my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: Memory-Powered Support Agent
#3	description: "Build a support assistant that keeps past tickets and resolutions at its fingertips."
#4	---
#5
#6
#7	You can create a personalized Customer Support AI Agent using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
#8
#9	## Overview
#10
#11	The Customer Support AI Agent leverages Mem0 to retain information across interactions, enabling a personalized and efficient support experience.
#12
#13	## Setup
#14
#15	Install the necessary packages using pip:
#16
#17	```bash
#18	pip install openai mem0ai
#19	```
#20
#21	## Full Code Example
#22
#23	Below is the simplified code to create and interact with a Customer Support AI Agent using Mem0:
#24
#25	```python
#26	import os
#27	from openai import OpenAI
#28	from mem0 import Memory
#29
#30	# Set the OpenAI API key
#31	os.environ['OPENAI_API_KEY'] = 'sk-xxx'
#32
#33	class CustomerSupportAIAgent:
#34	def __init__(self):
#35	"""
#36	Initialize the CustomerSupportAIAgent with memory configuration and OpenAI client.
#37	"""
#38	config = {
#39	"vector_store": {
#40	"provider": "qdrant",
#41	"config": {
#42	"host": "localhost",
#43	"port": 6333,
#44	}
#45	},
#46	}
#47	self.memory = Memory.from_config(config)
#48	self.client = OpenAI()
#49	self.app_id = "customer-support"
#50
#51	def handle_query(self, query, user_id=None):
#52	"""
#53	Handle a customer query and store the relevant information in memory.
#54
#55	:param query: The customer query to handle.
#56	:param user_id: Optional user ID to associate with the memory.
#57	"""
#58	# Start a streaming chat completion request to the AI
#59	stream = self.client.chat.completions.create(
#60	model="gpt-4",
#61	stream=True,
#62	messages=[
#63	{"role": "system", "content": "You are a customer support AI agent."},
#64	{"role": "user", "content": query}
#65	]
#66	)
#67	# Store the query in memory
#68	self.memory.add(query, user_id=user_id, metadata={"app_id": self.app_id})
#69
#70	# Print the response from the AI in real-time
#71	for chunk in stream:
#72	if chunk.choices[0].delta.content is not None:
#73	print(chunk.choices[0].delta.content, end="")
#74
#75	def get_memories(self, user_id=None):
#76	"""
#77	Retrieve all memories associated with the given customer ID.
#78
#79	:param user_id: Optional user ID to filter memories.
#80	:return: List of memories.
#81	"""
#82	return self.memory.get_all(user_id=user_id)
#83
#84	# Instantiate the CustomerSupportAIAgent
#85	support_agent = CustomerSupportAIAgent()
#86
#87	# Define a customer ID
#88	customer_id = "jane_doe"
#89
#90	# Handle a customer query
#91	support_agent.handle_query("I need help with my recent order. It hasn't arrived yet.", user_id=customer_id)
#92	```
#93
#94	### Fetching Memories
#95
#96	You can fetch all the memories at any point in time using the following code:
#97
#98	```python
#99	memories = support_agent.get_memories(user_id=customer_id)
#100	for m in memories['results']:
#101	print(m['memory'])
#102	```
#103
#104	### Key Points
#105
#106	- Initialization: The CustomerSupportAIAgent class is initialized with the necessary memory configuration and OpenAI client setup.
#107	- Handling Queries: The handle_query method sends a query to the AI and stores the relevant information in memory.
#108	- Retrieving Memories: The get_memories method fetches all stored memories associated with a customer.
#109
#110	### Conclusion
#111
#112	As the conversation progresses, Mem0's memory automatically updates based on the interactions, providing a continuously improving personalized support experience.
#113
#114	---
#115
#116	<CardGroup cols={2}>
#117	<Card title="Build a Mem0 Companion" icon="users" href="/cookbooks/essentials/building-ai-companion">
#118	Master the foundational patterns for building memory-powered assistants.
#119	</Card>
#120	<Card title="Email Automation with Mem0" icon="envelope" href="/cookbooks/operations/email-automation">
#121	Extend support capabilities with intelligent email processing and routing.
#122	</Card>
#123	</CardGroup>
#124

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public