docs: add inference section

CHANGELOG.md

@@ -26,6 +26,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Docs
 
+- Add inference session in examples. ([#529](https://github.com/jina-ai/finetuner/pull/529))
+
 
 ## [0.5.2] - 2022-08-31
 

docs/tasks/image-to-image.md

@@ -129,6 +129,24 @@ What you can do for now is to call {meth}`~finetuner.run.Run.logs()` in the end
 
 After the run has finished successfully, you can download the tuned model on your local machine:
 ```python
-run.save_artifact('resnet-model')
+artifact = run.save_artifact('resnet-model')
 ```
-That's it! Now you have a fine-tuned model which is ready to be {ref}`integrated with the Jina ecosystem <integrate-with-jina>`.
+
+## Inference
+
+Now you saved the `artifact` into your host machine,
+let's use the fine-tuned model to encode a new `Document`:
+
+```python
+import finetuner
+from docarray import Document, DocumentArray
+# Load model from artifact
+model = finetuner.get_model(artifact=artifact)
+# Prepare some text to encode, change the placeholder image uri to an image on your machine
+test_da = DocumentArray([Document(uri='my-image.png')])
+# Encoding will happen in-place in your `DocumentArray`
+finetuner.encode(model=model, data=test_da)
+print(test_da.embeddings)
+```
+
+That's it! If you want to integrate the fine-tuned model into your Jina Flow, please check out {ref}`integrated with the Jina ecosystem <integrate-with-jina>`.

docs/tasks/text-to-image.md

@@ -119,6 +119,34 @@ We have done the evaulation for you in the table below.
 
 After the run has finished successfully, you can download the tuned model on your local machine:
 ```python
-run.save_artifact('clip-model')
+artifact = run.save_artifact('clip-model')
 ```
-That's it! Now you have a fine-tuned model which is ready to be {ref}`integrated with the Jina ecosystem <integrate-with-jina>`.
+
+## Inference
+
+Now you saved the `artifact` into your host machine,
+let's use the fine-tuned model to encode a new `Document`:
+
+```python
+import finetuner
+from docarray import Document, DocumentArray
+# Load model from artifact
+model = finetuner.get_model(artifact=artifact, select_model='clip-text')
+# Prepare some text to encode
+test_da = DocumentArray([Document(text='some text to encode')])
+# Encoding will happen in-place in your `DocumentArray`
+finetuner.encode(model=model, data=test_da)
+print(test_da.embeddings)
+```
+
+```{admonition} what is select_model?
+:class: hint
+When fine-tuning CLIP, we are fine-tuning the CLIPVisionEncoder and CLIPTextEncoder in parallel.
+The artifact contains two models: `clip-vision` and `clip-text`.
+The parameter `select_model` tells finetuner which model to use for inference, in the above example,
+we use `clip-text` to encode a Document with text content.
+```
+
+Check out [clip-as-service](https://clip-as-service.jina.ai/user-guides/finetuner/?highlight=finetuner#fine-tune-models) to learn how to plug-in a finetuned CLIP model to our CLIP specific service.
+
+That's it! If you want to integrate the fine-tuned model into your Jina Flow, please check out {ref}`integrated with the Jina ecosystem <integrate-with-jina>`.

docs/tasks/text-to-text.md

@@ -196,6 +196,24 @@ print(f'Run logs: {run.logs()}')
 ## Saving
 Once your run has successfully completed, you can save your fine-tuned model in the following way:
 ```python
-run.save_artifact('bert-model')
+artifact = run.save_artifact('bert-model')
 ```
-That's it! Now you have a fine-tuned model which is ready to be {ref}`integrated with the Jina ecosystem <integrate-with-jina>`.
+
+## Inference
+
+Now you saved the `artifact` into your host machine,
+let's use the fine-tuned model to encode a new `Document`:
+
+```python
+import finetuner
+from docarray import Document, DocumentArray
+# Load model from artifact
+model = finetuner.get_model(artifact=artifact)
+# Prepare some text to encode
+test_da = DocumentArray([Document(text='some text to encode')])
+# Encoding will happen in-place in your `DocumentArray`
+finetuner.encode(model=model, data=test_da)
+print(test_da.embeddings)
+```
+
+That's it! If you want to integrate the fine-tuned model into your Jina Flow, please check out {ref}`integrated with the Jina ecosystem <integrate-with-jina>`.

tests/conftest.py

@@ -5,8 +5,8 @@
 
 @pytest.fixture(autouse=True)
 def overwrite_hubble_registry():
-    os.environ['JINA_FINETUNER_REGISTRY'] = 'https://api-staging.finetuner.fit'
-    os.environ['JINA_HUBBLE_REGISTRY'] = 'https://apihubble.staging.jina.ai'
+    os.environ['JINA_FINETUNER_REGISTRY'] = 'https://api.finetuner.fit'
+    os.environ['JINA_HUBBLE_REGISTRY'] = 'https://api.hubble.jina.ai'
     yield
     del os.environ['JINA_HUBBLE_REGISTRY']
     del os.environ['JINA_FINETUNER_REGISTRY']