jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

📝 docs(flow-runner.mdx): update explanation of using Document input in FlowRunner class

Browse source 
The change clarifies that using a `Document` as input in the `FlowRunner` class is a straightforward way to pass text data in Langflow, specifically because it can be connected to many loaders. It also mentions that generally, a flow expects a string or a dictionary as input. Additionally, it updates the explanation of extracting the content of a document using the `page_content` attribute, which is a string.
This commit is contained in:
Gabriel Luiz Freitas Almeida 2023-07-31 14:51:09 -03:00
commit ec17b4e9d3
1 changed files with 2 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

5
docs/docs/examples/flow-runner.mdx
View file

@ -280,12 +280,11 @@ class FlowRunner(CustomComponent):
return Document(page_content=str(result))
```
We are using a _`Document`_ as input because it is a straightforward way to pass text data in Langflow.
We are using a _`Document`_ as input because it is a straightforward way to pass text data in Langflow (specifically because you can connect it to many [loaders](../components/loaders)).
Generally, a flow will take a string or a dictionary as input because that's what LangChain components expect.
In case you are passing a dictionary, you need to build it according to the needs of the flow you are using.
The content of a document can be extracted using the _`page_content`_ property and passed as an argument to the selected flow. In this example, we are using a Document because it can be parsed by a [Loader](../components/loaders), but
we'd need to process _`page_content`_ depending on the input of the flow we are running.
The content of a document can be extracted using the _`page_content`_ attribute, which is a string, and passed as an argument to the selected flow.
---