Integrations

An integration is the real backend that replaces an in-memory piece: a persistent checkpointer, a store, or a vector store, each passed in where the course's stand-in went.

Last updated: 29 Sep, 2026 · LangGraph 1.2

The course kept its storage in memory so it needed no setup. To ship, you swap each in-memory piece for a real backend. The graph code does not change; only the piece you pass in does. The model is already real, and changing provider is one string.

The pieces you used, and their real versions

Why the swap is drop-in

Every real checkpointer subclasses the same BaseCheckpointSaver that InMemorySaver does, so the graph accepts any of them in the same checkpointer= slot. Install the SQLite backend first: pip install langgraph-checkpoint-sqlite.

# pip install langgraph-checkpoint-sqlite
from langgraph.checkpoint.base import BaseCheckpointSaver
from langgraph.checkpoint.memory import InMemorySaver
from langgraph.checkpoint.sqlite import SqliteSaver

for saver in (InMemorySaver, SqliteSaver):
    print(saver.__name__, "is a checkpointer:", issubclass(saver, BaseCheckpointSaver))

InMemorySaver is a checkpointer: True
SqliteSaver is a checkpointer: True

Using a persistent checkpointer

Install the backend's package, open the saver, and compile with it. The checkpointer= call is the one from the checkpointer lesson, now pointing at a file.

# pip install langgraph-checkpoint-sqlite
from langgraph.checkpoint.sqlite import SqliteSaver

# same compile call, a real file instead of memory
with SqliteSaver.from_conn_string("checkpoints.db") as saver:
    graph = builder.compile(checkpointer=saver)

InMemorySaver vs SqliteSaver vs PostgresSaver

When to switch a piece

• Anything a user comes back to needs a persistent checkpointer, not InMemorySaver.
• Moving to another model provider is one string in init_chat_model; the graph code stays the same.
• RAG over real documents needs a vector store, not the keyword search.

Related

• Previous: RAG
• Next: Deploy
• Reference: Checkpointer integrations