According to the official example, when creating a knowledge graph using the local large model glm-4-9b-chat, the generated nodes and relationships in the graph are empty.

[KOBEBRYANTand]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

code：
from langchain_core.prompts import PromptTemplate
from langchain_openai import ChatOpenAI
from langchain.schema import HumanMessage
import os
from langchain_experimental.graph_transformers import LLMGraphTransformer
from langchain_core.documents import Document

from langchain_community.graphs import Neo4jGraph

初始化模型

llm = ChatOpenAI(
streaming=True,
verbose=True,
openai_api_key="none", # 根据实际情况配置
openai_api_base="http://192.168.3.188:8080/v1", # 根据实际情况配置
model_name="glm-4-9b-chat",
)
os.environ["NEO4J_URI"] = "bolt://192.168.3.188:7687"
os.environ["NEO4J_USERNAME"] = "neo4j"
os.environ["NEO4J_PASSWORD"] = "123456"

graph = Neo4jGraph()
llm_transformer = LLMGraphTransformer(llm=llm)
from langchain_core.documents import Document

text = """
Marie Curie, born in 1867, was a Polish and naturalised-French physicist and chemist who conducted pioneering research on radioactivity.
She was the first woman to win a Nobel Prize, the first person to win a Nobel Prize twice, and the only person to win a Nobel Prize in two scientific fields.
Her husband, Pierre Curie, was a co-winner of her first Nobel Prize, making them the first-ever married couple to win the Nobel Prize and launching the Curie family legacy of five Nobel Prizes.
She was, in 1906, the first woman to become a professor at the University of Paris.
"""
documents = [Document(page_content=text)]
graph_documents = llm_transformer.convert_to_graph_documents(documents)
print(f"Nodes:{graph_documents[0].nodes}")
print(f"Relationships:{graph_documents[0].relationships}")

response：
Nodes:[]
Relationships:[]

Error Message and Stack Trace (if applicable)

1

Description

help me！ According to the official example, when creating a knowledge graph using the local large model glm-4-9b-chat, the generated nodes and relationships in the graph are empty.

System Info

11

[KOBEBRYANTand]

Is isuue with the llm？