How to achieve hierarchical summary generation for community reports?

[YueAn329]

Do you need to file an issue?

• [x] 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.
• [x] I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.

Describe the bug

How to achieve hierarchical summary generation for community reports? When I was reading the code, I found that the summary of the community report was not associated with sub - communities. It presented as an independent community summary. As shown in the following code implementation, the parameter reports of level_context_builder is always empty, making the parameter community_hierarchy useless. Please tell me how to understand and implement bottom - up hierarchical abstraction to generate community summaries.

async def summarize_communities(
    nodes: pd.DataFrame,
    communities: pd.DataFrame,
    local_contexts,
    level_context_builder: Callable,
    callbacks: WorkflowCallbacks,
    cache: PipelineCache,
    strategy: dict,
    max_input_length: int,
    async_mode: AsyncType = AsyncType.AsyncIO,
    num_threads: int = 4,
):
    """Generate community summaries."""
    reports: list[CommunityReport | None] = []
    tick = progress_ticker(callbacks.progress, len(local_contexts))
    strategy_exec = load_strategy(strategy["type"])
    strategy_config = {**strategy}

    # if max_retries is not set, inject a dynamically assigned value based on the total number of expected LLM calls to be made
    if strategy_config.get("llm") and strategy_config["llm"]["max_retries"] == -1:
        strategy_config["llm"]["max_retries"] = len(nodes)

    community_hierarchy = (
        communities.explode("children")
        .rename({"children": "sub_community"}, axis=1)
        .loc[:, ["community", "level", "sub_community"]]
    ).dropna()

    levels = get_levels(nodes)

    level_contexts = []
    for level in levels:
        level_context = level_context_builder(
            pd.DataFrame(reports),
            community_hierarchy_df=community_hierarchy,
            local_context_df=local_contexts,
            level=level,
            max_context_tokens=max_input_length,
        )
        level_contexts.append(level_context)

    for level_context in level_contexts:

        async def run_generate(record):
            result = await _generate_report(
                strategy_exec,
                community_id=record[schemas.COMMUNITY_ID],
                community_level=record[schemas.COMMUNITY_LEVEL],
                community_context=record[schemas.CONTEXT_STRING],
                callbacks=callbacks,
                cache=cache,
                strategy=strategy_config,
            )
            tick()
            return result

        local_reports = await derive_from_rows(
            level_context,
            run_generate,
            callbacks=NoopWorkflowCallbacks(),
            num_threads=num_threads,
            async_type=async_mode,
        )
        reports.extend([lr for lr in local_reports if lr is not None])

    return pd.DataFrame(reports)

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: