LangChain
Memori supports any LangChain chat model. Each class has its own registration keyword: chatopenai for ChatOpenAI/ChatAnthropic, chatbedrock for ChatBedrock, chatgooglegenai for ChatGoogleGenerativeAI.
Want a zero-setup option? The Memori Cloud at app.memorilabs.ai.
Quick Start
LangChain Integration
from langchain_openai import ChatOpenAI
from memori import Memori
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
engine = create_engine("sqlite:///memori.db")
SessionLocal = sessionmaker(bind=engine)
client = ChatOpenAI(model="gpt-4o-mini")
mem = Memori(conn=SessionLocal).llm.register(chatopenai=client)
mem.config.storage.build()
mem.attribution(entity_id="user_123", process_id="langchain_agent")
response = client.invoke("Hello!")
print(response.content)
Different Providers
| Package | Chat Model | Registration Keyword |
|---|---|---|
langchain-openai | ChatOpenAI | chatopenai=client |
langchain-anthropic | ChatAnthropic | chatopenai=client |
langchain-google-genai | ChatGoogleGenerativeAI | chatgooglegenai=client |
langchain-aws | ChatBedrock | chatbedrock=client |
LangChain Providers
from langchain_anthropic import ChatAnthropic
client = ChatAnthropic(model="claude-3-5-sonnet-20241022")
mem = Memori(conn=SessionLocal).llm.register(chatopenai=client)
Supported Modes
| Mode | Method |
|---|---|
| Sync | client.invoke() |
| Async | await client.ainvoke() |
| Streamed | client.stream() |