[Bug]: <title>FileNotFoundError: Table default-community-full_content does not exist

[HENScience]

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 following error is displayed when creating an index and executing to flows.generate_text_embeddings:
15:11:42,754 graphrag.index.run.run_workflows ERROR error running workflow generate_text_embeddings
Traceback (most recent call last):
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1195, in open
tbl.version
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1237, in version
return self._dataset.version
^^^^^^^^^^^^^
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1210, in _dataset
return self._ref.dataset
^^^^^^^^^^^^^^^^^
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1086, in dataset
self.dataset = lance.dataset(
^^^^^^^^^^^^^^
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lance_init.py", line 107, in dataset
ds = LanceDataset(
^^^^^^^^^^^^^
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lance\dataset.py", line 171, in init
self._ds = _Dataset(
^^^^^^^^^
ValueError: Dataset at path E:/data/graphrag/index/books/output/lancedb/default-community-full_content.lance was not found: Not found: E:/data/graphrag/index/books/output/lancedb/default-community-full_content.lance/_versions, D:\a\lance\lance\rust\lance-table\src\io\commit.rs:286:23, D:\a\lance\lance\rust\lance\src\dataset\builder.rs:317:35

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\run\run_workflows.py", line 166, in _run_workflows
result = await run_workflow(
^^^^^^^^^^^^^^^^^^^
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\workflows\generate_text_embeddings.py", line 45, in run_workflow
await generate_text_embeddings(
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\flows\generate_text_embeddings.py", line 98, in generate_text_embeddings
await _run_and_snapshot_embeddings(
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\flows\generate_text_embeddings.py", line 121, in _run_and_snapshot_embeddings
data["embedding"] = await embed_text(
^^^^^^^^^^^^^^^^^
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\operations\embed_text\embed_text.py", line 89, in embed_text
return await _text_embed_with_vector_store(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\operations\embed_text\embed_text.py", line 206, in _text_embed_with_vector_store
vector_store.load_documents(documents, overwrite and i == 0)
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\vector_stores\lancedb.py", line 76, in load_documents
self.document_collection = self.db_connection.open_table(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\db.py", line 445, in open_table
return LanceTable.open(self, name, index_cache_size=index_cache_size)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1198, in open
raise FileNotFoundError(f"Table {name} does not exist")
FileNotFoundError: Table default-community-full_content does not exist
15:11:42,762 graphrag.callbacks.file_workflow_callbacks INFO Error running pipeline! details=None
15:11:42,908 graphrag.cli.index ERROR Errors occurred during the pipeline run, see logs for more details.

### logs.json:
{
"type": "error",
"data": "Error running pipeline!",
"stack": "Traceback (most recent call last):\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1195, in open\n tbl.version\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1237, in version\n return self._dataset.version\n ^^^^^^^^^^^^^\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1210, in _dataset\n return self._ref.dataset\n ^^^^^^^^^^^^^^^^^\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1086, in dataset\n self._dataset = lance.dataset(\n ^^^^^^^^^^^^^^\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lance\init.py", line 107, in dataset\n ds = LanceDataset(\n ^^^^^^^^^^^^^\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lance\dataset.py", line 171, in init\n self._ds = _Dataset(\n ^^^^^^^^^\nValueError: Dataset at path E:/data/graphrag/index/books/output/lancedb/default-community-full_content.lance was not found: Not found: E:/data/graphrag/index/books/output/lancedb/default-community-full_content.lance/_versions, D:\a\lance\lance\rust\lance-table\src\io\commit.rs:286:23, D:\a\lance\lance\rust\lance\src\dataset\builder.rs:317:35\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\run\run_workflows.py", line 166, in _run_workflows\n result = await run_workflow(\n ^^^^^^^^^^^^^^^^^^^\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\workflows\generate_text_embeddings.py", line 45, in run_workflow\n await generate_text_embeddings(\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\flows\generate_text_embeddings.py", line 98, in generate_text_embeddings\n await _run_and_snapshot_embeddings(\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\flows\generate_text_embeddings.py", line 121, in _run_and_snapshot_embeddings\n data["embedding"] = await embed_text(\n ^^^^^^^^^^^^^^^^^\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\operations\embed_text\embed_text.py", line 89, in embed_text\n return await _text_embed_with_vector_store(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\index\operations\embed_text\embed_text.py", line 206, in _text_embed_with_vector_store\n vector_store.load_documents(documents, overwrite and i == 0)\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\graphrag\vector_stores\lancedb.py", line 76, in load_documents\n self.document_collection = self.db_connection.open_table(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\db.py", line 445, in open_table\n return LanceTable.open(self, name, index_cache_size=index_cache_size)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "D:\software\Anaconda3\envs\graphrag\Lib\site-packages\lancedb\table.py", line 1198, in open\n raise FileNotFoundError(f"Table {name} does not exist")\nFileNotFoundError: Table default-community-full_content does not exist\n",
"source": "Table default-community-full_content does not exist",
"details": null
}

Steps to reproduce

No response

Expected Behavior

No response

GraphRAG Config Used

# Paste your config here
parallelization:
  stagger: 0.3
  num_threads: 20

async_mode: asyncio # or asyncio/threaded
    
embeddings:
  async_mode: asyncio # or asyncio/threaded
  parallelization:
    num_threads: 10
  batch_max_tokens: 8192
  vector_store: 
    type: lancedb
    db_uri: 'output\lancedb'
    container_name: default
    overwrite: false
  llm:
    api_key: XXXX
    type: azure_openai_embedding # or openai_embedding
    model: text-embedding-3-large
    api_base: XXXX
    api_version: XXXX
    deployment_name: text-embedding-3-large

### Input settings ###

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

chunks:
  size: 1200   # 是token的大小
  overlap: 30
  group_by_columns: [id]

### Storage settings ###
## If blob storage is specified in the following four sections,
## connection_string and container_name must be provided

cache:
  type: file # or blob
  base_dir: "cache"

reporting:
  type: file # or console, blob
  base_dir: "logs"

storage:
  type: file # or blob
  base_dir: "output"

## only turn this on if running `graphrag index` with custom settings
## we normally use `graphrag update` with the defaults
update_index_storage:
  # type: file # or blob
  # base_dir: "update_output"

### Workflow settings ###

skip_workflows: []

entity_extraction:
  prompt: "prompts/entity_extraction.txt"
  entity_types: [organization,person,geo,event]
  max_gleanings: 1
  # strategy: 
  #   type: nltk

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

claim_extraction:
  enabled: true
  prompt: "prompts/claim_extraction.txt"
  description: "Any claims or facts that could be relevant to information discovery."
  max_gleanings: 1

community_reports:
  prompt: "prompts/community_report.txt"
  max_length: 1000
  max_input_length: 2000

cluster_graph:
  max_cluster_size: 10

embed_graph:
  enabled: false # if true, will generate node2vec embeddings for nodes

umap:
  enabled: false # if true, will generate UMAP embeddings for nodes

snapshots:
  graphml: true
  embeddings: false
  transient: false

### Query settings ###
## The prompt locations are required here, but each search method has a number of optional knobs that can be tuned.
## See the config docs: https://microsoft.github.io/graphrag/config/yaml/#query

local_search:
  prompt: "prompts/local_search_system_prompt.txt"

global_search:
  map_prompt: "prompts/global_search_map_system_prompt.txt"
  reduce_prompt: "prompts/global_search_reduce_system_prompt.txt"
  knowledge_prompt: "prompts/global_search_knowledge_system_prompt.txt"

drift_search:
  prompt: "prompts/drift_search_system_prompt.txt"

Logs and screenshots

No response

Additional Information

• GraphRAG Version: v1.2.0
• Operating System: Windows11
• Python Version: 3.12.8
• Related Issues: