Pinned issues
Issues
- 0
Neo4j查询无结果:No high level context found. Switching to local mode. An error occurred: cannot access local variable 'll_entities_context' where it is not associated with a value
#501 opened by hixulei - 2
Error calling ChatGLM Embedding API
#490 opened by Dullne - 2
Extracting entities from chunks trapped
#431 opened by FocusCareer - 0
Entity Extraction stuck on 0% with only CPU
#500 opened by podral3 - 0
INFO:httpx:HTTP Request: POST http://127.0.0.1:11434/api/chat "HTTP/1.1 500 Internal Server Error" ollama._types.ResponseError: POST predict: Post "http://127.0.0.1:52582/completion": EOF
#497 opened by shalini-agarwal - 0
Not able to extract any entities; LLM is not working error. Writing graph with 0 nodes, 0 edges.
#499 opened by shalini-agarwal - 2
请问如何控制抽取实体和关系过程中大模型的并发量
#463 opened by wi162yyxq - 0
Getting 'internal server error' while running ollama_demo file for lightrag for various smaller models. NEED HELP.
#498 opened by shalini-agarwal - 2
并发调用API query接口报错
#496 opened by Yu-Xiao-Sheng - 2
Poor node deduplication - how to have more control?
#495 opened by jbartot - 0
Can we change entites that are hardcoded
#493 opened by pratham-adav - 0
We particularly need experimental scripts and evaluation functions to reproduce the performance results mentioned in the paper.
#492 opened by dannis97500 - 5
requests.exceptions.ConnectionError
#472 opened by fireSunset - 0
- 0
- 0
Debug:lightrag:Trigger summary:
#488 opened by anguy044 - 2
Question about trained/chunked rag
#449 opened by anguy044 - 5
production use-case questions
#422 opened by ChristianWunderlich - 0
Why Using Labels for Node Names and Label-Based Search Optimization in Neo4j
#487 opened by domenicopolicastro - 1
- 0
- 0
when using grok for chat and openai for embedding, some http requests to openai.com/v1/embeddings work, some fail because it's using the wrong api key
#484 opened by felixniemeyer - 1
fixed the examples bug :ERROR:asyncio:Cancelling an overlapped future failed
#478 opened by KevinZhuoGpt - 0
- 0
Redundant sorting
#480 opened by ajmani2195 - 2
Possibility to add metadata to chunks and return that with the result in json structure
#468 opened by ewagner70 - 1
Increase speed when insert batch
#475 opened by vanhdz2611 - 0
- 1
- 0
- 0
Regardless of the method chosen, it displays requests.exceptions.ConnectionError
#471 opened by fireSunset - 0
Examining the path of torch.classes raised: Tried to instantiate class '__path__._path', but it does not exist! Ensure that it is registered via torch::class_
#470 opened by KevinZhuoGpt - 0
- 5
use lightrag-1.0..5 TypeError: lazy_external_import.<locals>.import_class() got an unexpected keyword argument 'namespace'
#457 opened by fairleehu - 1
- 1
lightrag_ollama_demo.py running successfully, but without answering the question, keeping embedding
#455 opened by SorrowRX - 1
[Enh]: add support for elasticsearch
#460 opened by flefevre - 0
Adding Azure AI Search / Customized database
#459 opened by annawiewer - 9
Use light-rag without cuda
#454 opened by Fianax - 1
Looking for 'openaipublic.blob.core.windows.net' even using only local ollama models
#439 opened by miary - 3
AsyncCompletions.create() got an unexpected keyword argument 'keyword_extraction
#453 opened by Z-oo883 - 4
如何使用本地的embedding模型
#448 opened by joseph16388 - 1
batch_eval may be subject to positional / recency bias
#438 opened by bhelm - 2
content_keywords & high_level_keywords
#451 opened by eddprogrammer - 2
关于单纯使用LightRAG
#445 opened by joseph16388 - 2
Propose to standardize Document structure
#446 opened by zhangxingeng - 0
10x slower performance on Neo4j AuraDB vs Local Neo4j
#450 opened by Nauxie - 1
使用 pip install lightrag-hku 安装需要额外安装其他库才能运行
#433 opened by HuiDBK - 1
- 1
why sorted(edge['src_id'],edge('tgt_id'))?
#427 opened by masterwang22327