finish docs

docs/reference/pipeline/integrations.md

@@ -8,6 +8,23 @@ This document provides an overview of the integration components available in th
 2. [HuggingFaceComponent](#huggingfacecomponent)
 3. [LangChainComponent](#langchaincomponent)
 
+## Installation Requirements
+Before utilizing the integration components, it is important to note that the required third-party libraries are not included in HealthChain's default installation. This design decision was made to:
+
+- Maintain a lean and flexible core package
+- Allow users to selectively install only the necessary dependencies
+- Avoid potential version conflicts with other packages in your environment
+
+To use these integrations, you will need to manually install the corresponding libraries using pip.
+
+```python
+pip install spacy
+python -m spacy download en_core_web_sm  # or another desired model
+pip install transformers
+pip install langchain
+```
+
+
 ## SpacyComponent
 
 The `SpacyComponent` allows you to integrate spaCy models into your HealthChain pipeline. To initialize the component it only requires the path to the Spacy pipeline you wish to use. To run this example you may need to first run `python -m spacy download en_core_web_sm` to download the model.

docs/reference/pipeline/pipeline.md

@@ -109,6 +109,12 @@ pipeline.add(RemoveStopwords(stopwords))
 
 [(BaseComponent API Reference)](../../api/component.md#healthchain.pipeline.components.basecomponent.BaseComponent)
 
+### Integrations
+
+HealthChain offers powerful integrations with popular NLP libraries, enhancing its capabilities and allowing you to build more sophisticated pipelines. These integrations include components for spaCy, Hugging Face Transformers, and LangChain, enabling you to leverage state-of-the-art NLP models and techniques within your HealthChain workflows.
+
+Integrations are covered in detail on the [Integration](./integrations.md) homepage.
+
 ## Pipeline Management 🔨
 
 #### Adding

healthchain/pipeline/components/integrations.py

@@ -17,12 +17,7 @@ def __call__(self, doc: Document) -> Document:
 
 class HuggingFaceComponent(BaseComponent[str]):
     def __init__(self, task, model):
-        try:
-            from transformers import pipeline
-        except ImportError:
-            raise ImportError(
-                "Transformers is not installed. Install it with 'pip install healthchain[transformers]'"
-            )
+        from transformers import pipeline
 
         nlp = pipeline(task=task, model=model)
         self.nlp = nlp

mkdocs.yml

@@ -22,6 +22,7 @@ nav:
         - Overview: reference/pipeline/pipeline.md
         - Data Container: reference/pipeline/data_container.md
         - Component: reference/pipeline/component.md
+        - Integrations: reference/pipeline/integrations.md
         - Models:
           - Overview: reference/pipeline/models/models.md
         - Prebuilt: