Update README.md
Browse files
README.md
CHANGED
@@ -44,7 +44,7 @@ This model has 137 million parameters, which enables fast and memory efficient i
|
|
44 |
Additionally, we provide the following embedding models:
|
45 |
|
46 |
- [`jina-embeddings-v2-small-en`](https://huggingface.co/jinaai/jina-embeddings-v2-small-en): 33 million parameters.
|
47 |
-
- [`jina-embeddings-v2-base-en`](https://huggingface.co/jinaai/jina-embeddings-v2-base-en): 137 million parameters
|
48 |
- [`jina-embeddings-v2-base-zh`](https://huggingface.co/jinaai/jina-embeddings-v2-base-zh): Chinese-English Bilingual embeddings.
|
49 |
- [`jina-embeddings-v2-base-de`](https://huggingface.co/jinaai/jina-embeddings-v2-base-de): German-English Bilingual embeddings.
|
50 |
- [`jina-embeddings-v2-base-es`](https://huggingface.co/jinaai/jina-embeddings-v2-base-es): Spanish-English Bilingual embeddings (soon).
|
@@ -148,6 +148,7 @@ embeddings = model.encode(
|
|
148 |
]
|
149 |
)
|
150 |
print(cos_sim(embeddings[0], embeddings[1]))
|
|
|
151 |
```
|
152 |
|
153 |
If you only want to handle shorter sequence, such as 2k, pass the `max_length` parameter to the `encode` function:
|
@@ -159,14 +160,11 @@ embeddings = model.encode(
|
|
159 |
)
|
160 |
```
|
161 |
|
162 |
-
## Fully-managed Embeddings Service
|
163 |
-
|
164 |
-
Alternatively, you can use Jina AI's [Embeddings platform](https://jina.ai/embeddings/) for fully-managed access to Jina Embeddings models.
|
165 |
-
|
166 |
## Plans
|
167 |
|
168 |
-
|
169 |
-
|
|
|
170 |
|
171 |
## Contact
|
172 |
|
|
|
44 |
Additionally, we provide the following embedding models:
|
45 |
|
46 |
- [`jina-embeddings-v2-small-en`](https://huggingface.co/jinaai/jina-embeddings-v2-small-en): 33 million parameters.
|
47 |
+
- [`jina-embeddings-v2-base-en`](https://huggingface.co/jinaai/jina-embeddings-v2-base-en): 137 million parameters.
|
48 |
- [`jina-embeddings-v2-base-zh`](https://huggingface.co/jinaai/jina-embeddings-v2-base-zh): Chinese-English Bilingual embeddings.
|
49 |
- [`jina-embeddings-v2-base-de`](https://huggingface.co/jinaai/jina-embeddings-v2-base-de): German-English Bilingual embeddings.
|
50 |
- [`jina-embeddings-v2-base-es`](https://huggingface.co/jinaai/jina-embeddings-v2-base-es): Spanish-English Bilingual embeddings (soon).
|
|
|
148 |
]
|
149 |
)
|
150 |
print(cos_sim(embeddings[0], embeddings[1]))
|
151 |
+
>>> 0.7230249
|
152 |
```
|
153 |
|
154 |
If you only want to handle shorter sequence, such as 2k, pass the `max_length` parameter to the `encode` function:
|
|
|
160 |
)
|
161 |
```
|
162 |
|
|
|
|
|
|
|
|
|
163 |
## Plans
|
164 |
|
165 |
+
1. Bilingual embedding models supporting more European & Asian languages, including Spanish, French, Italian and Japanese.
|
166 |
+
2. Multimodal embedding models enable Multimodal RAG applications.
|
167 |
+
3. High-performt rerankers.
|
168 |
|
169 |
## Contact
|
170 |
|