[Bug]: error ragflow v0.23.0 #13725
Description
Self Checks
- I have searched for existing issues search for existing issues, including closed ones.
- I confirm that I am using English to submit this report (Language Policy).
- Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) (Language Policy).
- Please do not modify this template :) and fill in all the required fields.
RAGFlow workspace code commit ID
34567
RAGFlow image version
v0.23.0
Other environment information
ragflow-gpu-1 | ]
ragflow-gpu-1 | [2026-03-20 15:32:02 +0800] [31] [INFO] 127.0.0.1:45890 GET /api/v1/datasets/e541a586242b11f1a26d7e8d48ea0d62/documents 1.1 200 2111 18646
ragflow-gpu-1 | 2026-03-20 15:32:02,236 ERROR 52 OpenAI async completion
ragflow-gpu-1 | Traceback (most recent call last):
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 481, in async_chat
ragflow-gpu-1 | return await self._async_chat(history, gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 465, in _async_chat
ragflow-gpu-1 | response = await self.async_client.chat.completions.create(model=self.model_name, messages=history, **gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 2678, in create
ragflow-gpu-1 | return await self._post(
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1794, in post
ragflow-gpu-1 | return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1594, in request
ragflow-gpu-1 | raise self._make_status_error_from_response(err.response) from None
ragflow-gpu-1 | openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,238 ERROR 52 async base giving up: **ERROR**: INVALID_REQUEST - Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,255 INFO 52 set_progress(dc4808cd242e11f19dfa7e8d48ea0d62), progress: None, progress_msg:
ragflow-gpu-1 | 2026-03-20 15:32:02,256 INFO 52Actual behavior
ragflow-gpu-1 | ]
ragflow-gpu-1 | [2026-03-20 15:32:02 +0800] [31] [INFO] 127.0.0.1:45890 GET /api/v1/datasets/e541a586242b11f1a26d7e8d48ea0d62/documents 1.1 200 2111 18646
ragflow-gpu-1 | 2026-03-20 15:32:02,236 ERROR 52 OpenAI async completion
ragflow-gpu-1 | Traceback (most recent call last):
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 481, in async_chat
ragflow-gpu-1 | return await self._async_chat(history, gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 465, in _async_chat
ragflow-gpu-1 | response = await self.async_client.chat.completions.create(model=self.model_name, messages=history, **gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 2678, in create
ragflow-gpu-1 | return await self._post(
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1794, in post
ragflow-gpu-1 | return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1594, in request
ragflow-gpu-1 | raise self._make_status_error_from_response(err.response) from None
ragflow-gpu-1 | openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,238 ERROR 52 async base giving up: ERROR: INVALID_REQUEST - Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,255 INFO 52 set_progress(dc4808cd242e11f19dfa7e8d48ea0d62), progress: None, progress_msg:
ragflow-gpu-1 | 2026-03-20 15:32:02,256 INFO 52
Expected behavior
ragflow-gpu-1 | ]
ragflow-gpu-1 | [2026-03-20 15:32:02 +0800] [31] [INFO] 127.0.0.1:45890 GET /api/v1/datasets/e541a586242b11f1a26d7e8d48ea0d62/documents 1.1 200 2111 18646
ragflow-gpu-1 | 2026-03-20 15:32:02,236 ERROR 52 OpenAI async completion
ragflow-gpu-1 | Traceback (most recent call last):
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 481, in async_chat
ragflow-gpu-1 | return await self._async_chat(history, gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 465, in _async_chat
ragflow-gpu-1 | response = await self.async_client.chat.completions.create(model=self.model_name, messages=history, **gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 2678, in create
ragflow-gpu-1 | return await self._post(
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1794, in post
ragflow-gpu-1 | return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1594, in request
ragflow-gpu-1 | raise self._make_status_error_from_response(err.response) from None
ragflow-gpu-1 | openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,238 ERROR 52 async base giving up: ERROR: INVALID_REQUEST - Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,255 INFO 52 set_progress(dc4808cd242e11f19dfa7e8d48ea0d62), progress: None, progress_msg:
ragflow-gpu-1 | 2026-03-20 15:32:02,256 INFO 52
Steps to reproduce
ragflow-gpu-1 | ]
ragflow-gpu-1 | [2026-03-20 15:32:02 +0800] [31] [INFO] 127.0.0.1:45890 GET /api/v1/datasets/e541a586242b11f1a26d7e8d48ea0d62/documents 1.1 200 2111 18646
ragflow-gpu-1 | 2026-03-20 15:32:02,236 ERROR 52 OpenAI async completion
ragflow-gpu-1 | Traceback (most recent call last):
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 481, in async_chat
ragflow-gpu-1 | return await self._async_chat(history, gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 465, in _async_chat
ragflow-gpu-1 | response = await self.async_client.chat.completions.create(model=self.model_name, messages=history, **gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 2678, in create
ragflow-gpu-1 | return await self._post(
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1794, in post
ragflow-gpu-1 | return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1594, in request
ragflow-gpu-1 | raise self._make_status_error_from_response(err.response) from None
ragflow-gpu-1 | openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,238 ERROR 52 async base giving up: **ERROR**: INVALID_REQUEST - Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,255 INFO 52 set_progress(dc4808cd242e11f19dfa7e8d48ea0d62), progress: None, progress_msg:
ragflow-gpu-1 | 2026-03-20 15:32:02,256 INFO 52Additional information
ragflow-gpu-1 | ]
ragflow-gpu-1 | [2026-03-20 15:32:02 +0800] [31] [INFO] 127.0.0.1:45890 GET /api/v1/datasets/e541a586242b11f1a26d7e8d48ea0d62/documents 1.1 200 2111 18646
ragflow-gpu-1 | 2026-03-20 15:32:02,236 ERROR 52 OpenAI async completion
ragflow-gpu-1 | Traceback (most recent call last):
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 481, in async_chat
ragflow-gpu-1 | return await self._async_chat(history, gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/rag/llm/chat_model.py", line 465, in _async_chat
ragflow-gpu-1 | response = await self.async_client.chat.completions.create(model=self.model_name, messages=history, **gen_conf, **kwargs)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 2678, in create
ragflow-gpu-1 | return await self._post(
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1794, in post
ragflow-gpu-1 | return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
ragflow-gpu-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ragflow-gpu-1 | File "/ragflow/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1594, in request
ragflow-gpu-1 | raise self._make_status_error_from_response(err.response) from None
ragflow-gpu-1 | openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,238 ERROR 52 async base giving up: ERROR: INVALID_REQUEST - Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 100000 tokens. However, you requested 211529 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}
ragflow-gpu-1 | 2026-03-20 15:32:02,255 INFO 52 set_progress(dc4808cd242e11f19dfa7e8d48ea0d62), progress: None, progress_msg:
ragflow-gpu-1 | 2026-03-20 15:32:02,256 INFO 52