my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: AutoGen
#3	---
#4
#5	Build conversational AI agents with memory capabilities. This integration combines AutoGen for creating AI agents with Mem0 for memory management, enabling context-aware and personalized interactions.
#6
#7	## Overview
#8
#9	This guide demonstrates creating a conversational AI system with memory. We'll build a customer service bot that can recall previous interactions and provide personalized responses.
#10
#11	## Setup and Configuration
#12
#13	Install necessary libraries:
#14
#15	```bash
#16	pip install autogen mem0ai openai python-dotenv
#17	```
#18
#19	First, we'll import the necessary libraries and set up our configurations.
#20
#21	<Note>Remember to get the Mem0 API key from [Mem0 Platform](https://app.mem0.ai).</Note>
#22
#23	```python
#24	import os
#25	from autogen import ConversableAgent
#26	from mem0 import MemoryClient
#27	from openai import OpenAI
#28	from dotenv import load_dotenv
#29
#30	load_dotenv()
#31
#32	# Configuration
#33	# OPENAI_API_KEY = 'sk-xxx' # Replace with your actual OpenAI API key
#34	# MEM0_API_KEY = 'your-mem0-key' # Replace with your actual Mem0 API key from https://app.mem0.ai
#35	USER_ID = "alice"
#36
#37	# Set up OpenAI API key
#38	OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY')
#39	# os.environ['MEM0_API_KEY'] = MEM0_API_KEY
#40
#41	# Initialize Mem0 and AutoGen agents
#42	memory_client = MemoryClient()
#43	agent = ConversableAgent(
#44	"chatbot",
#45	llm_config={"config_list": [{"model": "gpt-4", "api_key": OPENAI_API_KEY}]},
#46	code_execution_config=False,
#47	human_input_mode="NEVER",
#48	)
#49	```
#50
#51	## Storing Conversations in Memory
#52
#53	Add conversation history to Mem0 for future reference:
#54
#55	```python
#56	conversation = [
#57	{"role": "assistant", "content": "Hi, I'm Best Buy's chatbot! How can I help you?"},
#58	{"role": "user", "content": "I'm seeing horizontal lines on my TV."},
#59	{"role": "assistant", "content": "I'm sorry to hear that. Can you provide your TV model?"},
#60	{"role": "user", "content": "It's a Sony - 77\" Class BRAVIA XR A80K OLED 4K UHD Smart Google TV"},
#61	{"role": "assistant", "content": "Thank you for the information. Let's troubleshoot this issue..."}
#62	]
#63
#64	memory_client.add(messages=conversation, user_id=USER_ID)
#65	print("Conversation added to memory.")
#66	```
#67
#68	## Retrieving and Using Memory
#69
#70	Create a function to get context-aware responses based on user's question and previous interactions:
#71
#72	```python
#73	def get_context_aware_response(question):
#74	relevant_memories = memory_client.search(question, user_id=USER_ID)
#75	context = "\n".join([m["memory"] for m in relevant_memories.get('results', [])])
#76
#77	prompt = f"""Answer the user question considering the previous interactions:
#78	Previous interactions:
#79	{context}
#80
#81	Question: {question}
#82	"""
#83
#84	reply = agent.generate_reply(messages=[{"content": prompt, "role": "user"}])
#85	return reply
#86
#87	# Example usage
#88	question = "What was the issue with my TV?"
#89	answer = get_context_aware_response(question)
#90	print("Context-aware answer:", answer)
#91	```
#92
#93	## Multi-Agent Conversation
#94
#95	For more complex scenarios, you can create multiple agents:
#96
#97	```python
#98	manager = ConversableAgent(
#99	"manager",
#100	system_message="You are a manager who helps in resolving complex customer issues.",
#101	llm_config={"config_list": [{"model": "gpt-4", "api_key": OPENAI_API_KEY}]},
#102	human_input_mode="NEVER"
#103	)
#104
#105	def escalate_to_manager(question):
#106	relevant_memories = memory_client.search(question, user_id=USER_ID)
#107	context = "\n".join([m["memory"] for m in relevant_memories.get('results', [])])
#108
#109	prompt = f"""
#110	Context from previous interactions:
#111	{context}
#112
#113	Customer question: {question}
#114
#115	As a manager, how would you address this issue?
#116	"""
#117
#118	manager_response = manager.generate_reply(messages=[{"content": prompt, "role": "user"}])
#119	return manager_response
#120
#121	# Example usage
#122	complex_question = "I'm not satisfied with the troubleshooting steps. What else can be done?"
#123	manager_answer = escalate_to_manager(complex_question)
#124	print("Manager's response:", manager_answer)
#125	```
#126
#127	## Conclusion
#128
#129	By integrating AutoGen with Mem0, you've created a conversational AI system with memory capabilities. This example demonstrates a customer service bot that can recall previous interactions and provide context-aware responses, with the ability to escalate complex issues to a manager agent.
#130
#131	This integration enables the creation of more intelligent and personalized AI agents for various applications, such as customer support, virtual assistants, and interactive chatbots.
#132
#133	<CardGroup cols={2}>
#134	<Card title="CrewAI Integration" icon="users" href="/integrations/crewai">
#135	Build multi-agent systems with CrewAI and Mem0
#136	</Card>
#137	<Card title="LangGraph Integration" icon="diagram-project" href="/integrations/langgraph">
#138	Create stateful workflows with LangGraph
#139	</Card>
#140	</CardGroup>
#141
#142

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public