Built-in reranker models have been removed from official deliveries. (#7439)

### What problem does this PR solve?

### Type of change


- [x] Documentation Update

docs/faq.mdx

@@ -43,9 +43,7 @@ RAGFlow offers two Docker image editions, `v0.18.0-slim` and `v0.18.0`:
 - `infiniflow/ragflow:v0.18.0`: The RAGFlow Docker image with embedding models including:
   - Built-in embedding models:
     - `BAAI/bge-large-zh-v1.5`
-    - `BAAI/bge-reranker-v2-m3`
     - `maidalun1020/bce-embedding-base_v1`
-    - `maidalun1020/bce-reranker-base_v1`
   - Embedding models that will be downloaded once you select them in the RAGFlow UI:
     - `BAAI/bge-base-en-v1.5`
     - `BAAI/bge-large-en-v1.5`

docs/guides/agent/agent_component_reference/generate.mdx

@@ -83,10 +83,9 @@ This toggle sets whether to cite the original text as reference.
 
 
 :::tip NOTE
-This feature is used for multi-turn dialogue *only* and is applicable *only* when the original documents are uploaded to a knowledge base and have finished file parsing.
+This feature is applicable *only* when the original documents are uploaded to a knowledge base and have finished file parsing.
 :::
 
-
 ### Message window size
 
 An integer specifying the number of previous dialogue rounds to input into the LLM. For example, if it is set to 12, the tokens from the last 12 dialogue rounds will be fed to the LLM. This feature consumes additional tokens.