[Bug]: Notebook examples for global/local/drift search are outdated since V2.0.0 is released.

[icejean]

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 method to initialize a chat or embedding model is changed in V2.0.0, so the example notebooks can't run any longer. These lines will lead to exceptions:

from graphrag.query.llm.oai.chat_openai import ChatOpenAI
from graphrag.query.llm.oai.typing import OpenaiApiType

Waiting for updates. 8-）

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:

[nanda-rani]

I'm also facing the same issue. Any idea on how to change the package import??

[ricky-bug]

`from pathlib import Path
import asyncio

import pandas as pd
import graphrag.api as api
from graphrag.config.load_config import load_config
config = load_config(
root_dir=Path("."),
config_filepath=Path("settings.yaml")
)

INPUT_DIR = "./inputs"
LANCEDB_URI = f"./output/lancedb"

NODES_TABLE = "create_final_nodes"
COMMUNITY_REPORT_TABLE = "create_final_community_reports"
COMMUNITY_TABLE = "create_final_communities"
ENTITY_TABLE = "create_final_entities"
RELATIONSHIP_TABLE = "create_final_relationships"
COVARIATE_TABLE = "create_final_covariates"
TEXT_UNIT_TABLE = "create_final_text_units"
COMMUNITY_LEVEL = 2

read nodes table to get community and degree data

entity_df = pd.read_parquet(f"output/{ENTITY_TABLE}.parquet")
community_df = pd.read_parquet(f"output/{COMMUNITY_TABLE}.parquet")
nodes_df = pd.read_parquet(f"output/{NODES_TABLE}.parquet")
relationship_df = pd.read_parquet(f"output/{RELATIONSHIP_TABLE}.parquet")
text_unit_df = pd.read_parquet(f"output/{TEXT_UNIT_TABLE}.parquet")
covariates_df = pd.read_parquet(f"output/{COVARIATE_TABLE}.parquet")

community_report_df = pd.read_parquet(f"output/{COMMUNITY_REPORT_TABLE}.parquet")

query = "Your query can put here"
response, context_data = asyncio.run(
api.local_search(
config=config,
nodes=nodes_df,
entities=entity_df,
community_reports=community_report_df,
text_units=text_unit_df,
relationships=relationship_df,
covariates=covariates_df,
community_level=COMMUNITY_LEVEL,
response_type="Multiple Paragraphs",
query=query,
)
)
print(response)`

[ricky-bug]

You can check other search in "api" folder