Fix errors in docs
Browse filesThe model's HF id had an an extra "/" at the end preventing it to be downloaded automatically. The pymilvus installation instruction was also incomplete, missing the installation of the "model" component.
README.md
CHANGED
|
@@ -31,7 +31,7 @@ The model is compatible with Milvus Vector DB and is very easy to use:
|
|
| 31 |
|
| 32 |
First, install the pymilvus library
|
| 33 |
```shell
|
| 34 |
-
pip install pymilvus
|
| 35 |
```
|
| 36 |
|
| 37 |
The model can then be used to encode pairs of text and find the similarity between their representations
|
|
@@ -68,7 +68,7 @@ client.create_collection(
|
|
| 68 |
)
|
| 69 |
|
| 70 |
embeddings_model = model.sparse.SpladeEmbeddingFunction(
|
| 71 |
-
model_name="ibm-granite/granite-embedding-30m-sparse
|
| 72 |
device="cpu",
|
| 73 |
batch_size=2,
|
| 74 |
k_tokens_query=50,
|
|
|
|
| 31 |
|
| 32 |
First, install the pymilvus library
|
| 33 |
```shell
|
| 34 |
+
pip install pymilvus[model]
|
| 35 |
```
|
| 36 |
|
| 37 |
The model can then be used to encode pairs of text and find the similarity between their representations
|
|
|
|
| 68 |
)
|
| 69 |
|
| 70 |
embeddings_model = model.sparse.SpladeEmbeddingFunction(
|
| 71 |
+
model_name="ibm-granite/granite-embedding-30m-sparse",
|
| 72 |
device="cpu",
|
| 73 |
batch_size=2,
|
| 74 |
k_tokens_query=50,
|