Description
Is there an existing issue for the same bug?
- I have checked the existing issues.
RAGFlow workspace code commit ID
n/a
RAGFlow image version
nightly(v0.15.0-17-g35580af8 full)
Other environment information
Ubuntu 24
Ragflow nightly with infinity doc engine
Actual behavior
*The parsing process was hanging up without any error message in the front page.
while, in the backend, there are a lot of LLMBundle.encode error, seems it can't update the LLM token usage data.
*My task info list below. And, the LLM status is good. it's really make me confused.
2024-12-22 00:50:35,739 INFO 20 task_consumer_0 reported heartbeat: {"name": "task_consumer_0", "now": "2024-12-22T00:50:35.737928", "boot_at": "2024-12-22T00:46:35.409047", "pending": 1, "lag": 38, "done": 133, "failed": 0, "current": {"id": "61e542aabfbb11efab780242ac150006", "doc_id": "59bb2120bfa311efb8850242ac150006", "from_page": 0, "to_page": 12, "retry_count": 0, "kb_id": "eb856922bfa211ef97d60242ac150006", "parser_id": "book", "parser_config": {"auto_keywords": 3, "auto_questions": 1, "raptor": {"use_raptor": true, "prompt": "\u8bf7\u603b\u7ed3\u4ee5\u4e0b\u6bb5\u843d\u3002 \u5c0f\u5fc3\u6570\u5b57\uff0c\u4e0d\u8981\u7f16\u9020\u3002 \u6bb5\u843d\u5982\u4e0b\uff1a\n {cluster_content}\n\u4ee5\u4e0a\u5c31\u662f\u4f60\u9700\u8981\u603b\u7ed3\u7684\u5185\u5bb9\u3002", "max_token": 512, "threshold": 0.1, "max_cluster": 64, "random_seed": 0}}, "name": "2023\u5e74\u7248GMP\u6307\u5357-\u8d28\u91cf\u7ba1\u7406\u4f53\u7cfb.pdf", "type": "pdf", "location": "2023\u5e74\u7248GMP\u6307\u5357-\u8d28\u91cf\u7ba1\u7406\u4f53\u7cfb.pdf", "size": 7081164, "tenant_id": "dd78793cbfa211efaa260242ac150006", "language": "Chinese", "embd_id": "nomic-ai/nomic-embed-text-v1.5@FastEmbed", "pagerank": 10, "img2txt_id": "", "asr_id": "", "llm_id": "Qwen/Qwen2-7B-Instruct@SILICONFLOW", "update_time": 1734799699414}}
*Trying to change to the other LLM, error message is the same.
2024-12-22 01:06:57,576 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: None, progress_msg: Page(2537): Generate 94 chunks37): Embedding chunks (2.82s)
2024-12-22 01:06:57,787 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 304
2024-12-22 01:06:57,789 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.601063829787234, progress_msg:
2024-12-22 01:06:57,924 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 304
2024-12-22 01:06:57,928 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.6180851063829788, progress_msg:
2024-12-22 01:06:58,064 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 304
2024-12-22 01:06:58,067 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.6351063829787233, progress_msg:
2024-12-22 01:06:58,203 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 304
2024-12-22 01:06:58,206 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.652127659574468, progress_msg:
2024-12-22 01:06:58,344 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 304
2024-12-22 01:06:58,347 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.6691489361702128, progress_msg:
2024-12-22 01:06:58,477 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 266
2024-12-22 01:06:58,480 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.6861702127659575, progress_msg:
2024-12-22 01:06:58,820 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 736
2024-12-22 01:06:58,823 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.702127659574468, progress_msg:
2024-12-22 01:06:59,281 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 784
2024-12-22 01:06:59,285 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.7361702127659574, progress_msg:
2024-12-22 01:06:59,489 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 432
2024-12-22 01:06:59,492 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.7702127659574468, progress_msg:
2024-12-22 01:06:59,863 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 816
2024-12-22 01:06:59,866 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.8042553191489361, progress_msg:
2024-12-22 01:07:00,133 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 624
2024-12-22 01:07:00,136 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.8382978723404255, progress_msg:
2024-12-22 01:07:00,390 ERROR 19 LLMBundle.encode can't update token usage for dd78793cbfa211efaa260242ac150006/EMBEDDING used_tokens: 588
2024-12-22 01:07:00,393 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: 0.8723404255319148, progress_msg:
2024-12-22 01:07:00,400 INFO 19 Embedding chunks (2.82s)
2024-12-22 01:07:00,403 INFO 19 set_progress(512598e6bfbd11efb3870242ac150006), progress: None, progress_msg: Page(25
2024-12-22 01:07:00,414 INFO 19 INFINITY created table ragflow_dd78793cbfa211efaa260242ac150006_eb856922bfa211ef97d60242ac150006, vector size 768
2024-12-22 01:07:15,590 INFO 19 task_consumer_0 reported heartbeat: {"name": "task_consumer_0", "now": "2024-12-22T01:07:15.589376", "boot_at": "2024-12-22T01:03:45.295776", "pending": 1, "lag": 36, "done": 41, "failed": 0, "current": {"id": "512598e6bfbd11efb3870242ac150006", "doc_id": "59bb2120bfa311efb8850242ac150006", "from_page": 24, "to_page": 36, "retry_count": 0, "kb_id": "eb856922bfa211ef97d60242ac150006", "parser_id": "book", "parser_config": {"auto_keywords": 3, "auto_questions": 1, "raptor": {"use_raptor": true, "prompt": "\u8bf7\u603b\u7ed3\u4ee5\u4e0b\u6bb5\u843d\u3002 \u5c0f\u5fc3\u6570\u5b57\uff0c\u4e0d\u8981\u7f16\u9020\u3002 \u6bb5\u843d\u5982\u4e0b\uff1a\n {cluster_content}\n\u4ee5\u4e0a\u5c31\u662f\u4f60\u9700\u8981\u603b\u7ed3\u7684\u5185\u5bb9\u3002", "max_token": 512, "threshold": 0.1, "max_cluster": 64, "random_seed": 0}}, "name": "2023\u5e74\u7248GMP\u6307\u5357-\u8d28\u91cf\u7ba1\u7406\u4f53\u7cfb.pdf", "type": "pdf", "location": "2023\u5e74\u7248GMP\u6307\u5357-\u8d28\u91cf\u7ba1\u7406\u4f53\u7cfb.pdf", "size": 7081164, "tenant_id": "dd78793cbfa211efaa260242ac150006", "language": "Chinese", "embd_id": "nomic-ai/nomic-embed-text-v1.5@FastEmbed", "pagerank": 10, "img2txt_id": "", "asr_id": "", "llm_id": "THUDM/glm-4-9b-chat@SILICONFLOW", "update_time": 1734800530312}}
Expected behavior
No response
Steps to reproduce
n/a
Additional information
No response