Updated readme and docs (mostly info about 'get_model_from_name' function)

Author: PierreMarza

README.md

@@ -51,6 +51,15 @@ In order to reproduce the above example you can run the following command:
 thunder benchmark phikon break_his knn
 ```
 
+### Extracting embeddings with any supported foundation model (API Usage)
+We also provide a [`get_model_from_name`](https://mics-lab.github.io/thunder/api/#thunder.models.get_model_from_name) function through our API to extract embeddings using any foundation model we support on your own data. Below is an example if you want to get the Pytorch callable, transforms and function to extract embeddings for `uni2h`:
+
+```python
+from thunder.models import get_model_from_name
+
+model, transform, get_embeddings = get_model_from_name("uni2h", device="cuda")
+```
+
 ## Installing thunder
 
 Code tested with Python 3.10. To replicate, you can create the following conda environment and activate it,

docs/get_model.md

@@ -0,0 +1,16 @@
+In addition to benchmarking, we also provide a [`get_model_from_name`](https://mics-lab.github.io/thunder/api/#thunder.models.get_model_from_name) function through our API to extract embeddings using any foundation model we support on your own data. It returns a Pytorch model callable, associated transforms (to apply to images to extract embeddings from) and a function to get embeddings from a batch of transformed images, the model callable, and the type of embeddings (pooled or spatial) to return.
+
+Below is an example if you want to get the Pytorch callable, transforms and function to extract embeddings for `uni2h`:
+
+```python
+from thunder.models import get_model_from_name
+
+model, transform, get_embeddings = get_model_from_name("uni2h", device="cuda")
+```
+
+You can then extract the embedding of a PIL image `im`  as follows:
+
+```python
+pooled_emb = get_embeddings(transform(im), model, pooled_emb=True)
+spatial_emb = get_embeddings(transform(im), model, pooled_emb=False)
+```

mkdocs.yml

@@ -10,11 +10,12 @@ nav:
   - Home: index.md
   - Tutorials:
     - Getting Started: getting_started.md
-    - Benchmark a Custom Model: custom_model.md
+    - Benchmarking a Custom Model: custom_model.md
     - Overriding Configurations: custom_config.md
+    - Using foundation models on your data: get_model.md
   - API: api.md
 
-theme: 
+theme:
   name: material
   logo: logo.svg
   favicon: logo.svg