Update README.md (#13)

- Update README.md (3870b93479f5ff8c80c7b4638987a0d39b8bab34)

README.md

@@ -2672,17 +2672,15 @@ embeddings = model.encode(
 )
 ```
 
-*Alternatively, you can use Jina AI's [Embeddings platform](https://jina.ai/embeddings/) for fully-managed access to Jina Embeddings models*. 
+## Fully-managed Embeddings Service
 
-## Fine-tuning
+Alternatively, you can use Jina AI's [Embeddings platform](https://jina.ai/embeddings/) for fully-managed access to Jina Embeddings models.
 
-Please consider [Finetuner](https://github.com/jina-ai/finetuner).
-
-## Use Jina Embeddings for RAG
+## RAG Performance
 
 Jina Embeddings are very effective for retrieval augmented generation (RAG).
-Ravi Theja wrote a blog post on using Jina Embeddings together with [LLama Index](https://github.com/run-llama/llama_index) for RAG:
-https://blog.llamaindex.ai/boosting-rag-picking-the-best-embedding-reranker-models-42d079022e83
+Ravi Theja wrote a [blog post](https://blog.llamaindex.ai/boosting-rag-picking-the-best-embedding-reranker-models-42d079022e83) on using Jina Embeddings together with [LLama Index](https://github.com/run-llama/llama_index) for RAG:
+
 
 <img src="https://miro.medium.com/v2/resize:fit:4800/format:webp/1*ZP2RVejCZovF3FDCg-Bx3A.png" width="780px">