limit_async Exception During Ingestion

[deepblue523]

Hi everyone!

I am wondering if you can help with an exception I am getting while ingesting documents. It occurs for every document type and I am including just one of the exceptions. I am running LightRAG v1.3.7.

• I am using Python 3.11.0.

• I am running everything on CPU as I have only integrated Intel graphics right now. Things are slow.

• I have Ollama installed with the following models:

   bge-m3:latest
   mistral-nemo:latest
   mistral:7b-instruct-q4_K_M
   mistral:latest
  

Seems to be related to limit_async, which I'm guessing is a throttle value. Maybe the value is too high, given my poor performance?
Thoughts?

INFO: Successfully fetched and enqueued file: Project Clarity and Direction.docx
INFO: Processing 1 document(s)
INFO: Extracting stage 1/1: Project Clarity and Direction.docx
INFO: Processing d-id: doc-892c3d9e152974fed05ff331b35eeb14
INFO: limit_async: 16 new workers initialized
INFO: limit_async: 4 new workers initialized
ERROR: limit_async: Error in decorated function:
ERROR: Failed to extract entities and relationships:
ERROR: Traceback (most recent call last):
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpx_transports\default.py", line 101, in map_httpcore_exceptions
yield
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpx_transports\default.py", line 394, in handle_async_request
resp = await self._pool.handle_async_request(req)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpcore_async\connection_pool.py", line 256, in handle_async_request
raise exc from None
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpcore_async\connection_pool.py", line 236, in handle_async_request
response = await connection.handle_async_request(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpcore_async\connection.py", line 103, in handle_async_request
return await self._connection.handle_async_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpcore_async\http11.py", line 136, in handle_async_request
raise exc
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpcore_async\http11.py", line 106, in handle_async_request
) = await self._receive_response_headers(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpcore_async\http11.py", line 177, in _receive_response_headers
event = await self._receive_event(timeout=timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpcore_async\http11.py", line 217, in _receive_event
data = await self._network_stream.read(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpcore_backends\anyio.py", line 32, in read
with map_exceptions(exc_map):
File "C:\Program Files\Python311\Lib\contextlib.py", line 155, in exit
self.gen.throw(typ, value, traceback)
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpcore_exceptions.py", line 14, in map_exceptions
raise to_exc(exc) from exc
httpcore.ReadTimeout

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "c:\users\jkessl78\lightrag\lightrag\lightrag.py", line 1002, in process_document
await asyncio.gather(*tasks)
File "c:\users\jkessl78\lightrag\lightrag\lightrag.py", line 1200, in _process_entity_relation_graph
raise e
File "c:\users\jkessl78\lightrag\lightrag\lightrag.py", line 1186, in _process_entity_relation_graph
chunk_results = await extract_entities(
^^^^^^^^^^^^^^^^^^^^^^^
File "c:\users\jkessl78\lightrag\lightrag\operate.py", line 853, in extract_entities
raise task.exception()
File "c:\users\jkessl78\lightrag\lightrag\operate.py", line 829, in process_with_semaphore
return await process_single_content(chunk)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\users\jkessl78\lightrag\lightrag\operate.py", line 754, in process_single_content
final_result = await use_llm_func_with_cache(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\users\jkessl78\lightrag\lightrag\utils.py", line 1648, in use_llm_func_with_cache
res: str = await use_llm_func(input_text, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\users\jkessl78\lightrag\lightrag\utils.py", line 586, in wait_func
return await future
^^^^^^^^^^^^
File "c:\users\jkessl78\lightrag\lightrag\utils.py", line 370, in worker
result = await func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\users\jkessl78\lightrag\lightrag\llm\ollama.py", line 130, in ollama_model_complete
return await ollama_model_if_cache(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\tenacity\asyncio_init.py", line 189, in async_wrapped
return await copy(fn, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\tenacity\asyncio_init.py", line 111, in call
do = await self.iter(retry_state=retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\tenacity\asyncio_init.py", line 153, in iter
result = await action(retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\tenacity_utils.py", line 99, in inner
return call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\tenacity_init.py", line 400, in
self._add_action_func(lambda rs: rs.outcome.result())
^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python311\Lib\concurrent\futures_base.py", line 449, in result
return self.__get_result()
^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python311\Lib\concurrent\futures_base.py", line 401, in __get_result
raise self.exception
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\tenacity\asyncio_init.py", line 114, in call
result = await fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\users\jkessl78\lightrag\lightrag\llm\ollama.py", line 109, in _ollama_model_if_cache
raise e
File "c:\users\jkessl78\lightrag\lightrag\llm\ollama.py", line 72, in _ollama_model_if_cache
response = await ollama_client.chat(model=model, messages=messages, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\ollama_client.py", line 837, in chat
return await self._request(
^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\ollama_client.py", line 682, in _request
return cls((await self._request_raw(*args, **kwargs)).json())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\ollama_client.py", line 622, in _request_raw
r = await self._client.request(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpx_client.py", line 1540, in request
return await self.send(request, auth=auth, follow_redirects=follow_redirects)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpx_client.py", line 1629, in send
response = await self._send_handling_auth(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpx_client.py", line 1657, in _send_handling_auth
response = await self._send_handling_redirects(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpx_client.py", line 1694, in _send_handling_redirects
response = await self._send_single_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpx_client.py", line 1730, in _send_single_request
response = await transport.handle_async_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpx_transports\default.py", line 393, in handle_async_request
with map_httpcore_exceptions():
File "C:\Program Files\Python311\Lib\contextlib.py", line 155, in exit
self.gen.throw(typ, value, traceback)
File "C:\Users\jkessl78\LightRAG\venv\Lib\site-packages\httpx_transports\default.py", line 118, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.ReadTimeout

ERROR: Failed to extrat document 1/1: Project Clarity and Direction.docx
INFO: Document processing pipeline completed

[ntsarb]

Check this issue. I think it's the same issue. Changing the timeout setting to NONE worked for me:

Time out in seconds for LLM, None for infinite timeout

TIMEOUT=None