mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 20:42:30 +08:00
Don't release full image (#10654)
### What problem does this PR solve? Introduced gpu profile in .env Added Dockerfile_tei fix datrie Removed LIGHTEN flag ### Type of change - [x] Documentation Update - [x] Refactoring
This commit is contained in:
@ -47,7 +47,7 @@ By default, a combination of weighted keyword similarity and weighted vector cos
|
||||
As a starter, you can skip this step to stay with the default retrieval method.
|
||||
|
||||
:::caution WARNING
|
||||
Using a rerank model will *significantly* increase the system's response time. If you must use a rerank model, ensure you use a SaaS reranker; if you prefer a locally deployed rerank model, ensure you start RAGFlow with **docker-compose-gpu.yml**.
|
||||
Using a rerank model will *significantly* increase the system's response time.
|
||||
:::
|
||||
|
||||
### 5. Enable cross-language search
|
||||
@ -140,6 +140,5 @@ The global variable name for the output of the **Retrieval** component, which ca
|
||||
|
||||
Go through the checklist below for best performance:
|
||||
|
||||
- Leave the **Rerank model** field empty.
|
||||
- If you must use a rerank model, ensure you use a SaaS reranker; if you prefer a locally deployed rerank model, ensure you start RAGFlow with **docker-compose-gpu.yml**.
|
||||
- Leave the **Rerank model** field empty to disable rerank.
|
||||
- Disable **Use knowledge graph**.
|
||||
|
||||
Reference in New Issue
Block a user