RuntimeError: no validator found for <class '__main__.Node'>, see arbitrary_types_allowed in Config

[xjloong]

from langchain_community.graphs.graph_document import (
    Node as BaseNode,
    Relationship as BaseRelationship,
    GraphDocument,
)
from langchain.schema import Document
from typing import List, Dict, Any, Optional
from langchain.pydantic_v1 import Field, BaseModel

class Property(BaseModel):
    """A single property consisting of key and value"""
    key: str = Field(..., description="key")
    value: str = Field(..., description="value")
        
class Node(BaseNode):
    properties: Optional[List[Property]] = Field(
        None, description="List of node properties")

class Relationship(BaseRelationship):
    properties: Optional[List[Property]] = Field(
        None, description="List of relationship properties"
    )

# class Source(BaseSource):
#     properties: Optional[List[Property]] = Field(
#         None, description="List of sources"
#     )        
        
class KnowledgeGraph(BaseModel):
    """Generate a knowledge graph with entities and relationships."""
    nodes: List[Node] = Field(
        ..., description="List of nodes in the knowledge graph")
    rels: List[Relationship] = Field(
        ..., description="List of relationships in the knowledge graph"
    )

When I run this code, he gets this error. After looking around online, I added

class Config: 
        arbitrary_types_allowed = True

in class Node(BaseNode):.It is still getting the error, so I hope I can get some help!

[kartikpersistent]

Hi @xjloong can you give more information on which model you are getting this and any error trace ?

[xjloong]

Hi @xjloong can you give more information on which model you are getting this and any error trace ?
Thank you for you help,i have solved this error.i used llamam3.1 to run. firstly ,i used

from langchain_ollama.llms import OllamaLLM
model = OllamaLLM(model="llama3.1")

it got this error,but when i changed the code to

from langchain_ollama import ChatOllama
llm = ChatOllama(
    model="llama3.1",
    temperature=0,
    # other params...
)

it can go right into my code , though i don't konw the reason