195 lines
3.2 KiB
Plaintext
195 lines
3.2 KiB
Plaintext
---
|
|
title: 🚀 Quickstart
|
|
description: 'Get started with Mem0 quickly!'
|
|
---
|
|
|
|
> Welcome to the Mem0 quickstart guide. This guide will help you get up and running with Mem0 in no time.
|
|
|
|
## Installation
|
|
|
|
To install Mem0, you can use pip. Run the following command in your terminal:
|
|
|
|
```bash
|
|
pip install mem0ai
|
|
```
|
|
|
|
## Basic Usage
|
|
|
|
### Initialize Mem0
|
|
|
|
<Tabs>
|
|
<Tab title="Basic">
|
|
```python
|
|
from mem0 import Memory
|
|
m = Memory()
|
|
```
|
|
</Tab>
|
|
<Tab title="Advanced">
|
|
If you want to run Mem0 in production, initialize using the following method:
|
|
|
|
Run Qdrant first:
|
|
|
|
```bash
|
|
docker pull qdrant/qdrant
|
|
|
|
docker run -p 6333:6333 -p 6334:6334 \
|
|
-v $(pwd)/qdrant_storage:/qdrant/storage:z \
|
|
qdrant/qdrant
|
|
```
|
|
|
|
Then, instantiate memory with qdrant server:
|
|
|
|
```python
|
|
from mem0 import Memory
|
|
|
|
config = {
|
|
"vector_store": {
|
|
"provider": "qdrant",
|
|
"config": {
|
|
"host": "localhost",
|
|
"port": 6333,
|
|
}
|
|
},
|
|
}
|
|
|
|
m = Memory.from_config(config)
|
|
```
|
|
</Tab>
|
|
</Tabs>
|
|
|
|
|
|
### Store a Memory
|
|
|
|
```python
|
|
# For a user
|
|
result = m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})
|
|
print(result)
|
|
```
|
|
|
|
Output:
|
|
```python
|
|
[
|
|
{
|
|
'id': 'm1',
|
|
'event': 'add',
|
|
'data': 'Likes to play cricket on weekends'
|
|
}
|
|
]
|
|
```
|
|
|
|
### Retrieve Memories
|
|
|
|
```python
|
|
# Get all memories
|
|
all_memories = m.get_all()
|
|
print(all_memories)
|
|
```
|
|
|
|
Output:
|
|
|
|
```python
|
|
[
|
|
{
|
|
'id': 'm1',
|
|
'text': 'Likes to play cricket on weekends',
|
|
'metadata': {
|
|
'data': 'Likes to play cricket on weekends',
|
|
'category': 'hobbies'
|
|
}
|
|
},
|
|
# ... other memories ...
|
|
]
|
|
```
|
|
|
|
```python
|
|
# Get a single memory by ID
|
|
specific_memory = m.get("m1")
|
|
print(specific_memory)
|
|
```
|
|
|
|
Output:
|
|
```python
|
|
{
|
|
'id': 'm1',
|
|
'text': 'Likes to play cricket on weekends',
|
|
'metadata': {
|
|
'data': 'Likes to play cricket on weekends',
|
|
'category': 'hobbies'
|
|
}
|
|
}
|
|
```
|
|
|
|
### Search Memories
|
|
|
|
```python
|
|
related_memories = m.search(query="What are Alice's hobbies?", user_id="alice")
|
|
print(related_memories)
|
|
```
|
|
|
|
Output:
|
|
|
|
```python
|
|
[
|
|
{
|
|
'id': 'm1',
|
|
'text': 'Likes to play cricket on weekends',
|
|
'metadata': {
|
|
'data': 'Likes to play cricket on weekends',
|
|
'category': 'hobbies'
|
|
},
|
|
'score': 0.85 # Similarity score
|
|
},
|
|
# ... other related memories ...
|
|
]
|
|
```
|
|
|
|
### Update a Memory
|
|
|
|
```python
|
|
result = m.update(memory_id="m1", data="Likes to play tennis on weekends")
|
|
print(result)
|
|
```
|
|
|
|
Output:
|
|
|
|
```python
|
|
{
|
|
'id': 'm1',
|
|
'event': 'update',
|
|
'data': 'Likes to play tennis on weekends'
|
|
}
|
|
```
|
|
|
|
### Memory History
|
|
|
|
```python
|
|
history = m.history(memory_id="m1")
|
|
print(history)
|
|
```
|
|
Output:
|
|
```python
|
|
[
|
|
{
|
|
'id': 'h1',
|
|
'memory_id': 'm1',
|
|
'prev_value': None,
|
|
'new_value': 'Likes to play cricket on weekends',
|
|
'event': 'add',
|
|
'timestamp': '2024-07-14 10:00:54.466687',
|
|
'is_deleted': 0
|
|
},
|
|
{
|
|
'id': 'h2',
|
|
'memory_id': 'm1',
|
|
'prev_value': 'Likes to play cricket on weekends',
|
|
'new_value': 'Likes to play tennis on weekends',
|
|
'event': 'update',
|
|
'timestamp': '2024-07-14 10:15:17.230943',
|
|
'is_deleted': 0
|
|
}
|
|
]
|
|
```
|
|
|
|
If you have any questions, please feel free to reach out to us using one of the following methods:
|
|
|
|
<Snippet file="get-help.mdx" /> |