Make each Usage integration self-contained (own install), drop the shared Installation section

README.md

@@ -20,6 +20,8 @@ For more information about this model or how it was trained, head over to the [a
 
 ## Usage
 
+This model was designed with the upcoming RAGatouille overhaul in mind. However, it's compatible with all recent ColBERT implementations!
+
 ### Sentence Transformers
 
 This model can be used with [Sentence Transformers](https://www.sbert.net/) as a multi-vector (ColBERT-style late interaction) retriever via the `MultiVectorEncoder`:
@@ -52,24 +54,14 @@ print(scores)
 # tensor([[30.5692, 31.4895, 31.3029, 31.3072]])
 ```
 
-### Installation
-
-This model was designed with the upcoming RAGatouille overhaul in mind. However, it's compatible with all recent ColBERT implementations!
-
-To use it, you can either use the Stanford ColBERT library, or RAGatouille. You can install both or either by simply running.
-
-```sh
-pip install --upgrade ragatouille
-pip install --upgrade colbert-ai
-```
+### Rerankers
 
 If you're interested in using this model as a re-ranker (it vastly outperforms cross-encoders its size!), you can do so via the [rerankers](https://github.com/AnswerDotAI/rerankers) library:
-```sh
+
+```bash
 pip install --upgrade rerankers[transformers]
 ```
 
-### Rerankers
-
 ```python
 from rerankers import Reranker
 
@@ -81,6 +73,10 @@ ranker.rank(query=query, docs=docs)
 
 ### RAGatouille
 
+```bash
+pip install --upgrade ragatouille
+```
+
 ```python
 from ragatouille import RAGPretrainedModel
 
@@ -96,6 +92,10 @@ results = RAG.search(query)
 
 ### Stanford ColBERT
 
+```bash
+pip install --upgrade colbert-ai
+```
+
 #### Indexing
 
 ```python