Update README.md
Browse files
README.md
CHANGED
@@ -2672,17 +2672,15 @@ embeddings = model.encode(
|
|
2672 |
)
|
2673 |
```
|
2674 |
|
2675 |
-
|
2676 |
|
2677 |
-
|
2678 |
|
2679 |
-
|
2680 |
-
|
2681 |
-
## Use Jina Embeddings for RAG
|
2682 |
|
2683 |
Jina Embeddings are very effective for retrieval augmented generation (RAG).
|
2684 |
-
Ravi Theja wrote a blog post on using Jina Embeddings together with [LLama Index](https://github.com/run-llama/llama_index) for RAG:
|
2685 |
-
|
2686 |
|
2687 |
<img src="https://miro.medium.com/v2/resize:fit:4800/format:webp/1*ZP2RVejCZovF3FDCg-Bx3A.png" width="780px">
|
2688 |
|
|
|
2672 |
)
|
2673 |
```
|
2674 |
|
2675 |
+
## Fully-managed Embeddings Service
|
2676 |
|
2677 |
+
Alternatively, you can use Jina AI's [Embeddings platform](https://jina.ai/embeddings/) for fully-managed access to Jina Embeddings models.
|
2678 |
|
2679 |
+
## RAG Performance
|
|
|
|
|
2680 |
|
2681 |
Jina Embeddings are very effective for retrieval augmented generation (RAG).
|
2682 |
+
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:
|
2683 |
+
|
2684 |
|
2685 |
<img src="https://miro.medium.com/v2/resize:fit:4800/format:webp/1*ZP2RVejCZovF3FDCg-Bx3A.png" width="780px">
|
2686 |
|