Langflow demo: next steps for using non-local files or a different vector store (#322)

Author: Paul-Cornell

examplecode/tools/langflow.mdx

@@ -199,6 +199,73 @@ Also:
     </Step>
 </Steps>
 
+## Next steps
+
+Now that you have your pipeline set up, here are just a few ways that you could modify it to support different requirements, 
+such as processing non-local files or using a different vector store.
+
+### Process non-local files
+
+In this demonstration, you pass to Unstructured a file or a directory of files that are stored locally. To pass 
+non-local files to Unstructured instead, you can use the 
+[Unstructured Platform](/platform/overview) or 
+[Unstructured Ingest](/ingestion/overview) outside of Langflow.
+
+To do this, you can:
+
+- [Use the Unstructured Platform to create a workflow](/platform/quickstart) that relies on any available non-local 
+  [source connector](/platform/sources/overview) to connect to 
+  [Astra DB](/platform/destinations/astradb). Run this workflow outside of Langflow anytime you have new documents in that non-local source location that 
+  you want Unstructured to process and then insert the new processed data into Astra DB. Then, back in the Langflow project, 
+  use the **Playground** to ask additional questions, which will now include the new data when generating answers.
+
+- [Use Unstructured Ingest to create a pipeline](/api-reference/ingest/overview) that relies on any available non-local 
+  [source connector](/api-reference/ingest/source-connectors/overview) to connect to 
+  [Astra DB](/api-reference/ingest/destination-connector/astradb). Run this pipeline outside of Langflow anytime you have new documents in that non-local source location that 
+  you want Unstructured to process and then insert the new processed data into Astra DB. Then, back in the Langflow project, 
+  use the **Playground** to ask additonal questions, which will now include the new data when generating answers.
+
+### Use a different vector store
+
+In this demonstration, you use Astra DB as the vector store. Langflow and Unstructured support several vector stores in addition to Astra DB.
+
+To do this, you can: 
+
+[Use the Unstructured Platform to create a workflow](/platform/quickstart) that relies on any available 
+[source connector](/platform/sources/overview) to connect to 
+one of the following available vector stores that Langflow also supports:
+
+- [Milvus](/platform/destinations/milvus)
+- [MongoDB](/platform/destinations/mongodb)
+- [Pinecone](/platform/destinations/pinecone)
+
+Run this workflow outside of Langflow anytime you have new documents in the source location that 
+you want Unstructured to process and then insert the new processed data into the vector store. Then, back in the Langflow project, 
+swap out the **Astra DB RAG** component for the corresponding **Vector Stores** component that matches the new vector 
+store's name. Configure the new component, and then 
+use the **Playground** to ask additional questions, which will now use the new vector store when generating answers.
+
+Or, [use Unstructured Ingest to create a pipeline](/api-reference/ingest/overview) that relies on any available 
+[source connector](/api-reference/ingest/source-connectors/overview) to connect to 
+one of the following available vector stores that Langflow also supports:
+
+- [Chroma DB](/api-reference/ingest/destination-connector/chroma)
+- [Couchbase](/api-reference/ingest/destination-connector/couchbase)
+- [Elasticsearch](/api-reference/ingest/destination-connector/elasticsearch)
+- [Milvus](/api-reference/ingest/destination-connector/milvus)
+- [MongoDB](/api-reference/ingest/destination-connector/mongodb)
+- [OpenSearch](/api-reference/ingest/destination-connector/opensearch)
+- [Pinecone](/api-reference/ingest/destination-connector/pinecone)
+- [Qdrant](/api-reference/ingest/destination-connector/qdrant)
+- [Vectara](/api-reference/ingest/destination-connector/vectara)
+- [Weaviate](/api-reference/ingest/destination-connector/weaviate)
+
+Run this pipeline outside of Langflow anytime you have new documents in the source location that 
+you want Unstructured to process and then insert the new processed data into the vector store. Then, back in the Langflow project, 
+swap out the **Astra DB RAG** component for the corresponding **Vector Stores** component that matches the new vector 
+store's name. Configure the new component, and then 
+use the **Playground** to ask additional questions, which will now use the new vector store when generating answers.
+
 ## Learn more
 
 See the [Langflow documentation](https://docs.langflow.org/).