ValidationError when using LLMGraphTransformer

[arisylafeta]

Hi, I was trying the GraphRAG tutorial from Neo4j:
https://neo4j.com/developer-blog/global-graphrag-neo4j-langchain/

and upon trying the snippet:

import concurrent.futures
from concurrent.futures import ThreadPoolExecutor, as_completed
from tqdm import tqdm


MAX_WORKERS = 10
NUM_ARTICLES = 200
graph_documents = []

with ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
    # Submitting all tasks and creating a list of future objects
    futures = [
        executor.submit(process_text, f"{row['title']} {row['text']}")
        for i, row in news.head(NUM_ARTICLES).iterrows()
    ]

    for future in tqdm(
        as_completed(futures), total=len(futures), desc="Processing documents"
    ):
        graph_document = future.result()
        graph_documents.extend(graph_document)

graph.add_graph_documents(
    graph_documents,
    baseEntityLabel=True,
    include_source=True
)

I get this error:

ValidationError: 1 validation error for Node
properties
  Input should be a valid dictionary [type=dict_type, input_value=FieldInfo(default=Pydanti...class 'dict'>, extra={}), input_type=FieldInfo]
    For further information visit https://errors.pydantic.dev/2.8/v/dict_type

interestingly, I tried implementing one of the examples in the langchain docs: https://python.langchain.com/docs/how_to/graph_constructing/

and lo and behold I get the same error. It seems that something is broken. Can someone confirm getting the same issue?

[alexthomas93]

Hi @arisylafeta, could you please share more details about your environment, including the versions of langchain and langchain-neo4j you’re using? It would also be helpful if you could provide the full script you’re running. I’m having difficulty reproducing the error based on the Neo4j or LangChain documentation. Thanks!