Description
Describe your problem
docker 本地启动， 解析长文本报错， 求大家帮忙看看错误原因。
embedding模型使用 shaw/dmeta-embedding-zh:latest
2025-03-02 21:57:51,367 INFO 12 set_progress(2afc9582f76e11ef9f4d0242ac1b0006), progress: 0.7127773749093546, progress_msg:
2025-03-02 21:57:51,809 INFO 12 HTTP Request: POST http://10.3.81.35:11434/api/embeddings "HTTP/1.1 500 Internal Server Error"
2025-03-02 21:57:51,819 INFO 12 set_progress(2afc9582f76e11ef9f4d0242ac1b0006), progress: -1, progress_msg: 21:57:51 Page(1~100000001): [ERROR]Generate embedding error:{}
2025-03-02 21:57:51,829 ERROR 12 Generate embedding error:{}
Traceback (most recent call last):
File "/ragflow/rag/svr/task_executor.py", line 571, in do_handle_task
token_count, vector_size = embedding(chunks, embedding_model, task_parser_config, progress_callback)
File "/ragflow/rag/svr/task_executor.py", line 368, in embedding
vts, c = mdl.encode(cnts[i: i + batch_size])
File "<@beartype(api.db.services.llm_service.LLMBundle.encode) at 0x7ffa3d9a5cf0>", line 31, in encode
File "/ragflow/api/db/services/llm_service.py", line 238, in encode
embeddings, used_tokens = self.mdl.encode(texts)
File "<@beartype(rag.llm.embedding_model.OllamaEmbed.encode) at 0x7ffa3fd141f0>", line 31, in encode
File "/ragflow/rag/llm/embedding_model.py", line 262, in encode
res = self.client.embeddings(prompt=txt,
File "/ragflow/.venv/lib/python3.10/site-packages/ollama/_client.py", line 201, in embeddings
return self._request(
File "/ragflow/.venv/lib/python3.10/site-packages/ollama/_client.py", line 74, in _request
raise ResponseError(e.response.text, e.response.status_code) from None
ollama._types.ResponseError: {}
2025-03-02 21:57:51,837 INFO 12 set_progress(2afc9582f76e11ef9f4d0242ac1b0006), progress: -1, progress_msg: 21:57:51 [ERROR][Exception]: {}
2025-03-02 21:57:51,845 ERROR 12 handle_task got exception for task {"id": "2afc9582f76e11ef9f4d0242ac1b0006", "doc_id": "2a47be3ef5a511efbd920242ac1b0006", "from_page": 0, "to_page": 100000000, "retry_count": 0, "kb_id": "1869f86cf5a511efba5c0242ac1b0006", "parser_id": "book", "parser_config": {"auto_keywords": 0, "auto_questions": 0, "raptor": {"use_raptor": false, "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": 256, "threshold": 0.1, "max_cluster": 64, "random_seed": 0}, "graphrag": {"use_graphrag": false}, "chunk_token_num": 128, "delimiter": "\n!?;\u3002\uff1b\uff01\uff1f", "layout_recognize": "DeepDOC", "html4excel": false, "pages": []}, "name": "\u6bdb\u6cfd\u4e1c\u9009\u96c6\u7b2c1-5\u5377.txt", "type": "doc", "location": "\u6bdb\u6cfd\u4e1c\u9009\u96c6\u7b2c1-5\u5377.txt", "size": 3717702, "tenant_id": "feb59172f59c11efa7740242ac1b0006", "language": "Chinese", "embd_id": "shaw/dmeta-embedding-zh:latest@Ollama", "pagerank": 0, "kb_parser_config": {"auto_keywords": 0, "auto_questions": 0, "raptor": {"use_raptor": false}, "graphrag": {"use_graphrag": false}, "chunk_token_num": 128, "delimiter": "\n!?;\u3002\uff1b\uff01\uff1f", "layout_recognize": "Plain Text", "html4excel": false}, "img2txt_id": "", "asr_id": "", "llm_id": "deepseek-r1:8b@Ollama", "update_time": 1740923801157, "task_type": ""}
Traceback (most recent call last):
File "/ragflow/rag/svr/task_executor.py", line 626, in handle_task
do_handle_task(task)
File "/ragflow/rag/svr/task_executor.py", line 571, in do_handle_task
token_count, vector_size = embedding(chunks, embedding_model, task_parser_config, progress_callback)
File "/ragflow/rag/svr/task_executor.py", line 368, in embedding
vts, c = mdl.encode(cnts[i: i + batch_size])
File "<@beartype(api.db.services.llm_service.LLMBundle.encode) at 0x7ffa3d9a5cf0>", line 31, in encode
File "/ragflow/api/db/services/llm_service.py", line 238, in encode
embeddings, used_tokens = self.mdl.encode(texts)
File "<@beartype(rag.llm.embedding_model.OllamaEmbed.encode) at 0x7ffa3fd141f0>", line 31, in encode
File "/ragflow/rag/llm/embedding_model.py", line 262, in encode
res = self.client.embeddings(prompt=txt,
File "/ragflow/.venv/lib/python3.10/site-packages/ollama/_client.py", line 201, in embeddings
return self._request(
File "/ragflow/.venv/lib/python3.10/site-packages/ollama/_client.py", line 74, in _request
raise ResponseError(e.response.text, e.response.status_code) from None
ollama._types.ResponseError: {}