[Bug]: ValueError: unexpected '{' in field name

[NathanAP]

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

I'm trying to use GRAPHRA_API.build_index to create my indexes, but I'm getting the following error:

[2025-01-23 19:21:28,418: INFO/ForkPoolWorker-1] found text files from input, found [('Ata_Reuniao_Condominio_2.pdf__0.txt', {})]
[2025-01-23 19:21:28,427: INFO/ForkPoolWorker-1] Found 1 files, loading 1
[2025-01-23 19:21:28,457: INFO/ForkPoolWorker-1] Final # of rows loaded: 1
[2025-01-23 19:21:28,551: INFO/ForkPoolWorker-1] reading table from storage: input.parquet
[2025-01-23 19:21:29,097: INFO/ForkPoolWorker-1] reading table from storage: input.parquet
[2025-01-23 19:21:29,104: INFO/ForkPoolWorker-1] reading table from storage: create_base_text_units.parquet
[2025-01-23 19:21:29,134: INFO/ForkPoolWorker-1] reading table from storage: create_base_text_units.parquet
[2025-01-23 19:21:29,405: ERROR/ForkPoolWorker-1] error extracting graph
Traceback (most recent call last):
  File "/usr/local/lib/python3.12/site-packages/graphrag/index/operations/extract_entities/graph_extractor.py", line 127, in __call__
    result = await self._process_document(text, prompt_variables)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/graphrag/index/operations/extract_entities/graph_extractor.py", line 156, in _process_document
    self._extraction_prompt.format(**{
ValueError: unexpected '{' in field name
[2025-01-23 19:21:29,407: INFO/ForkPoolWorker-1] Entity Extraction Error details={'doc_index': 0, 'text': 'Ata de Reunião do Condomínio Residencial Monte Aurora\n\nData: 04 de dezembro de 2024\n\nHorário: 20:00\n\nLocal: Auditório Privativo do Condomínio\n\n1. Abertura da Reunião\n\nA  reunião  foi  iniciada  pelo  síndico,  Sr.  Eduardo  Fontana,  pontualmente  às\n\n20:00.  Estiveram  presentes  45  moradores,  representando  75%  das  unidades,\n\nalém de representantes da administradora de condomínios LuxGest.\n\n2. Pautas Discutidas\n\n2.1 Instalação de Painéis Solares\n\nFoi apresentada a proposta de instalação de painéis solares nas áreas comuns,\n\ncom  o  objetivo  de  reduzir  os  custos  de  energia  elétrica  e  promover\n\nsustentabilidade.\n\nO  projeto  foi  aprovado  por  unanimidade,  com  um  orçamento  estimado  de  R$\n\n150.000,00, a ser financiado em 12 parcelas.\n\n2.2 Ampliação da Academia\n\nOs condôminos discutiram a necessidade de modernizar e ampliar a academia.\n\nUm  arquiteto  será  contratado  para  projetar  a  reforma,  e  os  custos  serão\n\napresentados na próxima reunião.\n\n2.3 Segurança e Monitoramento\n\nDiante  de  recentes  relatos  de  tentativas  de  invasão  na  região,  foi  aprovada  a\n\n\x0cimplementação  de  novas  câmeras  de  segurança  e  a  contratação  de  uma\n\nempresa de monitoramento 24 horas.\n\nO  investimento  inicial  será  de  R$  25.000,00,  com  uma  taxa  mensal  de  R$\n\n3.500,00.\n\n2.4 Regras para Uso do Spa e Sauna\n\nMoradores sugeriram melhorias nas regras de agendamento e higiene do spa e\n\nsauna.  Decidiu-se  criar  um  sistema  online  de  reservas  e  exigir  o  uso\n\nobrigatório de toalhas para proteção dos assentos.\n\n3. Encerramento\n\nO síndico agradeceu a presença e participação de todos e encerrou a reunião\n\nàs 22:15.\n\nA próxima reunião foi marcada para o dia 10 de março de 2025.\n\nAssinam a presente ata'}
[2025-01-23 19:21:29,411: ERROR/ForkPoolWorker-1] error extracting graph
Traceback (most recent call last):
  File "/usr/local/lib/python3.12/site-packages/graphrag/index/operations/extract_entities/graph_extractor.py", line 127, in __call__
    result = await self._process_document(text, prompt_variables)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/graphrag/index/operations/extract_entities/graph_extractor.py", line 156, in _process_document
    self._extraction_prompt.format(**{
ValueError: unexpected '{' in field name
[2025-01-23 19:21:29,412: INFO/ForkPoolWorker-1] Entity Extraction Error details={'doc_index': 0, 'text': 'um  sistema  online  de  reservas  e  exigir  o  uso\n\nobrigatório de toalhas para proteção dos assentos.\n\n3. Encerramento\n\nO síndico agradeceu a presença e participação de todos e encerrou a reunião\n\nàs 22:15.\n\nA próxima reunião foi marcada para o dia 10 de março de 2025.\n\nAssinam a presente ata:\n\n__________________________        __________________________\n\nSíndico  Eduardo  Fontana                      Moradora  Mariana  Torres,  Secretária  da\n\nReunião'}
[2025-01-23 19:21:29,416: ERROR/ForkPoolWorker-1] error running workflow extract_graph
Traceback (most recent call last):
  File "/usr/local/lib/python3.12/site-packages/graphrag/index/run/run_workflows.py", line 166, in _run_workflows
    result = await run_workflow(
             ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/graphrag/index/workflows/extract_graph.py", line 45, in run_workflow
    base_entity_nodes, base_relationship_edges = await extract_graph(
                                                 ^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/graphrag/index/flows/extract_graph.py", line 33, in extract_graph
    entities, relationships = await extract_entities(
                              ^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/graphrag/index/operations/extract_entities/extract_entities.py", line 136, in extract_entities
    entities = _merge_entities(entity_dfs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/graphrag/index/operations/extract_entities/extract_entities.py", line 168, in _merge_entities
    all_entities.groupby(["title", "type"], sort=False)
  File "/usr/local/lib/python3.12/site-packages/pandas/core/frame.py", line 9183, in groupby
    return DataFrameGroupBy(
           ^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pandas/core/groupby/groupby.py", line 1329, in __init__
    grouper, exclusions, obj = get_grouper(
                               ^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/site-packages/pandas/core/groupby/grouper.py", line 1043, in get_grouper
    raise KeyError(gpr)
KeyError: 'title'
[2025-01-23 19:21:29,425: INFO/ForkPoolWorker-1] Error running pipeline! details=None
[2025-01-23 19:21:29,506: ERROR/MainProcess] Task handler raised error: WorkerLostError('Worker exited prematurely: exitcode 0 Job: 0.')
Traceback (most recent call last):
  File "/usr/local/lib/python3.12/site-packages/billiard/pool.py", line 1265, in mark_as_worker_lost
    raise WorkerLostError(
billiard.einfo.ExceptionWithTraceback: 
"""
Traceback (most recent call last):
  File "/usr/local/lib/python3.12/site-packages/billiard/pool.py", line 1265, in mark_as_worker_lost
    raise WorkerLostError(
billiard.exceptions.WorkerLostError: Worker exited prematurely: exitcode 0 Job: 0.

Steps to reproduce

I'm not sure if this is important tbh, but I'm using the following:

graphrag_config = create_graphrag_config(
  values=settings,
  root_dir=source_path,
)
index_result: List[PipelineRunResult] = await GraphRAG_API.build_index(config=graphrag_config)

Please let me know if I'm doing anything wrong.

Expected Behavior

My documents should be indexed.

GraphRAG Config Used

async_mode: threaded
basic_search:
  prompt: prompts/basic_search_system_prompt.txt
cache:
  base_dir: cache
  type: file
chunks:
  group_by_columns:
  - id
  overlap: 0
  size: 600
claim_extraction:
  description: Any claims or facts that could be relevant to information discovery.
  enabled: false
  max_gleanings: 1
  prompt: prompts/claim_extraction.txt
cluster_graph:
  max_cluster_size: 10
community_reports:
  max_input_length: 8000
  max_length: 2000
  prompt: prompts/community_report.txt
drift_search:
  prompt: prompts/drift_search_system_prompt.txt
  reduce_prompt: prompts/drift_search_reduce_prompt.txt
embed_graph:
  enabled: false
embeddings:
  async_mode: threaded
  llm:
    api_key: ${GRAPHRAG_API_KEY}
    model: text-embedding-3-small
    type: openai_embedding
  vector_store:
    collection_name: default
    db_uri: output/lancedb
    overwrite: true
    type: lancedb
encoding_model: cl100k_base
entity_extraction:
  entity_types:
  - organization
  - person
  - geo
  - event
  max_gleanings: 1
  prompt: prompts/entity_extraction.txt
global_search:
  knowledge_prompt: prompts/global_search_knowledge_system_prompt.txt
  map_prompt: prompts/global_search_map_system_prompt.txt
  reduce_prompt: prompts/global_search_reduce_system_prompt.txt
input:
  base_dir: input
  file_encoding: utf-8
  file_pattern: .*\.txt$
  file_type: text
  type: file
llm:
  api_key: ${GRAPHRAG_API_KEY}
  model: gpt-4o-mini
  model_supports_json: true
  type: openai_chat
local_search:
  prompt: prompts/local_search_system_prompt.txt
parallelization:
  stagger: 0.3
reporting:
  base_dir: logs
  type: file
skip_workflows: []
snapshots:
  embeddings: false
  graphml: false
  transient: false
storage:
  base_dir: output
  type: file
summarize_descriptions:
  max_length: 500
  prompt: prompts/summarize_descriptions.txt
umap:
  enabled: false
update_index_storage: null

Logs and screenshots

No response

Additional Information

• GraphRAG Version: 1.2.0
• Operating System: Linux
• Python Version: 3.12
• Related Issues: I didn't find any