Menu
Language
Theme
class PostgresSaverLangGraph checkpointer that uses a Postgres instance as the backing store. Uses the node-postgres package internally to connect to a Postgres instance.
Delete all checkpoints and writes associated with a specific thread ID.
Generate the next version ID for a channel.
Default is to use integer versions, incrementing by 1. If you override, you can use str/int/float versions, as long as they are monotonically increasing.
Get a checkpoint tuple from the database. This method retrieves a checkpoint tuple from the Postgres database based on the provided config. If the config's configurable field contains a "checkpoint_id" key, the checkpoint with the matching thread_id and namespace is retrieved. Otherwise, the latest checkpoint for the given thread_id is retrieved.
List checkpoints from the database.
This method retrieves a list of checkpoint tuples from the Postgres database based on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
Save a checkpoint to the database.
This method saves a checkpoint to the Postgres database. The checkpoint is associated with the provided config and its parent config (if any).
Store intermediate writes linked to a checkpoint.
This method saves intermediate writes associated with a checkpoint to the Postgres database.
Set up the checkpoint database asynchronously.
This method creates the necessary tables in the Postgres database if they don't already exist and runs database migrations. It MUST be called directly by the user the first time checkpointer is used.
Creates a new instance of PostgresSaver from a connection string.
import { ChatOpenAI } from "@langchain/openai";
import { PostgresSaver } from "@langchain/langgraph-checkpoint-postgres";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
const checkpointer = PostgresSaver.fromConnString(
"postgresql://user:password@localhost:5432/db",
// optional configuration object
{
schema: "custom_schema" // defaults to "public"
}
);
// NOTE: you need to call .setup() the first time you're using your checkpointer
await checkpointer.setup();
const graph = createReactAgent({
tools: [getWeather],
llm: new ChatOpenAI({
model: "gpt-4o-mini",
}),
checkpointSaver: checkpointer,
});
const config = { configurable: { thread_id: "1" } };
await graph.invoke({
messages: [{
role: "user",
content: "what's the weather in sf"
}],
}, config);