Update README.md (#27)
Browse files- Update README.md (3627135d756fd2fa86ad752269966f6570ec0650)
README.md
CHANGED
@@ -2652,7 +2652,7 @@ Jina Embeddings V2 [technical report](https://arxiv.org/abs/2310.19923)
|
|
2652 |
|
2653 |
## Usage
|
2654 |
|
2655 |
-
|
2656 |
<p>
|
2657 |
|
2658 |
### Why mean pooling?
|
@@ -2717,7 +2717,7 @@ Alternatively, you can use Jina AI's [Embedding platform](https://jina.ai/embedd
|
|
2717 |
|
2718 |
## Use Jina Embeddings for RAG
|
2719 |
|
2720 |
-
According to the latest blog post from [
|
2721 |
|
2722 |
> In summary, to achieve the peak performance in both hit rate and MRR, the combination of OpenAI or JinaAI-Base embeddings with the CohereRerank/bge-reranker-large reranker stands out.
|
2723 |
|
|
|
2652 |
|
2653 |
## Usage
|
2654 |
|
2655 |
+
**<details><summary>Please apply mean pooling when integrating the model.</summary>**
|
2656 |
<p>
|
2657 |
|
2658 |
### Why mean pooling?
|
|
|
2717 |
|
2718 |
## Use Jina Embeddings for RAG
|
2719 |
|
2720 |
+
According to the latest blog post from [LLamaIndex](https://blog.llamaindex.ai/boosting-rag-picking-the-best-embedding-reranker-models-42d079022e83),
|
2721 |
|
2722 |
> In summary, to achieve the peak performance in both hit rate and MRR, the combination of OpenAI or JinaAI-Base embeddings with the CohereRerank/bge-reranker-large reranker stands out.
|
2723 |
|