gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: add doc

Browse source
This commit is contained in:
earayu 2025-05-23 11:57:45 +08:00
parent 6d6aefa2ff
commit 2679f619b6
3 changed files with 0 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
docs/LightRAG_concurrent_explain.md
View file

@ -239,11 +239,6 @@ Total:
- 4 chunks waiting for LLM response - 4 chunks waiting for LLM response
``` ```
### Scenario 3: Resource Bottleneck Analysis
**Timeline Example (max_parallel_insert=2, llm_model_max_async=4)**:
![lightrag_llm_request_timeline.png](assets%2Flightrag_llm_request_timeline.png)
## 7. Performance Optimization Recommendations ## 7. Performance Optimization Recommendations
### Understanding the Bottleneck ### Understanding the Bottleneck

BIN
docs/assets/lightrag_llm_request_timeline.png
View file

Binary file not shown.
Side by side

Before

Width:  |  Height:  |  Size: 118 KiB

3
docs/zh/LightRAG_concurrent_explain_zh.md
View file

@ -235,9 +235,6 @@ async def _process_single_content(chunk_key_dp: tuple[str, TextChunkSchema]):
- 4个chunks等待LLM响应 - 4个chunks等待LLM响应
``` ```
### 场景3：资源瓶颈分析
![lightrag_llm_request_timeline.png](..%2Fassets%2Flightrag_llm_request_timeline.png)
## 7. 性能优化建议 ## 7. 性能优化建议
### 理解瓶颈 ### 理解瓶颈