Skip to content

Issues: HKUDS/LightRAG

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.

Sign up for GitHub

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

51 Open 174 Closed
51 Open 174 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

对于已有的三元组数据，可以怎么构建
#280 opened Nov 15, 2024 by laizef
An error occurred: Error code: 400 - {'object': 'error', 'message': '**NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.**\n\n(The expanded size of the tensor (513) must match the existing size (512) at non-singleton dimension 1. Target sizes: [2, 513]. Tensor sizes: [1, 512])', 'code': 50001}
#279 opened Nov 15, 2024 by Z-oo883
Plans for supporting massive parallelization
#278 opened Nov 14, 2024 by chandasampath
我测试发现即使是在专业的知识领域，使用lightrag模型回答的准确率似乎不如让LLM直接给出答案。
#277 opened Nov 14, 2024 by sunzhaoyang1
V100 gpu执行ollama的示例失败
#276 opened Nov 14, 2024 by litaolaile
2
The program runs into an infinite loop and cannot be stopped.
#275 opened Nov 14, 2024 by Cherries-Man
The speed of processing trunks
#274 opened Nov 14, 2024 by icvplayer
An error occurred: Error code: 400 - {'object': 'error', 'message': 'could not broadcast input array from shape (535,) into shape (512,)', 'type': 'BadRequestError', 'param': None, 'code': 400}
#273 opened Nov 14, 2024 by Z-oo883
How to read long texts
#271 opened Nov 14, 2024 by smileyboy2019
embedding dimension problem
#270 opened Nov 13, 2024 by 13331112522
Encounter problem when using Neo4j as storage.
#269 opened Nov 13, 2024 by SuiJiGuoChengSuiJiGuo
What's the Default Prompt to use
#268 opened Nov 13, 2024 by vigneshmj1997
Add user_id based insertion
#267 opened Nov 13, 2024 by Tejaswgupta
请问后续会有根据文件名删除文件中所含所有节点的功能吗
#265 opened Nov 13, 2024 by small122
2
lightrag能返回引用的数据吗
#264 opened Nov 13, 2024 by suercxx
1
LightRAG indexing causing problematic symbols that don't conform to UTF-8 encoding standards
#262 opened Nov 12, 2024 by daamazonbird
Whether the complete 'results.json' of the all dataset & all Methods (NaiveRAG, RQ-RAG, HyDE, GraphRAG, LightRAG) can be provided for reproduction?
#260 opened Nov 12, 2024 by CooFlow
1
Hey, I've been wondering, aside from setting top_k, max_token_for_text_unit, and max_token_for_global_context, what other ways can I truncate the context window to make sure my request doesn't exceed the maximum context length? Any tips?
#259 opened Nov 12, 2024 by DragonLsy
Finding contradictory statements using LightRAG
#258 opened Nov 12, 2024 by abylikhsanov
Unstable context on each start
#255 opened Nov 11, 2024 by Burakabdi
can release a xinference demo since not all model can be found by Ollama?
#254 opened Nov 11, 2024 by gcl916
3
Example code not working openai compatible code.
#253 opened Nov 11, 2024 by ASAD-BE18
Model not found
#252 opened Nov 11, 2024 by wangtianqi1993
As a RAG task, why wasn't the context content used during evaluation (batch_eval)? If there are possibilities of hallucinations, this evaluation might not be quite accurate.
#251 opened Nov 11, 2024 by luoling1993
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select) bug Something isn't working
#249 opened Nov 11, 2024 by Z-oo883
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.