[Bug]: Example notebooks code is incorrect (not updated)

[szegad]

Do you need to file an issue?

• I have searched the existing issues and this bug is not already filed.
• My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
• I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.

Describe the bug

The example notebooks included in the github repo, for example:
#docs/examples_notebooks/local_search.ipynb
[https://microsoft.github.io/graphrag/examples_notebooks/local_search/]
seem to use incorrect, not existing classes.
I guess there were some major changes to the project structure, yet those examples are not updated.
The errors include:
ImportError: cannot import name 'ModelType' from 'graphrag.config.enums'
NameError: name 'LanceDBVectorStore' is not defined
NameError: name 'description_embedding_store' is not defined

It would be great to have working examples, especially for beginers.

Steps to reproduce

No response

Expected Behavior

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Additional Information

• GraphRAG Version:
• Operating System:
• Python Version:
• Related Issues:

[Mkamilmu]

import os
import pandas as pd
import ticker
from graphrag.vector_stores.lancedb import LanceDBVectorStore
from graphrag.config.models.graph_rag_config import ModelType
from graphrag.query.llm.text_utils import Tag

1. Fix: Corrected import path for ModelType

Previous: from graphrag.config.enums import ModelType

2. Fix: Initialize the missing embedding store variables

This prevents the "NameError: name 'description_embedding_store' is not defined"

description_embedding_store = LanceDBVectorStore(
collection_name="description_embeddings"
)
description_embedding_store.connect(db_uri="./lancedb")

3. Fix: Ensure the environment is ready for the GraphRAG pipeline

INPUT_DIR = "./inputs"
if not os.path.exists(INPUT_DIR):
os.makedirs(INPUT_DIR)

print("Imports and stores successfully initialized.")