Add converter information

docs/latest/components/reader.mdx

@@ -45,6 +45,48 @@ While these models can work on CPU, it is recommended that they are run using GP
 
 <div style={{ marginBottom: "3rem" }} />
 
+## Usage
+
+A Reader can be used in isolation through its `predict()` method.
+
+```python
+result = reader.predict(
+ query="Which country is Canberra located in?",
+ documents=documents,
+ top_k=10
+)
+```
+
+This will return a dictionary of the following format:
+
+```python
+{
+ 'query': 'Which country is Canberra located in?',
+ 'answers':[
+ {'answer': 'Australia',
+ 'context': "Canberra, federal capital of the Commonwealth of Australia. It occupies part of the Australian Capital Territory (ACT),",
+ 'offset_answer_start': 147,
+ 'offset_answer_end': 154,
+ 'score': 0.9787139466668613,
+ 'document_id': '1337'
+ },...
+ ],
+}
+```
+
+However, if you are looking to set up Haystack as a service, we recommend using the Reader in a pipeline.
+
+```python
+from haystack.pipeline import ExtractiveQAPipeline
+
+pipe = ExtractiveQAPipeline(reader, retriever)
+
+prediction = pipe.run(
+ query='Which country is Canberra located in?',
+ params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 10}}
+)
+```
+
 ## Choosing the Right Model
 
 In Haystack, you can start using pretrained QA models simply by providing its HuggingFace Model Hub name to the Reader.
@@ -207,6 +249,44 @@ you might like to try ALBERT XXL which has set SoTA performance on SQuAD 2.0.
 
 <div style={{ marginBottom: "3rem" }} />
 
+## Fine-tuning, Saving, Loading and Converting
+
+<div className="max-w-xl bg-yellow-light-theme border-l-8 border-yellow-dark-theme px-6 pt-6 pb-4 my-4 rounded-md dark:bg-yellow-900">
+
+**Tutorial:** If you'd like a hands on example, check out our tutorial on fine-tuning [here](/tutorials/fine-tuning-a-model)
+
+</div>
+
+In Haystack, it is possible to fine-tune your FARMReader model on any SQuAD format QA dataset.
+Simply call the `train()` method to kick off training.
+This method will also save your model in the specified save directory.
+
+```python
+reader.train(
+ data_dir=data_dir,
+ train_filename="dev-v2.0.json",
+ use_gpu=True,
+ n_epochs=1,
+ save_dir="my_model"
+)
+```
+
+If you want to load the model at a later point, simply initialize a `FARMReader` object as follows.
+
+```python
+new_reader = FARMReader(model_name_or_path="my_model")
+```
+
+If you would like to convert your model from or into the HuggingFace Transformers format we provide a `Converter` object.
+Calling `Converter.convert_to_transformers()` will return a list of HuggingFace models.
+This can be particularly useful if you'd like to upload the model to the HuggingFace Model Hub.
+
+```python
+from haystack.modelling.conversion.transformers import Converter
+
+transformers_models = Converter.convert_to_transformers(reader.inferencer.model)
+```
+
 ## Confidence Scores
 
 When printing the full results of a Reader,

docs/latest/components/retriever.mdx

@@ -186,6 +186,10 @@ They are particular suited to cases where your query input is similar in style t
 i.e. when you are searching for most similar documents.
 This is not inherently suited to query based search where the length, language and format of the query usually significantly differs from the searched for text.
 
+If you are interested in using an embedding model from the HuggingFace Model hub as an Embedding Retirever,
+you should consider using the `haystack.modeling.transformers.Converter` object which can convert a Transformers model
+into the format required in order for it to be loaded as an `EmbeddingRetriever`.
+
 <div className="max-w-xl bg-yellow-light-theme border-l-8 border-yellow-dark-theme px-6 pt-6 pb-4 my-4 rounded-md dark:bg-yellow-900">
 
 **Tip**