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 issue
When I execute the command 'python - m graphrag. query -- root./ragtest -- method local "..."', the error is as follows:
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in _run_code
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/site-packages/graphrag/query/main.py", line 86, in
run_local_search(
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/site-packages/graphrag/query/cli.py", line 98, in run_local_search
return asyncio.run(
^^^^^^^^^^^^
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/asyncio/runners.py", line 190, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/asyncio/base_events.py", line 654, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/site-packages/graphrag/query/api.py", line 172, in local_search
description_embedding_store = __get_embedding_description_store(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/site-packages/graphrag/query/api.py", line 62, in __get_embedding_description_store
store_entity_semantic_embeddings(
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/site-packages/graphrag/query/input/loaders/dfs.py", line 91, in store_entity_semantic_embeddings
vectorstore.load_documents(documents=documents)
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/site-packages/graphrag/vector_stores/lancedb.py", line 55, in load_documents
self.document_collection = self.db_connection.create_table(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/site-packages/lancedb/db.py", line 417, in create_table
tbl = LanceTable.create(
^^^^^^^^^^^^^^^^^^
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/site-packages/lancedb/table.py", line 1578, in create
lance.write_dataset(empty, tbl._dataset_uri, schema=schema, mode=mode)
File "/CSTemp/fishfield/Anaconda3/envs/ragtest/lib/python3.11/site-packages/lance/dataset.py", line 2644, in write_dataset
inner_ds = _write_dataset(reader, uri, params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: LanceError(IO): Generic LocalFileSystem error: Unable to copy file from /CSTemp/zk/GraphragTest-main/lancedb/entity_description_embeddings.lance/_versions/1.manifest-ea6604dc-cbb6-4d09-acd6-bf517decb9ee to /CSTemp/zk/GraphragTest-main/lancedb/entity_description_embeddings.lance/_latest.manifest: Device or resource busy (os error 16), /home/runner/work/lance/lance/rust/lance-table/src/io/commit.rs:240:5
Steps to reproduce
No response
GraphRAG Config Used
# Paste your config here
Logs and screenshots
No response
Additional Information
- GraphRAG Version:
- Operating System:
- Python Version:
- Related Issues:
你能为这个issue提供更多的描述吗？ @wangruidedie
你能为这个issue提供更多的描述吗？ @wangruidedie
已经提供全部信息了，我感觉是我们服务器环境的问题，我在我的本地和另外一台服务器上并没有这个问题
according to https://github.com/lancedb/lancedb/issues/1630
It sounds like you are using a filesystem that doesn't support hard link. That is required for LanceDB to function. You should > either mount a fully-featured filesystem, or connect to an object storage service.
I encountered this issue while running graphrag in WSL environment and I stored the lancedb windows volumes (/mnt/e/graphrag). After moving the folder to Linux directory (~/graphrag), I didn't encounter this issue anymore.
according to https://github.com/lancedb/lancedb/issues/1630
It sounds like you are using a filesystem that doesn't support hard link. That is required for LanceDB to function. You should > either mount a fully-featured filesystem, or connect to an object storage service.
I encountered this issue while running graphrag in WSL environment and I stored the lancedb windows volumes (/mnt/e/graphrag). After moving the folder to Linux directory (~/graphrag), I didn't encounter this issue anymore.
Me too, it works fine on Linux but not on Windows.
microsoft
