AssertionError('_async_engine not found') with PGVector in a RAG tool

[cj2001]

Hi, all.

I have created vector embeddings using PGVector following the docs. Here is a rough snippet of how I created the vectors:

import requests
import os

from bs4 import BeautifulSoup
import html2text
from dotenv import load_dotenv

from langchain_community.embeddings import OpenAIEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter, MarkdownHeaderTextSplitter
from langchain_postgres.vectorstores import PGVector

from settings import Settings


PGDATABASE = '...'
CONNECTION_STRING = f"postgresql+psycopg://{Settings.PGUSER}:{Settings.PGPASSWORD}@{Settings.PGHOST}:{Settings.PGPORT}/{PGDATABASE}"
COLLECTION_NAME = "..."

...a bunch of markdown webpages read...

text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=3000,
    chunk_overlap=150,
    length_function=len,
    is_separator_regex=False,
)

text_splits = text_splitter.create_documents([text_content])

docs = md_header_splits + text_splits

embedding = OpenAIEmbeddings(openai_api_key=Settings.OPENAI_API_KEY)

vector_store = PGVector(
    embeddings=embedding,
    collection_name=COLLECTION_NAME,
    connection=CONNECTION_STRING,
    pre_delete_collection=True,
    use_jsonb=True,
)

document_ids = vector_store.add_documents(documents=docs)

print(document_ids[0:5])

I can see that this creates tables in postgres with embeddings. I then created a retriever as a tool in LangGraph with roughly the following code:

from langchain.tools.retriever import create_retriever_tool
from langchain_postgres.vectorstores import PGVector
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()

COLLECTION_NAME = "..."
PGDATABASE = '...'
CONNECTION_STRING = f"postgresql+psycopg://{settings.PGUSER}:{settings.PGPASSWORD}@{settings.PGHOST}:{settings.PGPORT}/{PGDATABASE}"

store = PGVector(
    collection_name=COLLECTION_NAME,
    connection=CONNECTION_STRING,
    embeddings=embeddings,
)

retriever = store.as_retriever(search_kwargs={"k": 5})

MyDocs = create_retriever_tool(
    retriever,
    "...",
    """
    Description of RAG.
    """,
)

However, when I ask a question in LangGraph that would use this RAG, I get the following error:

Error: AssertionError('_async_engine not found') Please fix your mistakes.

For the record, here are my package versions:

langchain                     0.3.14
langchain-community           0.3.14
langchain-core                0.3.29
langchain-openai              0.2.14
langchain-postgres            0.0.13
langchain-text-splitters      0.3.5
langgraph                     0.2.61
langgraph-api                 0.0.15
langgraph-checkpoint          2.0.9
langgraph-checkpoint-postgres 2.0.11
langgraph-cli                 0.1.65
langgraph-sdk                 0.1.48
langsmith                     0.2.10

[hinthornw]

This seems like an error for the langchain-postgres package, rather than langgraph

[cj2001]

OK...I will move this conversation over there...

[hinthornw]

Thank you!

[mujz]

Can you please share the thread of the conversation on the langchain-postgres repo? I too am getting this error, and Google brought me here.