klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add output examples and multion travel agent notebook (#1594)

Browse Source
This commit is contained in:
Dev Khant
2024-07-26 23:35:21 +05:30
committed by GitHub
parent bb2efb8b8b
commit ab3c9f889d
3 changed files with 583 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

153
docs/integrations/multion.mdx
View File

@@ -6,42 +6,48 @@ Build personal browser agent remembers user preferences and automates web tasks.
## Overview
In this example, we will create a Browser based AI Agent that searches [arxiv.org](https://arxiv.org) for research papers relevant to user's research interests.
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.
## Setup and Configuration
Install necessary libraries:
```bash
pip install mem0ai multion
pip install mem0ai multion openai
```
First, we'll import the necessary libraries and set up our configurations.
```python
import os
from mem0 import Memory
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
USER_ID = "deshraj"
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()
memory = Memory() # For local usage
memory_client = MemoryClient(api_key=MEM0_API_KEY) # For API usage
multion = MultiOn(api_key=MULTION_API_KEY)
```
## Add memories to Mem0
## Example 1: Research Paper Search Agent
Next, we'll define our user data and add it to Mem0.
### Add memories to Mem0
Define user data and add it to Mem0.
```python
# Define user data
USER_DATA = """
About me
- I'm Deshraj Yadav, Co-founder and CTO at Mem0, interested in AI and ML Infrastructure.
@@ -50,17 +56,15 @@ About me
- Outside of work, I enjoy playing cricket in two leagues in the San Francisco.
"""
# Add user data to memory
memory.add(USER_DATA, user_id=USER_ID)
print("User data added to memory.")
```
## Retrieving Relevant Memories
### Retrieving Relevant Memories
Now, we'll define our search command and retrieve relevant memories from Mem0.
Define search command and retrieve relevant memories from Mem0.
```python
# Define search command and retrieve relevant memories
command = "Find papers on arxiv that I should read based on my interests."
relevant_memories = memory.search(command, user_id=USER_ID, limit=3)
@@ -69,22 +73,139 @@ print(f"Relevant memories:")
print(relevant_memories_text)
```
## Browsing arXiv
### Browsing arXiv
Finally, we'll use MultiOn to browse arXiv based on our command and relevant memories.
Use MultiOn to browse arXiv based on the command and relevant memories.
```python
# Create prompt and browse arXiv
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 a personalized browser agent that remembers user preferences and automates web tasks. For more details and advanced usage, refer to the full [cookbook here](https://github.com/mem0ai/mem0/blob/main/cookbooks/mem0-multion.ipynb).
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).

141
docs/platform/quickstart.mdx
View File

@@ -80,6 +80,10 @@ curl -X POST "https://api.mem0.ai/v1/memories/" \
"user_id": "alex"
}'
```
```json Output
{'message': 'ok'}
```
</CodeGroup>
#### Short-term memory for a user session
@@ -123,6 +127,10 @@ curl -X POST "https://api.mem0.ai/v1/memories/" \
"session_id": "trip-planning-2024"
}'
```
```json Output
{'message': 'ok'}
```
</CodeGroup>
#### Long-term memory for agents
@@ -159,6 +167,10 @@ curl -X POST "https://api.mem0.ai/v1/memories/" \
"agent_id": "travel-assistant"
}'
```
```json Output
{'message': 'ok'}
```
</CodeGroup>
You can monitor memory operations on the platform:
@@ -239,6 +251,29 @@ client.getAll({ agent_id: "travel-assistant" })
curl -X GET "https://api.mem0.ai/v1/memories/?agent_id=travel-assistant" \
-H "Authorization: Token your-api-key"
```
```json Output
[
{
"id":"f38b689d-6b24-45b7-bced-17fbb4d8bac7",
"memory":"是素食主义者，对坚果过敏。",
"agent_id":"travel-assistant",
"hash":"62bc074f56d1f909f1b4c2b639f56f6a",
"metadata":"None",
"created_at":"2024-07-25T23:57:00.108347-07:00",
"updated_at":"2024-07-25T23:57:00.108367-07:00"
},
{
"id":"0a14d8f0-e364-4f5c-b305-10da1f0d0878",
"memory":"Will maintain personalized travel preferences for each user. Provide customized recommendations based on dietary restrictions, interests, and past interactions.",
"agent_id":"travel-assistant",
"hash":"35a305373d639b0bffc6c2a3e2eb4244",
"metadata":"None",
"created_at":"2024-07-26T00:31:03.543759-07:00",
"updated_at":"2024-07-26T00:31:03.543778-07:00"
}
]
```
</CodeGroup>
#### Get all memories of user
@@ -259,6 +294,29 @@ client.getAll({ user_id: "alex" })
curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex" \
-H "Authorization: Token your-api-key"
```
```json Output
[
{
"id":"f38b689d-6b24-45b7-bced-17fbb4d8bac7",
"memory":"是素食主义者，对坚果过敏。",
"agent_id":"travel-assistant",
"hash":"62bc074f56d1f909f1b4c2b639f56f6a",
"metadata":"None",
"created_at":"2024-07-25T23:57:00.108347-07:00",
"updated_at":"2024-07-25T23:57:00.108367-07:00"
},
{
"id":"0a14d8f0-e364-4f5c-b305-10da1f0d0878",
"memory":"Will maintain personalized travel preferences for each user. Provide customized recommendations based on dietary restrictions, interests, and past interactions.",
"agent_id":"travel-assistant",
"hash":"35a305373d639b0bffc6c2a3e2eb4244",
"metadata":"None",
"created_at":"2024-07-26T00:31:03.543759-07:00",
"updated_at":"2024-07-26T00:31:03.543778-07:00"
}
]
```
</CodeGroup>
#### Get short-term memories for a session
@@ -279,6 +337,38 @@ client.getAll({ user_id: "alex123", session_id: "trip-planning-2024" })
curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&session_id=trip-planning-2024" \
-H "Authorization: Token your-api-key"
```
```json Output
[
{
"id":"06d8df63-7bd2-4fad-9acb-60871bcecee0",
"memory":"Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",
"user_id":"alex123",
"hash":"d2088c936e259f2f5d2d75543d31401c",
"metadata":"None",
"created_at":"2024-07-26T00:25:16.566471-07:00",
"updated_at":"2024-07-26T00:25:16.566492-07:00"
},
{
"id":"b4229775-d860-4ccb-983f-0f628ca112f5",
"memory":"Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",
"user_id":"alex123",
"hash":"d2088c936e259f2f5d2d75543d31401c",
"metadata":"None",
"created_at":"2024-07-26T00:33:20.350542-07:00",
"updated_at":"2024-07-26T00:33:20.350560-07:00"
},
{
"id":"df1aca24-76cf-4b92-9f58-d03857efcb64",
"memory":"Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",
"user_id":"alex123",
"hash":"d2088c936e259f2f5d2d75543d31401c",
"metadata":"None",
"created_at":"2024-07-26T00:51:09.642275-07:00",
"updated_at":"2024-07-26T00:51:09.642295-07:00"
}
]
```
</CodeGroup>
#### Get specific memory
@@ -299,6 +389,18 @@ client.get("582bbe6d-506b-48c6-a4c6-5df3b1e63428")
curl -X GET "https://api.mem0.ai/v1/memories/582bbe6d-506b-48c6-a4c6-5df3b1e63428" \
-H "Authorization: Token your-api-key"
```
```json Output
{
"id":"06d8df63-7bd2-4fad-9acb-60871bcecee0",
"memory":"Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",
"user_id":"alex123",
"hash":"d2088c936e259f2f5d2d75543d31401c",
"metadata":"None",
"created_at":"2024-07-26T00:25:16.566471-07:00",
"updated_at":"2024-07-26T00:25:16.566492-07:00"
}
```
</CodeGroup>
### 4.4 Memory History
@@ -319,7 +421,6 @@ client.add(messages, user_id="alex")
# Get history of how memory changed over time
memory_id = "<memory-id-here>"
history = client.history(memory_id)
print(history)
```
```javascript JavaScript
@@ -366,6 +467,32 @@ curl -X POST "https://api.mem0.ai/v1/memories/" \
curl -X GET "https://api.mem0.ai/v1/memories/<memory-id-here>/history/" \
-H "Authorization: Token your-api-key"
```
```json Output
[
{
"id":"d6306e85-eaa6-400c-8c2f-ab994a8c4d09",
"memory_id":"b163df0e-ebc8-4098-95df-3f70a733e198",
"input":[
{
"role":"user",
"content":"I recently tried chicken and I loved it. I'm thinking of trying more non-vegetarian dishes.."
},
{
"role":"user",
"content":"I turned vegetarian now."
}
],
"old_memory":"None",
"new_memory":"Turned vegetarian.",
"user_id":"alex123456",
"event":"ADD",
"metadata":"None",
"created_at":"2024-07-26T01:02:41.737310-07:00",
"updated_at":"2024-07-26T01:02:41.726073-07:00"
}
]
```
</CodeGroup>
### 4.5 Delete Memory
@@ -388,6 +515,10 @@ client.delete("memory-id-here")
curl -X DELETE "https://api.mem0.ai/v1/memories/memory-id-here" \
-H "Authorization: Token your-api-key"
```
```json Output
{'message': 'Memory deleted successfully'}
```
</CodeGroup>
Delete all memories of a user:
@@ -408,6 +539,10 @@ client.deleteAll({ user_id: "alex" })
curl -X DELETE "https://api.mem0.ai/v1/memories/?user_id=alex" \
-H "Authorization: Token your-api-key"
```
```json Output
{'message': 'Memories deleted successfully!'}
```
</CodeGroup>
Fun fact: You can also delete the memory using the `add()` method by passing a natural language command:
@@ -433,6 +568,10 @@ curl -X POST "https://api.mem0.ai/v1/memories/" \
"user_id": "alex"
}'
```
```json Output
{'message': 'ok'}
```
</CodeGroup>
If you have any questions, please feel free to reach out to us using one of the following methods: