my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: CrewAI
#3	---
#4
#5	Build an AI system that combines CrewAI's agent-based architecture with Mem0's memory capabilities. This integration enables persistent memory across agent interactions and personalized task execution based on user history.
#6
#7	## Overview
#8
#9	In this guide, we'll create a CrewAI agent that:
#10	1. Uses CrewAI to manage AI agents and tasks
#11	2. Leverages Mem0 to store and retrieve conversation history
#12	3. Creates personalized experiences based on stored user preferences
#13
#14	## Setup and Configuration
#15
#16	Install necessary libraries:
#17
#18	```bash
#19	pip install crewai crewai-tools mem0ai
#20	```
#21
#22	Import required modules and set up configurations:
#23
#24	<Note>Remember to get your API keys from [Mem0 Platform](https://app.mem0.ai), [OpenAI](https://platform.openai.com) and [Serper Dev](https://serper.dev) for search capabilities.</Note>
#25
#26	```python
#27	import os
#28	from mem0 import MemoryClient
#29	from crewai import Agent, Task, Crew, Process
#30	from crewai_tools import SerperDevTool
#31
#32	# Configuration
#33	os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
#34	os.environ["OPENAI_API_KEY"] = "your-openai-api-key"
#35	os.environ["SERPER_API_KEY"] = "your-serper-api-key"
#36
#37	# Initialize Mem0 client
#38	client = MemoryClient()
#39	```
#40
#41	## Store User Preferences
#42
#43	Set up initial conversation and preferences storage:
#44
#45	```python
#46	def store_user_preferences(user_id: str, conversation: list):
#47	"""Store user preferences from conversation history"""
#48	client.add(conversation, user_id=user_id)
#49
#50	# Example conversation storage
#51	messages = [
#52	{
#53	"role": "user",
#54	"content": "Hi there! I'm planning a vacation and could use some advice.",
#55	},
#56	{
#57	"role": "assistant",
#58	"content": "Hello! I'd be happy to help with your vacation planning. What kind of destination do you prefer?",
#59	},
#60	{"role": "user", "content": "I am more of a beach person than a mountain person."},
#61	{
#62	"role": "assistant",
#63	"content": "That's interesting. Do you like hotels or Airbnb?",
#64	},
#65	{"role": "user", "content": "I like Airbnb more."},
#66	]
#67
#68	store_user_preferences("crew_user_1", messages)
#69	```
#70
#71	## Create CrewAI Agent
#72
#73	Define an agent with memory capabilities:
#74
#75	```python
#76	def create_travel_agent():
#77	"""Create a travel planning agent with search capabilities"""
#78	search_tool = SerperDevTool()
#79
#80	return Agent(
#81	role="Personalized Travel Planner Agent",
#82	goal="Plan personalized travel itineraries",
#83	backstory="""You are a seasoned travel planner, known for your meticulous attention to detail.""",
#84	allow_delegation=False,
#85	memory=True,
#86	tools=[search_tool],
#87	)
#88	```
#89
#90	## Define Tasks
#91
#92	Create tasks for your agent:
#93
#94	```python
#95	def create_planning_task(agent, destination: str):
#96	"""Create a travel planning task"""
#97	return Task(
#98	description=f"""Find places to live, eat, and visit in {destination}.""",
#99	expected_output=f"A detailed list of places to live, eat, and visit in {destination}.",
#100	agent=agent,
#101	)
#102	```
#103
#104	## Set Up Crew
#105
#106	Configure the crew with memory integration:
#107
#108	```python
#109	def setup_crew(agents: list, tasks: list):
#110	"""Set up a crew with Mem0 memory integration"""
#111	return Crew(
#112	agents=agents,
#113	tasks=tasks,
#114	process=Process.sequential,
#115	memory=True,
#116	memory_config={
#117	"provider": "mem0",
#118	"config": {"user_id": "crew_user_1"},
#119	}
#120	)
#121	```
#122
#123	## Main Execution Function
#124
#125	Implement the main function to run the travel planning system:
#126
#127	```python
#128	def plan_trip(destination: str, user_id: str):
#129	# Create agent
#130	travel_agent = create_travel_agent()
#131
#132	# Create task
#133	planning_task = create_planning_task(travel_agent, destination)
#134
#135	# Setup crew
#136	crew = setup_crew([travel_agent], [planning_task])
#137
#138	# Execute and return results
#139	return crew.kickoff()
#140
#141	# Example usage
#142	if __name__ == "__main__":
#143	result = plan_trip("San Francisco", "crew_user_1")
#144	print(result)
#145	```
#146
#147	## Key Features
#148
#149	1. Persistent Memory: Uses Mem0 to maintain user preferences and conversation history
#150	2. Agent-Based Architecture: Leverages CrewAI's agent system for task execution
#151	3. Search Integration: Includes SerperDev tool for real-world information retrieval
#152	4. Personalization: Utilizes stored preferences for tailored recommendations
#153
#154	## Benefits
#155
#156	1. Persistent Context & Memory: Maintains user preferences and interaction history across sessions
#157	2. Flexible & Scalable Design: Easily extendable with new agents, tasks, and capabilities
#158
#159	## Conclusion
#160
#161	By combining CrewAI with Mem0, you can create sophisticated AI systems that maintain context and provide personalized experiences while leveraging the power of autonomous agents.
#162
#163	<CardGroup cols={2}>
#164	<Card title="AutoGen Integration" icon="users" href="/integrations/autogen">
#165	Build multi-agent systems with AutoGen and Mem0
#166	</Card>
#167	<Card title="LangGraph Integration" icon="diagram-project" href="/integrations/langgraph">
#168	Create stateful agent workflows with memory
#169	</Card>
#170	</CardGroup>
#171
#172

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public