AgentAction, AgentFinish\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Chroma\n",
"from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
"from pydantic import BaseModel, Field"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# install additional dependencies\n",
"# ! pip install chromadb openai tiktoken"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@ -77,19 +73,21 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"1. Seed the SalesGPT agent\n",
"2. Run Sales Agent to decide what to do:\n",
"\n",
" a) Use a tool, such as look up Product Information in a Knowledge Base\n",
" a) Use a tool, such as look up Product Information in a Knowledge Base or Generate a Payment Link\n",
" \n",
" b) Output a response to a user \n",
"3. Run Sales Stage Recognition Agent to recognize which stage is the sales agent at and adjust their behaviour accordingly."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@ -98,15 +96,17 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Architecture diagram\n",
"\n",
"<img src=\"https://singularity-assets-public.s3.amazonaws.com/new_flow.png\" width=\"800\" height=\"440\"/>\n"
"<img src=\"https://demo-bucket-45.s3.amazonaws.com/new_flow2.png\" width=\"800\" height=\"440\">\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@ -131,7 +131,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@ -149,7 +149,7 @@
" {conversation_history}\n",
" ===\n",
"\n",
" Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting only from the following options:\n",
" Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting ony from the following options:\n",
" 1. Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\n",
" 2. Qualification: Qualify the prospect by confirming if they are the right person to talk to regarding your product/service. Ensure that they have the authority to make purchasing decisions.\n",
" 3. Value proposition: Briefly explain how your product/service can benefit the prospect. Focus on the unique selling points and value proposition of your product/service that sets it apart from competitors.\n",
@ -171,7 +171,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@ -223,7 +223,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
@ -240,13 +240,17 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# test the intermediate chains\n",
"verbose = True\n",
"llm = ChatOpenAI(temperature=0.9)\n",
"llm = ChatOpenAI(\n",
" model=\"gpt-4-turbo-preview\",\n",
" temperature=0.9,\n",
" openai_api_key=os.getenv(\"OPENAI_API_KEY\"),\n",
")\n",
"\n",
"stage_analyzer_chain = StageAnalyzerChain.from_llm(llm, verbose=verbose)\n",
"\n",
@ -257,7 +261,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 6,
"metadata": {},
"outputs": [
{
@ -276,7 +280,7 @@
" \n",
" ===\n",
"\n",
" Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting only from the following options:\n",
" Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting ony from the following options:\n",
" 1. Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\n",
" 2. Qualification: Qualify the prospect by confirming if they are the right person to talk to regarding your product/service. Ensure that they have the authority to make purchasing decisions.\n",
" 3. Value proposition: Briefly explain how your product/service can benefit the prospect. Focus on the unique selling points and value proposition of your product/service that sets it apart from competitors.\n",
@ -296,21 +300,21 @@
{
"data": {
"text/plain": [
"'1'"
"{'conversation_history': '', 'text': '1'}"
]
},
"execution_count": 7,
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"stage_analyzer_chain.run(conversation_history=\"\")"
"stage_analyzer_chain.invoke({\"conversation_history\": \"\"})"
]
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"outputs": [
{
@ -352,32 +356,44 @@
{
"data": {
"text/plain": [
"\"I'm doing great, thank you for asking! As a Business Development Representative at Sleep Haven, I wanted to reach out to see if you are looking to achieve a better night's sleep. We provide premium mattresses that offer the most comfortable and supportive sleeping experience possible. Are you interested in exploring our sleep solutions? <END_OF_TURN>\""
"{'salesperson_name': 'Ted Lasso',\n",
" 'salesperson_role': 'Business Development Representative',\n",
" 'company_name': 'Sleep Haven',\n",
" 'company_business': 'Sleep Haven is a premium mattress company that provides customers with the most comfortable and supportive sleeping experience possible. We offer a range of high-quality mattresses, pillows, and bedding accessories that are designed to meet the unique needs of our customers.',\n",
" 'company_values': \"Our mission at Sleep Haven is to help people achieve a better night's sleep by providing them with the best possible sleep solutions. We believe that quality sleep is essential to overall health and well-being, and we are committed to helping our customers achieve optimal sleep by offering exceptional products and customer service.\",\n",
" 'conversation_purpose': 'find out whether they are looking to achieve better sleep via buying a premier mattress.',\n",
" 'conversation_history': 'Hello, this is Ted Lasso from Sleep Haven. How are you doing today? <END_OF_TURN>\\nUser: I am well, howe are you?<END_OF_TURN>',\n",
" 'conversation_type': 'call',\n",
" 'conversation_stage': 'Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional. Your greeting should be welcoming. Always clarify in your greeting the reason why you are contacting the prospect.',\n",
" 'text': \"I'm doing well, thank you for asking. The reason I'm calling is to discuss how Sleep Haven can help enhance your sleep quality with our premium mattresses. Are you currently looking for ways to achieve a better night's sleep? <END_OF_TURN>\"}"
]
},
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sales_conversation_utterance_chain.run(\n",
" salesperson_name=\"Ted Lasso\",\n",
" salesperson_role=\"Business Development Representative\",\n",
" company_name=\"Sleep Haven\",\n",
" company_business=\"Sleep Haven is a premium mattress company that provides customers with the most comfortable and supportive sleeping experience possible. We offer a range of high-quality mattresses, pillows, and bedding accessories that are designed to meet the unique needs of our customers.\",\n",
" company_values=\"Our mission at Sleep Haven is to help people achieve a better night's sleep by providing them with the best possible sleep solutions. We believe that quality sleep is essential to overall health and well-being, and we are committed to helping our customers achieve optimal sleep by offering exceptional products and customer service.\",\n",
" conversation_purpose=\"find out whether they are looking to achieve better sleep via buying a premier mattress.\",\n",
" conversation_history=\"Hello, this is Ted Lasso from Sleep Haven. How are you doing today? <END_OF_TURN>\\nUser: I am well, howe are you?<END_OF_TURN>\",\n",
" conversation_type=\"call\",\n",
" conversation_stage=conversation_stages.get(\n",
" \"1\",\n",
" \"Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\",\n",
" ),\n",
"sales_conversation_utterance_chain.invoke(\n",
" {\n",
" \"salesperson_name\": \"Ted Lasso\",\n",
" \"salesperson_role\": \"Business Development Representative\",\n",
" \"company_name\": \"Sleep Haven\",\n",
" \"company_business\": \"Sleep Haven is a premium mattress company that provides customers with the most comfortable and supportive sleeping experience possible. We offer a range of high-quality mattresses, pillows, and bedding accessories that are designed to meet the unique needs of our customers.\",\n",
" \"company_values\": \"Our mission at Sleep Haven is to help people achieve a better night's sleep by providing them with the best possible sleep solutions. We believe that quality sleep is essential to overall health and well-being, and we are committed to helping our customers achieve optimal sleep by offering exceptional products and customer service.\",\n",
" \"conversation_purpose\": \"find out whether they are looking to achieve better sleep via buying a premier mattress.\",\n",
" \"conversation_history\": \"Hello, this is Ted Lasso from Sleep Haven. How are you doing today? <END_OF_TURN>\\nUser: I am well, howe are you?<END_OF_TURN>\",\n",
" \"conversation_type\": \"call\",\n",
" \"conversation_stage\": conversation_stages.get(\n",
" \"1\",\n",
" \"Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\",\n",
" ),\n",
" }\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@ -385,6 +401,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@ -395,7 +412,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
@ -429,7 +446,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
@ -445,7 +462,7 @@
" text_splitter = CharacterTextSplitter(chunk_size=10, chunk_overlap=0)\n",
" texts = text_splitter.split_text(product_catalog)\n",
"\n",
" llm = OpenAI(temperature=0)\n",
" llm = ChatOpenAI(temperature=0)\n",
" embeddings = OpenAIEmbeddings()\n",
" docsearch = Chroma.from_texts(\n",
" texts, embeddings, collection_name=\"product-knowledge-base\"\n",
@ -454,29 +471,12 @@
" knowledge_base = RetrievalQA.from_chain_type(\n",
" llm=llm, chain_type=\"stuff\", retriever=docsearch.as_retriever()\n",
" )\n",
" return knowledge_base\n",
"\n",
"\n",
"def get_tools(product_catalog):\n",
" # query to get_tools can be used to be embedded and relevant tools found\n",
" # see here: https://langchain-langchain.vercel.app/docs/use_cases/agents/custom_agent_with_plugin_retrieval#tool-retriever\n",
"\n",
" # we only use one tool for now, but this is highly extensible!\n",
" knowledge_base = setup_knowledge_base(product_catalog)\n",
" tools = [\n",
" Tool(\n",
" name=\"ProductSearch\",\n",
" func=knowledge_base.run,\n",
" description=\"useful for when you need to answer questions about product information\",\n",
" )\n",
" ]\n",
"\n",
" return tools"
" return knowledge_base"
]
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 10,
"metadata": {},
"outputs": [
{
@ -485,16 +485,18 @@
"text": [
"Created a chunk of size 940, which is longer than the specified 10\n",
"Created a chunk of size 844, which is longer than the specified 10\n",
"Created a chunk of size 837, which is longer than the specified 10\n"
"Created a chunk of size 837, which is longer than the specified 10\n",
"/Users/filipmichalsky/Odyssey/sales_bot/SalesGPT/env/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `run` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",
" warn_deprecated(\n"
]
},
{
"data": {
"text/plain": [
"' We have four products available: the Classic Harmony Spring Mattress, the Plush Serenity Bamboo Mattress, the Luxury Cloud-Comfort Memory Foam Mattress, and the EcoGreen Hybrid Latex Mattress. Each product is available in different sizes, with the Classic Harmony Spring Mattress available in Queen and King sizes, the Plush Serenity Bamboo Mattress available in King size, the Luxury Cloud-Comfort Memory Foam Mattress available in Twin, Queen, and King sizes, and the EcoGreen Hybrid Latex Mattress available in Twin and Full sizes.'"
"'The Sleep Haven products available are:\\n\\n1. Luxury Cloud-Comfort Memory Foam Mattress\\n2. Classic Harmony Spring Mattress\\n3. EcoGreen Hybrid Latex Mattress\\n4. Plush Serenity Bamboo Mattress\\n\\nEach product has its unique features and price point.'"
]
},
"execution_count": 11,
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@ -508,12 +510,199 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"### Set up the SalesGPT Controller with the Sales Agent and Stage Analyzer and a Knowledge Base"
"### Payment gateway"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In order to set up your AI agent to use a payment gateway to generate payment links for your users you need two things:\n",
"\n",
"1. Sign up for a Stripe account and obtain a STRIPE API KEY\n",
"2. Create products you would like to sell in the Stripe UI. Then follow out example of `example_product_price_id_mapping.json`\n",
"to feed the product name to price_id mapping which allows you to generate the payment links."
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"\n",
"from litellm import completion\n",
"\n",
"# set GPT model env variable\n",
"os.environ[\"GPT_MODEL\"] = \"gpt-4-turbo-preview\"\n",
"\n",
"product_price_id_mapping = {\n",
" \"ai-consulting-services\": \"price_1Ow8ofB795AYY8p1goWGZi6m\",\n",
" \"Luxury Cloud-Comfort Memory Foam Mattress\": \"price_1Owv99B795AYY8p1mjtbKyxP\",\n",
" \"Classic Harmony Spring Mattress\": \"price_1Owv9qB795AYY8p1tPcxCM6T\",\n",
" \"EcoGreen Hybrid Latex Mattress\": \"price_1OwvLDB795AYY8p1YBAMBcbi\",\n",
" \"Plush Serenity Bamboo Mattress\": \"price_1OwvMQB795AYY8p1hJN2uS3S\",\n",
"}\n",
"with open(\"example_product_price_id_mapping.json\", \"w\") as f:\n",
" json.dump(product_price_id_mapping, f)\n",
"\n",
"\n",
"def get_product_id_from_query(query, product_price_id_mapping_path):\n",
" # Load product_price_id_mapping from a JSON file\n",
" with open(product_price_id_mapping_path, \"r\") as f:\n",
" product_price_id_mapping = json.load(f)\n",
"\n",
" # Serialize the product_price_id_mapping to a JSON string for inclusion in the prompt\n",
" product_price_id_mapping_json_str = json.dumps(product_price_id_mapping)\n",
"\n",
" # Dynamically create the enum list from product_price_id_mapping keys\n",
" enum_list = list(product_price_id_mapping.values()) + [\n",
" \"No relevant product id found\"\n",
" ]\n",
" enum_list_str = json.dumps(enum_list)\n",
"\n",
" prompt = f\"\"\"\n",
" You are an expert data scientist and you are working on a project to recommend products to customers based on their needs.\n",
" Given the following query:\n",
" {query}\n",
" and the following product price id mapping:\n",
" {product_price_id_mapping_json_str}\n",
" return the price id that is most relevant to the query.\n",
" ONLY return the price id, no other text. If no relevant price id is found, return 'No relevant price id found'.\n",
" Your output will follow this schema:\n",
" {{\n",
" \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n",
" \"title\": \"Price ID Response\",\n",
" \"type\": \"object\",\n",
" \"properties\": {{\n",
" \"price_id\": {{\n",
" \"type\": \"string\",\n",
" \"enum\": {enum_list_str}\n",
" }}\n",
" }},\n",
" \"required\": [\"price_id\"]\n",
" }}\n",
" Return a valid directly parsable json, dont return in it within a code snippet or add any kind of explanation!!\n",
" \"\"\"\n",
" prompt += \"{\"\n",
" response = completion(\n",
" model=os.getenv(\"GPT_MODEL\", \"gpt-3.5-turbo-1106\"),\n",
" messages=[{\"content\": prompt, \"role\": \"user\"}],\n",
" max_tokens=1000,\n",
" temperature=0,\n",
" )\n",
"\n",
" product_id = response.choices[0].message.content.strip()\n",
" return product_id"
]
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"\n",
"import requests\n",
"\n",
"\n",
"def generate_stripe_payment_link(query: str) -> str:\n",
" \"\"\"Generate a stripe payment link for a customer based on a single query string.\"\"\"\n",
"\n",
" # example testing payment gateway url\n",
" PAYMENT_GATEWAY_URL = os.getenv(\n",
" \"PAYMENT_GATEWAY_URL\", \"https://agent-payments-gateway.vercel.app/payment\"\n",
" )\n",
" PRODUCT_PRICE_MAPPING = \"example_product_price_id_mapping.json\"\n",
"\n",
" # use LLM to get the price_id from query\n",
" price_id = get_product_id_from_query(query, PRODUCT_PRICE_MAPPING)\n",
" price_id = json.loads(price_id)\n",
" payload = json.dumps(\n",
" {\"prompt\": query, **price_id, \"stripe_key\": os.getenv(\"STRIPE_API_KEY\")}\n",
" )\n",
" headers = {\n",
" \"Content-Type\": \"application/json\",\n",
" }\n",
"\n",
" response = requests.request(\n",
" \"POST\", PAYMENT_GATEWAY_URL, headers=headers, data=payload\n",
" )\n",
" return response.text"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'{\"response\":\"https://buy.stripe.com/test_6oEbLS8JB1F9bv229d\"}'"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"generate_stripe_payment_link(\n",
" query=\"Please generate a payment link for John Doe to buy two mattresses - the Classic Harmony Spring Mattress\"\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup agent tools"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"def get_tools(product_catalog):\n",
" # query to get_tools can be used to be embedded and relevant tools found\n",
" # see here: https://langchain-langchain.vercel.app/docs/use_cases/agents/custom_agent_with_plugin_retrieval#tool-retriever\n",
"\n",
" # we only use one tool for now, but this is highly extensible!\n",
" knowledge_base = setup_knowledge_base(product_catalog)\n",
" tools = [\n",
" Tool(\n",
" name=\"ProductSearch\",\n",
" func=knowledge_base.run,\n",
" description=\"useful for when you need to answer questions about product information or services offered, availability and their costs.\",\n",
" ),\n",
" Tool(\n",
" name=\"GeneratePaymentLink\",\n",
" func=generate_stripe_payment_link,\n",
" description=\"useful to close a transaction with a customer. You need to include product name and quantity and customer name in the query input.\",\n",
" ),\n",
" ]\n",
"\n",
" return tools"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Set up the SalesGPT Controller with the Sales Agent and Stage Analyzer\n",
"\n",
"#### The Agent has access to a Knowledge Base and can autonomously sell your products via Stripe"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
@ -563,19 +752,11 @@
" print(\"TEXT\")\n",
" print(text)\n",
" print(\"-------\")\n",
" if f\"{self.ai_prefix}:\" in text:\n",
" return AgentFinish(\n",
" {\"output\": text.split(f\"{self.ai_prefix}:\")[-1].strip()}, text\n",
" )\n",
" regex = r\"Action: (.*?)[\\n]*Action Input: (.*)\"\n",
" match = re.search(regex, text)\n",
" if not match:\n",
" ## TODO - this is not entirely reliable, sometimes results in an error.\n",
" return AgentFinish(\n",
" {\n",
" \"output\": \"I apologize, I was unable to find the answer to your question. Is there anything else I can help with?\"\n",
" },\n",
" text,\n",
" {\"output\": text.split(f\"{self.ai_prefix}:\")[-1].strip()}, text\n",
" )\n",
" # raise OutputParserException(f\"Could not parse LLM output: `{text}`\")\n",
" action = match.group(1)\n",
@ -589,7 +770,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
@ -647,18 +828,18 @@
"Previous conversation history:\n",
"{conversation_history}\n",
"\n",
"{salesperson_name}:\n",
"Thought:\n",
"{agent_scratchpad}\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"class SalesGPT(Chain, BaseModel):\n",
"class SalesGPT(Chain):\n",
" \"\"\"Controller model for the Sales Agent.\"\"\"\n",
"\n",
" conversation_history: List[str] = []\n",
@ -804,7 +985,9 @@
"\n",
" # WARNING: this output parser is NOT reliable yet\n",
" ## It makes assumptions about output from LLM which can break and throw an error\n",
" output_parser = SalesConvoOutputParser(ai_prefix=kwargs[\"salesperson_name\"])\n",
" output_parser = SalesConvoOutputParser(\n",
" ai_prefix=kwargs[\"salesperson_name\"], verbose=verbose\n",
" )\n",
"\n",
" sales_agent_with_tools = LLMSingleActionAgent(\n",
" llm_chain=llm_chain,\n",
@ -828,6 +1011,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@ -835,6 +1019,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@ -843,7 +1028,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
@ -880,6 +1065,7 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@ -888,7 +1074,7 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": 22,
"metadata": {},
"outputs": [
{
@ -897,7 +1083,9 @@
"text": [
"Created a chunk of size 940, which is longer than the specified 10\n",
"Created a chunk of size 844, which is longer than the specified 10\n",
"Created a chunk of size 837, which is longer than the specified 10\n"
"Created a chunk of size 837, which is longer than the specified 10\n",
"/Users/filipmichalsky/Odyssey/sales_bot/SalesGPT/env/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The class `langchain.agents.agent.LLMSingleActionAgent` was deprecated in langchain 0.1.0 and will be removed in 0.2.0. Use Use new agent constructor methods like create_react_agent, create_json_agent, create_structured_chat_agent, etc. instead.\n",
" warn_deprecated(\n"
]
}
],
@ -907,7 +1095,7 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
@ -917,7 +1105,7 @@
},
{
"cell_type": "code",
"execution_count": 18,
"execution_count": 22,
"metadata": {},
"outputs": [
{
@ -934,14 +1122,14 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Ted Lasso: Hello, this is Ted Lasso from Sleep Haven. How are you doing today?\n"
"Ted Lasso: Good day! This is Ted Lasso from Sleep Haven. How are you doing today?\n"
]
}
],
@ -951,18 +1139,18 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"sales_agent.human_step(\n",
" \"I am well, how are you? I would like to learn more about your mattresses.\"\n",
" \"I am well, how are you? I would like to learn more about your services.\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 21,
"execution_count": 25,
"metadata": {},
"outputs": [
{
@ -979,14 +1167,14 @@
},
{
"cell_type": "code",
"execution_count": 22,
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Ted Lasso: I'm glad to hear that you're doing well! As for our mattresses, at Sleep Haven, we provide customers with the most comfortable and supportive sleeping experience possible. Our high-quality mattresses are designed to meet the unique needs of our customers. Can I ask what specifically you'd like to learn more about? \n"
"Ted Lasso: I'm doing great, thank you for asking! I'm glad to hear you're interested. Sleep Haven is a premium mattress company, and we're all about offering the best sleep solutions, including top-notch mattresses, pillows, and bedding accessories. Our mission is to help you achieve a better night's sleep. May I know if you're looking to enhance your sleep experience with a new mattress or bedding accessories? \n"
]
}
],
@ -996,16 +1184,18 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"sales_agent.human_step(\"Yes, what materials are you mattresses made from?\")"
"sales_agent.human_step(\n",
" \"Yes, I would like to improve my sleep. Can you tell me more about your products?\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 24,
"execution_count": 28,
"metadata": {},
"outputs": [
{
@ -1022,14 +1212,14 @@
},
{
"cell_type": "code",
"execution_count": 25,
"execution_count": 29,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Ted Lasso: Our mattresses are made from a variety of materials, depending on the model. We have the EcoGreen Hybrid Latex Mattress, which is made from 100% natural latex harvested from eco-friendly plantations. The Plush Serenity Bamboo Mattress features a layer of plush, adaptive foam and a base of high-resilience support foam, with a bamboo-infused top layer. The Luxury Cloud-Comfort Memory Foam Mattress has an innovative, temperature-sensitive memory foam layer and a high-density foam base with cooling gel-infused particles. Finally, the Classic Harmony Spring Mattress has a robust inner spring construction and layers of plush padding, with a quilted top layer and a natural cotton cover. Is there anything specific you'd like to know about these materials?\n"
"Ted Lasso: Absolutely, I'd be happy to share more about our products. At Sleep Haven, we offer a variety of high-quality mattresses designed to cater to different sleeping preferences and needs. Whether you're looking for memory foam's comfort, the support of hybrid mattresses, or the breathability of natural latex, we have options for everyone. Our pillows and bedding accessories are similarly curated to enhance your sleep quality. Every product is built with the aim of helping you achieve the restful night's sleep you deserve. What specific features are you looking for in a mattress? \n"
]
}
],
@ -1039,25 +1229,23 @@
},
{
"cell_type": "code",
"execution_count": 26,
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"sales_agent.human_step(\n",
" \"Yes, I am looking for a queen sized mattress. Do you have any mattresses in queen size?\"\n",
")"
"sales_agent.human_step(\"What mattresses do you have and how much do they cost?\")"
]
},
{
"cell_type": "code",
"execution_count": 27,
"execution_count": 32,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Conversation Stage: Needs analysis: Ask open-ended questions to uncover the prospect's needs and pain points. Listen carefully to their responses and take notes.\n"
"Conversation Stage: Solution presentation: Based on the prospect's needs, present your product/service as the solution that can address their pain points.\n"
]
}
],
@ -1067,14 +1255,14 @@
},
{
"cell_type": "code",
"execution_count": 28,
"execution_count": 33,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Ted Lasso: Yes, we do have queen-sized mattresses available. We offer the Luxury Cloud-Comfort Memory Foam Mattress and the Classic Harmony Spring Mattress in queen size. Both mattresses provide exceptional comfort and support. Is there anything specific you would like to know about these options?\n"
"Ted Lasso: We offer two primary types of mattresses at Sleep Haven. The first is our Luxury Cloud-Comfort Memory Foam Mattress, which is priced at $999 and comes in Twin, Queen, and King sizes. The second is our Classic Harmony Spring Mattress, priced at $1,299, available in Queen and King sizes. Both are designed to provide exceptional comfort and support for a better night's sleep. Which type of mattress would you be interested in learning more about? \n"
]
}
],
@ -1084,23 +1272,25 @@
},
{
"cell_type": "code",
"execution_count": 29,
"execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
"sales_agent.human_step(\"Yea, compare and contrast those two options, please.\")"
"sales_agent.human_step(\n",
" \"Okay.I would like to order two Memory Foam mattresses in Twin size please.\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 30,
"execution_count": 35,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Conversation Stage: Solution presentation: Based on the prospect's needs, present your product/service as the solution that can address their pain points.\n"
"Conversation Stage: Close: Ask for the sale by proposing a next step. This could be a demo, a trial or a meeting with decision-makers. Ensure to summarize what has been discussed and reiterate the benefits.\n"
]
}
],
@ -1110,14 +1300,14 @@
},
{
"cell_type": "code",
"execution_count": 31,
"execution_count": 36,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Ted Lasso: The Luxury Cloud-Comfort Memory Foam Mattress is priced at $999 and is available in Twin, Queen, and King sizes. It features an innovative, temperature-sensitive memory foam layer and a high-density foam base. On the other hand, the Classic Harmony Spring Mattress is priced at $1,299 and is available in Queen and King sizes. It features a robust inner spring construction and layers of plush padding. Both mattresses provide exceptional comfort and support, but the Classic Harmony Spring Mattress may be a better option if you prefer the traditional feel of an inner spring mattress. Do you have any other questions about these options?\n"
"Ted Lasso: Fantastic choice! You're on your way to a better night's sleep with our Luxury Cloud-Comfort Memory Foam Mattresses. I've generated a payment link for two Twin size mattresses for you. Here is the link to complete your purchase: https://buy.stripe.com/test_6oEg28e3V97BdDabJn. Is there anything else I can assist you with today? \n"
]
}
],
@ -1127,14 +1317,21 @@
},
{
"cell_type": "code",
"execution_count": 32,
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"sales_agent.human_step(\n",
" \"Great, thanks, that's it. I will talk to my wife and call back if she is onboard. Have a good day!\"\n",
" \"Great, thanks! I will discuss with my wife and will buy it if she is onboard. Have a good day!\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@ -1153,9 +1350,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.3"
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}

Loading…
Cancel
Save