211 lines
8.5 KiB
Plaintext
211 lines
8.5 KiB
Plaintext
---
|
|
title: MultiOn
|
|
---
|
|
|
|
Build personal browser agent remembers user preferences and automates web tasks. It integrates Mem0 for memory management with MultiOn for executing browser actions, enabling personalized and efficient web interactions.
|
|
|
|
## Overview
|
|
|
|
In this guide, we'll explore two examples of creating Browser-based AI Agents:
|
|
1. An agent that searches [arxiv.org](https://arxiv.org) for research papers relevant to user's research interests.
|
|
2. A travel agent that provides personalized travel information based on user preferences. Refer the [notebook](https://github.com/MULTI-ON/cookbook/blob/main/personalized-travel-agent/mem0_travel_agent.ipynb) for detailed code.
|
|
|
|
## Setup and Configuration
|
|
|
|
Install necessary libraries:
|
|
|
|
```bash
|
|
pip install mem0ai multion openai
|
|
```
|
|
|
|
First, we'll import the necessary libraries and set up our configurations.
|
|
|
|
```python
|
|
import os
|
|
from mem0 import Memory, MemoryClient
|
|
from multion.client import MultiOn
|
|
from openai import OpenAI
|
|
|
|
# Configuration
|
|
OPENAI_API_KEY = 'sk-xxx' # Replace with your actual OpenAI API key
|
|
MULTION_API_KEY = 'your-multion-key' # Replace with your actual MultiOn API key
|
|
MEM0_API_KEY = 'your-mem0-key' # Replace with your actual Mem0 API key
|
|
USER_ID = "your-user-id"
|
|
|
|
# Set up OpenAI API key
|
|
os.environ['OPENAI_API_KEY'] = OPENAI_API_KEY
|
|
|
|
# Initialize Mem0 and MultiOn
|
|
memory = Memory() # For local usage
|
|
memory_client = MemoryClient(api_key=MEM0_API_KEY) # For API usage
|
|
multion = MultiOn(api_key=MULTION_API_KEY)
|
|
```
|
|
|
|
## Example 1: Research Paper Search Agent
|
|
|
|
### Add memories to Mem0
|
|
|
|
Define user data and add it to Mem0.
|
|
|
|
```python
|
|
USER_DATA = """
|
|
About me
|
|
- I'm Deshraj Yadav, Co-founder and CTO at Mem0, interested in AI and ML Infrastructure.
|
|
- Previously, I was a Senior Autopilot Engineer at Tesla, leading the AI Platform for Autopilot.
|
|
- I built EvalAI at Georgia Tech, an open-source platform for evaluating ML algorithms.
|
|
- Outside of work, I enjoy playing cricket in two leagues in the San Francisco.
|
|
"""
|
|
|
|
memory.add(USER_DATA, user_id=USER_ID)
|
|
print("User data added to memory.")
|
|
```
|
|
|
|
### Retrieving Relevant Memories
|
|
|
|
Define search command and retrieve relevant memories from Mem0.
|
|
|
|
```python
|
|
command = "Find papers on arxiv that I should read based on my interests."
|
|
|
|
relevant_memories = memory.search(command, user_id=USER_ID, limit=3)
|
|
relevant_memories_text = '\n'.join(mem['text'] for mem in relevant_memories)
|
|
print(f"Relevant memories:")
|
|
print(relevant_memories_text)
|
|
```
|
|
|
|
### Browsing arXiv
|
|
|
|
Use MultiOn to browse arXiv based on the command and relevant memories.
|
|
|
|
```python
|
|
prompt = f"{command}\n My past memories: {relevant_memories_text}"
|
|
browse_result = multion.browse(cmd=prompt, url="https://arxiv.org/")
|
|
print(browse_result)
|
|
```
|
|
|
|
## Example 2: Travel Agent
|
|
|
|
### Get Travel Information
|
|
|
|
Add conversation to Mem0 and create a function to get travel information based on user's question and optionally their preferences from memory.
|
|
|
|
<CodeGroup>
|
|
```python Code
|
|
def get_travel_info(question, use_memory=True):
|
|
if use_memory:
|
|
previous_memories = memory_client.search(question, user_id=USER_ID)
|
|
relevant_memories_text = ""
|
|
if previous_memories:
|
|
print("Using previous memories to enhance the search...")
|
|
relevant_memories_text = '\n'.join(mem["memory"] for mem in previous_memories)
|
|
|
|
command = "Find travel information based on my interests:"
|
|
prompt = f"{command}\n Question: {question} \n My preferences: {relevant_memories_text}"
|
|
else:
|
|
command = "Find travel information based on my interests:"
|
|
prompt = f"{command}\n Question: {question}"
|
|
|
|
print("Searching for travel information...")
|
|
browse_result = multion.browse(cmd=prompt)
|
|
return browse_result.message
|
|
|
|
# Example usage
|
|
question = "Show me flight details for it."
|
|
answer_without_memory = get_travel_info(question, use_memory=False)
|
|
answer_with_memory = get_travel_info(question, use_memory=True)
|
|
|
|
print("Answer without memory:", answer_without_memory)
|
|
print("Answer with memory:", answer_with_memory)
|
|
|
|
# Another example
|
|
question = "What is the best place to eat there?"
|
|
answer_without_memory = get_travel_info(question, use_memory=False)
|
|
answer_with_memory = get_travel_info(question, use_memory=True)
|
|
|
|
print("Answer without memory:", answer_without_memory)
|
|
print("Answer with memory:", answer_with_memory)
|
|
```
|
|
|
|
```json Conversation
|
|
# Add conversation to Mem0
|
|
conversation = [
|
|
{
|
|
"role": "user",
|
|
"content": "What are the best travel destinations in the world?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Could you please specify your interests or the type of travel information you are looking for? This will help me find the most relevant information for you."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Sure, I want to travel to San Francisco."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": """
|
|
Based on the information gathered from TripAdvisor, here are some popular attractions, activities, and travel tips for San Francisco: \
|
|
|
|
1. **Golden Gate Bridge**: A must-see iconic landmark. \
|
|
2. **Alcatraz Island**: Famous former prison offering tours. \
|
|
3. **Fisherman's Wharf**: Popular tourist area with shops, restaurants, and sea lions. \
|
|
4. **Chinatown**: The largest Chinatown outside of Asia. \
|
|
5. **Golden Gate Park**: Large urban park with gardens, museums, and recreational activities. \
|
|
6. **Cable Cars**: Historic streetcars offering a unique way to see the city. \
|
|
7. **Exploratorium**: Interactive science museum. \
|
|
8. **San Francisco Museum of Modern Art (SFMOMA)**: Modern and contemporary art museum. \
|
|
9. **Lombard Street**: Known for its steep, one-block section with eight hairpin turns. \
|
|
10. **Union Square**: Major shopping and cultural hub. \
|
|
|
|
Travel Tips: \
|
|
- **Weather**: San Francisco has a mild climate, but it can be foggy and windy. Dress in layers. \
|
|
- **Transportation**: Use public transportation like BART, Muni, and cable cars to get around. \
|
|
- **Safety**: Be aware of your surroundings, especially in crowded tourist areas. \
|
|
- **Dining**: Try local specialties like sourdough bread, seafood, and Mission-style burritos. \
|
|
"""
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Show me hotels around Golden Gate Bridge."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": """The search results for hotels around Golden Gate Bridge in San Francisco include: \
|
|
|
|
1. Hilton Hotels In San Francisco - Hotel Near Fishermans Wharf (hilton.com) \
|
|
2. The 10 Closest Hotels to Golden Gate Bridge (tripadvisor.com) \
|
|
3. Hotels near Golden Gate Bridge (expedia.com) \
|
|
4. Hotels near Golden Gate Bridge (hotels.com) \
|
|
5. Holiday Inn Express & Suites San Francisco Fishermans Wharf, an IHG Hotel $146 (1.8K) 3-star hotel Golden Gate Bridge • 3.5 mi DEAL 19% less than usual \
|
|
6. Holiday Inn San Francisco-Golden Gateway, an IHG Hotel $151 (3.5K) 3-star hotel Golden Gate Bridge • 3.7 mi Casual hotel with dining, a bar & a pool \
|
|
7. Hotel Zephyr San Francisco $159 (3.8K) 4-star hotel Golden Gate Bridge • 3.7 mi Nautical-themed lodging with bay views \
|
|
8. Lodge at the Presidio \
|
|
9. The Inn Above Tide \
|
|
10. Cavallo Point \
|
|
11. Casa Madrona Hotel and Spa \
|
|
12. Cow Hollow Inn and Suites \
|
|
13. Samesun San Francisco \
|
|
14. Inn on Broadway \
|
|
15. Coventry Motor Inn \
|
|
16. HI San Francisco Fisherman's Wharf Hostel \
|
|
17. Loews Regency San Francisco Hotel \
|
|
18. Fairmont Heritage Place Ghirardelli Square \
|
|
19. Hotel Drisco Pacific Heights \
|
|
20. Travelodge by Wyndham Presidio San Francisco \
|
|
"""
|
|
}
|
|
]
|
|
```
|
|
</CodeGroup>
|
|
|
|
## Conclusion
|
|
|
|
By integrating Mem0 with MultiOn, you've created personalized browser agents that remember user preferences and automate web tasks. The first example demonstrates a research-focused agent, while the second example shows a travel agent capable of providing personalized recommendations.
|
|
|
|
These examples illustrate how combining memory management with web browsing capabilities can create powerful, context-aware AI agents for various applications.
|
|
|
|
## Help
|
|
|
|
- For more details and advanced usage, refer to the full [cookbooks here](https://github.com/mem0ai/mem0/blob/main/cookbooks).
|
|
- Feel free to visit our [Github](https://github.com/mem0ai/mem0) or [Mem0 Platform](https://app.mem0.ai/).
|
|
- For any questions or assistance, please reach out to `taranjeetio` on [Discord](https://mem0.ai/discord). |