A database migration with optional conditions and parameters.
Connection pool settings for PostgreSQL connections.
Controls connection lifecycle and resource utilization:
Configuration for vector index in PostgreSQL store.
Configuration for HNSW (Hierarchical Navigable Small World) index.
IVFFlat index divides vectors into lists, and then searches a subset of those lists that are closest to the query vector. It has faster build times and uses less memory than HNSW, but has lower query performance (in terms of speed-recall tradeoff).
Three keys to achieving good recall are:
Configuration for vector embeddings in PostgreSQL store with pgvector-specific options.
Extends EmbeddingConfig with additional configuration for pgvector index and vector types.
Postgres-backed store with optional vector search using pgvector.
Basic setup and usage:
from langgraph.store.postgres import PostgresStore
from psycopg import Connection
conn_string = "postgresql://user:pass@localhost:5432/dbname"
# Using direct connection
with Connection.connect(conn_string) as conn:
store = PostgresStore(conn)
store.setup() # Run migrations. Done once
# Store and retrieve data
store.put(("users", "123"), "prefs", {"theme": "dark"})
item = store.get(("users", "123"), "prefs")Or using the convenient from_conn_string helper:
from langgraph.store.postgres import PostgresStore
conn_string = "postgresql://user:pass@localhost:5432/dbname"
with PostgresStore.from_conn_string(conn_string) as store:
store.setup()
# Store and retrieve data
store.put(("users", "123"), "prefs", {"theme": "dark"})
item = store.get(("users", "123"), "prefs")Vector search using LangChain embeddings:
from langchain.embeddings import init_embeddings
from langgraph.store.postgres import PostgresStore
conn_string = "postgresql://user:pass@localhost:5432/dbname"
with PostgresStore.from_conn_string(
conn_string,
index={
"dims": 1536,
"embed": init_embeddings("openai:text-embedding-3-small"),
"fields": ["text"] # specify which fields to embed. Default is the whole serialized value
}
) as store:
store.setup() # Do this once to run migrations
# Store documents
store.put(("docs",), "doc1", {"text": "Python tutorial"})
store.put(("docs",), "doc2", {"text": "TypeScript guide"})
store.put(("docs",), "doc2", {"text": "Other guide"}, index=False) # don't index
# Search by similarity
results = store.search(("docs",), query="programming guides", limit=2)