Add small changes

docs/latest/guides/chatbots.mdx

@@ -121,6 +121,11 @@ class ActionHaystack(Action):
 
  return []
 ```
+You will also want to declare this new action in the `domain.yml` file:
+```
+actions:
+- call_haystack
+```
 
 ## Running the Chatbot
 

docs/latest/guides/pipelines.mdx

@@ -220,9 +220,14 @@ NewNode = CustomNode()
 
 ## Decision nodes
 
-You can add decision nodes where only one "branch" is executed afterwards. This allows, for example, to classify an incoming query and depending on the result routing it to different modules:
+You can add decision nodes where only one "branch" is executed afterwards.
+This allows, for example, to classify an incoming query and depending on the result routing it to different modules.
+To find a ready-made example of a decision node, have a look at [the page](/usage/query-classifier) about the `QueryClassifier`.
+
 ![image](https://user-images.githubusercontent.com/1563902/102452199-41229b80-403a-11eb-9365-7038697e7c3e.png)
 
+If you'd like to define our own, you'll need to create a class that looks something like this:
+
 ```python
  class QueryClassifier():
  outgoing_edges = 2
@@ -280,8 +285,6 @@ res = doc_pipe.run(query="How can I change my address?", top_k_retriever=3)
 
 ```
 
-We plan many more features around the new pipelines including parallelized execution, distributed execution, dry runs - so stay tuned!
-
 <div style={{ marginBottom: "3rem" }} />
 
 ## Example: Multiple retrievers

docs/latest/guides/preprocessing.mdx

@@ -6,12 +6,18 @@ Haystack includes a suite of tools to:
 - normalize white space
 - split text into smaller pieces to optimize retrieval
 
-Check out our [preprocessing tutorial](/tutorials/train-dpr) if you'd like to start working with code examples already!
-
 These data preprocessing steps can have a big impact on the systems performance
 and effective handling of data is key to getting the most out of Haystack.
 
-The Document Store expects its inputs to come in the following format.
+<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">
+
+Check out our [preprocessing tutorial](/tutorials/train-dpr) if you'd like to start working with code examples already!
+
+</div>
+
+## Document Format
+
+The DocumentStore expects its inputs to come in the following format.
 The sections below will show you all the tools you'll need to ready your data for storing.
 
 ```python
@@ -91,10 +97,12 @@ See the [API documentation](https://haystack.deepset.ai/reference/crawler) for m
 ```python
 from haystack.connector import Crawler
 
-crawler = Crawler()
-docs = crawler.crawl(urls=["https://haystack.deepset.ai/overview/get-started"],
- output_dir="crawled_files",
- filter_urls= ["haystack\.deepset\.ai\/docs\/"])
+crawler = Crawler(output_dir="crawled_files")
+docs = crawler.crawl(
+ urls=["https://haystack.deepset.ai/overview/get-started"],
+ filter_urls=["haystack"],
+ crawler_depth=1
+)
 ```
 
 <div style={{ marginBottom: "3rem" }} />

docs/latest/guides/retriever.mdx

@@ -208,7 +208,7 @@ from haystack.pipeline import ExtractiveQAPipeline
 document_store = ElasticsearchDocumentStore(similarity="cosine")
 ...
 retriever = EmbeddingRetriever(document_store=document_store,
- embedding_model="deepset/sentence_bert")
+ embedding_model="sentence-transformers/all-MiniLM-L6-v2")
 ...
 p = ExtractiveQAPipeline(reader, retriever)
 ```