LlamaIndex supports Mem0 as a memory store. In this guide, we’ll show you how to use it.
🎉 Exciting news! Mem0Memory now supports ReAct and FunctionCalling agents.
Installation
To install the required package, run:
pip install llama-index-core llama-index-memory-mem0 python-dotenv
Set your Mem0 Platform API key as an environment variable. You can replace <your-mem0-api-key>
with your actual API key:
You can obtain your Mem0 Platform API key from the Mem0 Platform.
from dotenv import load_dotenv
import os
load_dotenv()
# os.environ["MEM0_API_KEY"] = "<your-mem0-api-key>"
Import the necessary modules and create a Mem0Memory instance:
from llama_index.memory.mem0 import Mem0Memory
context = {"user_id": "alice"}
memory_from_client = Mem0Memory.from_client(
context=context,
search_msg_limit=4, # optional, default is 5
output_format='v1.1', # Remove deprecation warnings
)
Context is used to identify the user, agent or the conversation in the Mem0. It is required to be passed in the at least one of the fields in the Mem0Memory
constructor. It can be any of the following:
context = {
"user_id": "alice",
"agent_id": "llama_agent_1",
"run_id": "run_1",
}
search_msg_limit
is optional, default is 5. It is the number of messages from the chat history to be used for memory retrieval from Mem0. More number of messages will result in more context being used for retrieval but will also increase the retrieval time and might result in some unwanted results.
search_msg_limit
is different from limit
. limit
is the number of messages to be retrieved from Mem0 and is used in search.
Setup with Mem0 OSS
Set your Mem0 OSS by providing configuration details:
config = {
"vector_store": {
"provider": "qdrant",
"config": {
"collection_name": "test_9",
"host": "localhost",
"port": 6333,
"embedding_model_dims": 1536, # Change this according to your local model's dimensions
},
},
"llm": {
"provider": "openai",
"config": {
"model": "gpt-4o",
"temperature": 0.2,
"max_tokens": 2000,
},
},
"embedder": {
"provider": "openai",
"config": {"model": "text-embedding-3-small"},
},
"version": "v1.1",
}
Create a Mem0Memory instance:
memory_from_config = Mem0Memory.from_config(
context=context,
config=config,
search_msg_limit=4, # optional, default is 5
output_format='v1.1', # Remove deprecation warnings
)
Initialize the LLM
from llama_index.llms.openai import OpenAI
from dotenv import load_dotenv
load_dotenv()
# os.environ["OPENAI_API_KEY"] = "<your-openai-api-key>"
llm = OpenAI(model="gpt-4o-mini")
SimpleChatEngine
Use the SimpleChatEngine
to start a chat with the agent with the memory.
from llama_index.core.chat_engine import SimpleChatEngine
agent = SimpleChatEngine.from_defaults(
llm=llm, memory=memory_from_client # or memory_from_config
)
# Start the chat
response = agent.chat("Hi, My name is Alice")
print(response)
Now we will learn how to use Mem0 with FunctionCalling and ReAct agents.
Initialize the tools:
from llama_index.core.tools import FunctionTool
def call_fn(name: str):
"""Call the provided name.
Args:
name: str (Name of the person)
"""
print(f"Calling... {name}")
def email_fn(name: str):
"""Email the provided name.
Args:
name: str (Name of the person)
"""
print(f"Emailing... {name}")
call_tool = FunctionTool.from_defaults(fn=call_fn)
email_tool = FunctionTool.from_defaults(fn=email_fn)
FunctionCallingAgent
from llama_index.core.agent import FunctionCallingAgent
agent = FunctionCallingAgent.from_tools(
[call_tool, email_tool],
llm=llm,
memory=memory_from_client, # or memory_from_config
verbose=True,
)
# Start the chat
response = agent.chat("Hi, My name is Alice")
print(response)
ReActAgent
from llama_index.core.agent import ReActAgent
agent = ReActAgent.from_tools(
[call_tool, email_tool],
llm=llm,
memory=memory_from_client, # or memory_from_config
verbose=True,
)
# Start the chat
response = agent.chat("Hi, My name is Alice")
print(response)
Key Features
- Memory Integration: Uses Mem0 to store and retrieve relevant information from past interactions.
- Personalization: Provides context-aware agent responses based on user history and preferences.
- Flexible Architecture: LlamaIndex allows for easy integration of the memory with the agent.
- Continuous Learning: Each interaction is stored, improving future responses.
Conclusion
By integrating LlamaIndex with Mem0, you can build a personalized agent that can maintain context across interactions with the agent and provide tailored recommendations and assistance.