Cinnamon/kotaemon

[BUG] Error: '\nt\nu\np\nl\ne\n_\nd\ne\nl\ni\nm\ni\nt\ne\nr\n' when trying to index docment

Opened this issue · 0 comments

Description

After uploading a txt file and trying to index it, this error occured, which has never occured before v0.9.6
image
kotaemon-v0.9.10, install without Docker in Python 3.10.16, use local LLM and embedding model here, didn't test online ones.

Reproduction steps

1. Go to 'Files'
2. Click on 'LightRAG Collection'
3. Drag a txt file to the uploading box and click 'Upload and Index'
4. See error

Screenshots

![DESCRIPTION](LINK.png)

Logs

User-id: None, can see public conversations: False
User-id: 1, can see public conversations: True
use_quick_index_mode False
reader_mode default
Chunk size: None, chunk overlap: None
Using reader TxtReader()
Got 0 page thumbnails
Adding documents to doc store
indexing step took 0.12047362327575684
INFO:httpx:HTTP Request: POST http://127.0.0.1:5678/v1/embeddings "HTTP/1.1 200 OK"
GraphRAG embedding dim 1536
Indexing GraphRAG with LLM ChatOpenAI(api_key=null, base_url=http://127.0.0...., frequency_penalty=None, logit_bias=None, logprobs=None, max_retries=None, max_retries_=2, max_tokens=4096, model=gguf/llm/qwenti..., n=1, organization=None, presence_penalty=None, stop=None, temperature=None, timeout=None, tool_choice=None, tools=None, top_logprobs=None, top_p=None) and Embedding OpenAIEmbeddings(api_key=null, base_url=http://127.0.0...., context_length=None, dimensions=None, max_retries=None, max_retries_=2, model=gte-Qwen2-1.5B-..., organization=None, timeout=None)...
INFO:lightrag:Logger initialized for working directory: E:\AI\LLM\kotaemon-v0.9.10\ktem_app_data\user_data\files\lightrag\ca83f6ff-7f8e-4f50-84d4-bcfb281ece77\input
INFO:lightrag:Load KV llm_response_cache with 0 data
INFO:lightrag:Load KV full_docs with 0 data
INFO:lightrag:Load KV text_chunks with 0 data
INFO:nano-vectordb:Init {'embedding_dim': 1536, 'metric': 'cosine', 'storage_file': 'E:\\AI\\LLM\\kotaemon-v0.9.10\\ktem_app_data\\user_data\\files\\lightrag\\ca83f6ff-7f8e-4f50-84d4-bcfb281ece77\\input\\vdb_entities.json'} 0 data
INFO:nano-vectordb:Init {'embedding_dim': 1536, 'metric': 'cosine', 'storage_file': 'E:\\AI\\LLM\\kotaemon-v0.9.10\\ktem_app_data\\user_data\\files\\lightrag\\ca83f6ff-7f8e-4f50-84d4-bcfb281ece77\\input\\vdb_relationships.json'} 0 data
INFO:nano-vectordb:Init {'embedding_dim': 1536, 'metric': 'cosine', 'storage_file': 'E:\\AI\\LLM\\kotaemon-v0.9.10\\ktem_app_data\\user_data\\files\\lightrag\\ca83f6ff-7f8e-4f50-84d4-bcfb281ece77\\input\\vdb_chunks.json'} 0 data
INFO:lightrag:Creating a new event loop in main thread.
INFO:lightrag:[New Docs] inserting 1 docs
Chunking documents: 100%|███████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 33.33doc/s]
INFO:lightrag:[New Chunks] inserting 48 chunks
INFO:lightrag:Inserting 48 vectors to chunks
Generating embeddings:   0%|                                                                  | 0/2 [00:00<?, ?batch/s]INFO:httpx:HTTP Request: POST http://127.0.0.1:5678/v1/embeddings "HTTP/1.1 200 OK"
Generating embeddings:  50%|█████████████████████████████                             | 1/2 [00:05<00:05,  5.66s/batch]INFO:httpx:HTTP Request: POST http://127.0.0.1:5678/v1/embeddings "HTTP/1.1 200 OK"
Generating embeddings: 100%|██████████████████████████████████████████████████████████| 2/2 [00:08<00:00,  4.35s/batch]
INFO:lightrag:[Entity Extraction]...
INFO:lightrag:Writing graph with 0 nodes, 0 edges

Browsers

Microsoft Edge

OS

Windows

Additional information

No response