session seems to expire while instantiating graph store

[jezieljones]

Please check the FAQ documentation before raising an issue

Describe the bug (required)
Upon running the python script to create a knowledge graph, I keep getting an error which seems as if a session keeps ending.

Your Environments (required)

• OS: uname -a
  23.2.0 Darwin Kernel Version 23.2.0: Wed Nov 15 21:53:34 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T8103 arm64
• Compiler: g++ --version or clang++ --version
  g++ (Homebrew GCC 11.4.0) 11.4.0

Apple clang version 15.0.0 (clang-1500.3.9.4)
Target: arm64-apple-darwin23.2.0
Thread model: posix
InstalledDir: /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin

How To Reproduce(required)

Steps to reproduce the behavior:

1. Step 1 - install required packages including nebula-u
2. Step 2 - run the following python (i'm running with python3 run_graph.py)

import os
import logging
import sys

logging.basicConfig(
    stream=sys.stdout, level=logging.INFO
)

from llama_index.core import (
    VectorStoreIndex,
    SimpleDirectoryReader,
    KnowledgeGraphIndex,
    ServiceContext,
)
from llama_index.core import Settings
from llama_index.core import StorageContext


from IPython.display import Markdown, display
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.core.node_parser import SentenceSplitter
from llama_index.llms.openai import OpenAI
from llama_index.graph_stores.nebula import NebulaGraphStore


os.environ["OPENAI_API_KEY"] = ""
os.environ["NEBULA_USER"] = "root"
os.environ["NEBULA_PASSWORD"] = "nebula"
os.environ["NEBULA_ADDRESS"] = "127.0.0.1:9669"


documents = SimpleDirectoryReader(
    "./data"
).load_data()

# define LLM
llm = OpenAI(temperature=0, model="gpt-3.5-turbo")

Settings.llm = OpenAI(model="gpt-3.5-turbo")
Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small")
Settings.node_parser = SentenceSplitter(chunk_size=256, chunk_overlap=20)
Settings.num_output = 256
Settings.context_window = 3900

space_name = "vc_persona"
edge_types, rel_prop_names = ["relationship"], ["relationship"]  # default, could be omit if create from an empty kg
tags = ["entity"]  # default, could be omit if create from an empty kg

graph_store = NebulaGraphStore(
    space_name=space_name,
    edge_types=edge_types,
    rel_prop_names=rel_prop_names,
    tags=tags)

storage_context = StorageContext.from_defaults(graph_store=graph_store)

index = KnowledgeGraphIndex.from_documents(
    documents,
    storage_context=storage_context,
    max_triplets_per_chunk=5,
    space_name=space_name,
    edge_types=edge_types,
    rel_prop_names=rel_prop_names,
    tags=tags,
    include_embeddings=True,
)

index.storage_context.persist(persist_dir='./storage_graph')

3. Step 3
   wait for about 10 seconds while embeddings and chat completions run. Then see failure

Expected behavior

Graph should store successfully

I have tried dozens of times running the graph on the paul graham dataset, and it continues to fail. Here is the full stack trace:

INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" Exception ignored in: <function NebulaGraphStore.__del__ at 0x154b63ba0> Traceback (most recent call last): File "/Users/jezieljones/Development/nebulagraph/nebulagraph/lib/python3.12/site-packages/llama_index/graph_stores/nebula/nebula_graph_store.py", line 242, in __del__ File "/Users/jezieljones/Development/nebulagraph/nebulagraph/lib/python3.12/site-packages/nebula3/gclient/net/SessionPool.py", line 326, in close File "/Users/jezieljones/Development/nebulagraph/nebulagraph/lib/python3.12/site-packages/nebula3/gclient/net/Session.py", line 351, in _sign_out File "/Users/jezieljones/Development/nebulagraph/nebulagraph/lib/python3.12/site-packages/nebula3/gclient/net/Connection.py", line 258, in signout File "/Users/jezieljones/Development/nebulagraph/nebulagraph/lib/python3.12/site-packages/nebula3/graph/GraphService.py", line 1603, in signout File "/Users/jezieljones/Development/nebulagraph/nebulagraph/lib/python3.12/site-packages/nebula3/graph/GraphService.py", line 1606, in send_signout AttributeError: 'NoneType' object has no attribute 'CALL'

Additional context

[jezieljones]

Looking into the stacktrace, this seems to be an issue with graphd session closing prematurely, but it's unclear where exactly to set a longer session timeout. This makes it very difficutl to build a knowledge graph on text longer than a few words.

[jezieljones]

@wey-gu any ideas on solution or debugging to this one?