Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug]: Knowledge Graph [ERROR]Generate embedding error:'title_tks' #3905

Closed
1 task done
neo-workship opened this issue Dec 6, 2024 · 3 comments
Closed
1 task done
Labels
bug Something isn't working

Comments

@neo-workship
Copy link

Is there an existing issue for the same bug?

  • I have checked the existing issues.

RAGFlow workspace code commit ID

0d5486a(v0.14.1~75) full

RAGFlow image version

0d5486a(v0.14.1~75) full - self build

Other environment information

install environment : ubuntu 24
ragflow version: 0d5486aa(v0.14.1~75) full

Actual behavior

Knowledge Graph embedding Error. use embedding model include: ollama nomic-embed-text 、 Baichuan-Text-Embedding 、zhipu embedding-3. use LLM : DeepSeek . All reported errors as shown in the picture

image

Expected behavior

reported errors as shown in the picture

image

log info

2024-12-06 16:34:12,414 INFO     15 set_progress(39a518c0b3ac11ef886c0242ac120006), progress: -1, progress_msg: Page(1~100000001): [ERROR]Generate embedding error:'title_tks'
2024-12-06 16:34:12,441 ERROR    15 Generate embedding error:'title_tks'
Traceback (most recent call last):
  File "/ragflow/rag/svr/task_executor.py", line 416, 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 276, in embedding
    tts.append(rmSpace(d["title_tks"]))
                       ~^^^^^^^^^^^^^
KeyError: 'title_tks'
2024-12-06 16:34:12,443 ERROR    15 handle_task got exception for task {"id": "39a518c0b3ac11ef886c0242ac120006", "doc_id": "5d3f2834b3a811ef8f060242ac120006", "from_page": 0, "to_page": 100000000, "retry_count": 0, "kb_id": "f03207d8b38e11efa8d90242ac120006", "parser_id": "knowledge_graph", "parser_config": {"auto_keywords": 0, "auto_questions": 0, "raptor": {"use_raptor": false}, "chunk_token_num": 8192, "delimiter": "\\n!?;\u3002\uff1b\uff01\uff1f", "layout_recognize": true, "html4excel": false, "entity_types": ["organization", "person", "location", "event", "time"], "pages": []}, "name": "hd.txt", "type": "doc", "location": "hd.txt", "size": 1826, "tenant_id": "169257b6b38d11ef8a960242ac120006", "language": "Chinese", "embd_id": "nomic-embed-text:latest@Ollama", "pagerank": 0, "img2txt_id": "qwen-vl-max@Tongyi-Qianwen", "asr_id": "paraformer-realtime-8k-v1@Tongyi-Qianwen", "llm_id": "deepseek-chat@DeepSeek", "update_time": 1733473775470}
Traceback (most recent call last):
  File "/ragflow/rag/svr/task_executor.py", line 463, in handle_task
    do_handle_task(task)
  File "/ragflow/rag/svr/task_executor.py", line 416, 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 276, in embedding
    tts.append(rmSpace(d["title_tks"]))
                       ~^^^^^^^^^^^^^
KeyError: 'title_tks'

Steps to reproduce

- select Knowledge Graph method
- config embedding model:ollama nomic-embed-text 、 Baichuan-Text-Embedding 、zhipu embedding-3
- Parsing document 
- triggered error

Additional information

No response

@neo-workship neo-workship added the bug Something isn't working label Dec 6, 2024
@Philips69696
Copy link

我也遇到了这个问题,一开始我以为是文件过大,后来传了个200字的小docx也会报这个错

@isthaison
Copy link
Contributor

#3875 I had the same problem, it gave me an added feature error, I rolled back the task_executor file and it no longer had the error.

KevinHuSh added a commit that referenced this issue Dec 9, 2024
### What problem does this PR solve?

#3905
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
@yuzhichang
Copy link
Member

Fixed by #3931

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

4 participants