RAG-Anything · Issues· 103 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #330
[Bug]: separate_content() concatenates text blocks before chunking, so page_idx never reaches text chunks
Updated Sep 15, 2026 - #256
[Question]:ERROR:Failed to initialize LightRAG instance
questionUpdated Sep 8, 2026 - #149
[Question]:检索时支持返回图片吗
questionUpdated Aug 28, 2026 - #348
This [Bug]:Image-heavy pages take 100s+ to ingest — ~24 LLM calls per image block
bugUpdated Aug 28, 2026 - #304
[Bug]:TypeError: 'PageChars' while processing xlsx file (excel)
bugUpdated Aug 13, 2026 - #73
[Question]: TypeError: DocProcessingStatus.__init__() got an unexpected keyword argument 'multimodal_processed'
questionUpdated Aug 12, 2026 - #332
[Bug]: multimodal chunks are appended after the doc_status record is written and never added to chunks_list
Updated Aug 11, 2026 - #136
[Question]:我使用中文数据构建了RAG，但是为什么检索出来的内容是英文的？
questionUpdated May 20, 2026 - #276
[Question]: raganything with lightrag api server??
questionUpdated May 15, 2026 - #235
[Question]:Consultation on the 63.4% accuracy on DocBench
questionUpdated Apr 15, 2026 - #211
[Question]: use Qwen3-Embedding text-embedding errors
questionUpdated Apr 12, 2026 - #213
[Feature Request]: Structured RAG failure-mode checklist based on the WFGY 16-problem map
enhancementUpdated Mar 5, 2026 - #48
[Question]: Is it normal for documents to take a while to process?
questionUpdated Mar 3, 2026 - #117
[Question]: Rag-Anything supports to AWS Bedrock ?
questionUpdated Feb 23, 2026 - #206
[Rust] Implement ONNX session pool for TableProcessor to improve parallelism
Updated Feb 19, 2026