[Issue]: Report only includes partial content for indexing multiple docs

[ReeveWu]

Is there an existing issue for this?

• [X] I have searched the existing issues
• [X] I have checked #657 to validate if my issue is covered by community support

Describe the issue

When I placed multiple txt files in the "input" folder and completed the indexing, the community reports only include the content from one of the files,. This especially happens when there is less related between the documents. However, the extraction of entities and relationships is correct. I tried prompt tuning before doing the indexing, but it doesn't seem to have any effect.

Steps to reproduce

No response

GraphRAG Config Used

encoding_model: cl100k_base
skip_workflows: []
llm:
  api_key: ${AZURE_API_KEY}
  type: azure_openai_chat
  api_base: ${AZURE_ENDPOINT}
  api_version: ${API_VERSION}
  deployment_name: gpt-4o
  model_supports_json: true

parallelization:
  stagger: 0.3

async_mode: threaded

embeddings:
  async_mode: threaded
  llm:
    api_key: ${AZURE_API_KEY}
    type: azure_openai_embedding
    api_base: ${AZURE_ENDPOINT}
    api_version: ${API_VERSION}
    deployment_name: text-embedding-ada-002

chunks:
  size: 300
  overlap: 100
  group_by_columns: [id]

input:
  type: file
  file_type: text
  base_dir: "input"
  file_encoding: utf-8
  file_pattern: ".*\\.txt$"

cache:
  type: file
  base_dir: "cache"

storage:
  type: file
  base_dir: "output/${timestamp}/artifacts"

reporting:
  type: file
  base_dir: "output/${timestamp}/reports"

entity_extraction:
  prompt: "prompts/entity_extraction.txt"
  entity_types: [organization, person, geo, event]
  max_gleanings: 0

summarize_descriptions:
  prompt: "prompts/summarize_descriptions.txt"
  max_length: 500

claim_extraction:
  prompt: "prompts/claim_extraction.txt"
  description: "Any claims or facts that could be relevant to information discovery."
  max_gleanings: 0

community_report:
  prompt: "prompts/community_report.txt"
  max_length: 2000
  max_input_length: 8000

cluster_graph:
  max_cluster_size: 10

embed_graph:
  enabled: false

umap:
  enabled: false

snapshots:
  graphml: false
  raw_entities: false
  top_level_nodes: false

local_search:
global_search:

Logs and screenshots

No response

Additional Information

• GraphRAG Version: 0.2.2
• Operating System: masOS, windows
• Python Version: 3.12.2
• Related Issues: