flowise
package globally:
flowise
server. The command below starts a server that defaults to http://localhost:300
:
+ Add Variable
at the top-right.Add
.
+ Add New
at the top right to open the Flowise canvas.
Save
.
+
icon at the top left and search for “HTTP” using the search bar.
+ Add Query Params
to set the target URL parameter. We’ll retrieve this URL dynamically from the chat box:
url
in the Key field.{{
) in the Value field. This loads dynamic input options.+ Add Query Params
and type apikey
in the Key field. Type {{
inside the Value and select $vars.ZENROWS_API_KEY
.
+ Add Query Params
repeatedly to add each of the following ZenRows parameters in order:
js_render
= true
premium_proxy
= true
wait
= 2500
css_extractor
= original_status
= true
css_extractor
value: We’ll use the following css_extractor
for this tutorial:
Flowise Canvas
. Then, click the Validate Nodes
icon at the top right and select Validate Nodes
to confirm that your setup is correct.
save
icon at the top right to save your changes.
Process Flow banner
in the chat box.
+
icon at the top left. Search LLM. Then, drag and drop it in the canvas next to the Scraper Agent.
ChatOpenAI
.
ChatOpenAI
Parameters:
Connect Credentials
, then on Create New
and set up your OpenAI API key and click Add
.+ Add Messages
:
Assistant
.{{
inside the Content field and select httpAgentflow_0
.Enable Memory
.
{{ httpAgentflow_0 }}
as the output and not attempt to visit any URL provided in the chat:
+ Add New
to start a new flow.
+
at the top left of the Flowise canvas.
Custom Function
and drag its card to the canvas.
axios
, configure the target URL to accept a search term, and load your ZenRows API key from the Flowise environment variables.
searchTerm
variable, click + Add Input Variables
.
searchTerm
inside the Variable Name field.
{{
in the Variable Value and select question
.
css_extractor
and return the response data. See the complete code below:
+
icon.
Custom Function 1
agent node and rename it (e.g., Data Cleaner).
+ Add Input Variables
. Then, type scrapedData in the Variable Name field. Then, enter {{
in the Variable Value field and select customFunctionAgentflow_0
.
+
icon.
ChatOpenAI
or your preferred model.
+ Add Messages
under the Messages section.
customFunctionAgentflow_1
is the cleaned data from the Data Cleaner agent node.
Assistant
. Then, enter the prompt into the Content field.
Assistant Message
.
css_extractor
array correctly.localhost unavailable
or the Flowise interface doesn’t loadWill ZenRows charge me extra for integrating Flowise?
Are there alternatives to Flowise?
Can I save the extracted data from Flowise to Google Sheets?
Does ZenRows bypass anti-bots on Flowise?