hi all,
I am building a scenario for reading image by manually reading the image files from google drive.
My question is the open ai seems cannot read the web view link from google drive “Watch files in drive” module.
And after processing the image, what module i should use to get the information i want from image? e.g. im table format in google sheet.
The model is requesting the image. So you would need to give the Data instead of the Web View Link.
L
Not sure if it will help but I created similar automation (in my case the image is analysed by Amazon’s Rekognition - skip the router)
I store image on the google drive but it has one more step, where I download the image (Download the file from GDrive).
Then in Rekognition (that acts like you GPT agent) I have settings as per screenshot.
Welcome to the Make community!
Did you forget to download the file using the file’s link/URL? If it’s not downloaded to the scenario, the next module can’t access the file binary data (contents).
To do this, you can use the HTTP “Get a File” module with the file URL that you need to download. Your file has to be publicly accessible on the internet (doesn’t require authentication).
If it’s hosted on Google Drive, you can also use the respective “Download a file” module.
For more information, see the HTTP page in the Make Help Centre, which covers the following:
If you have an Array of multiple file URLs, you can use an Iterator module, and map the resulting bundle value/URL to the “Get a file” module.
To download multiple files before proceeding to the next module, you can use an Array Aggregator.
Every result (item/record) from trigger/iterator/list/search/match modules will output a bundle. This can result in multiple bundles, which then trigger multiple operations in future modules (one operation per bundle). To “combine” multiple bundles into a single variable, you’ll need to use an aggregator of some sort.
Aggregators are modules that accumulate multiple bundles into one single bundle. An example of a commonly-used aggregator module is the Array aggregator module.
Question: Which type of aggregator do you think you’ll need?
The Array Aggregator module is very powerful because it allows you to build a complex array of collections for a later module’s field to map multiple items (collections) to it.
This is done using the “Target structure type” field in an Array Aggregator module.
Here is an example:
As you can see, the “Map” toggle on complex fields are used when you have an array. You can easily build an array variable to map to a future module’s field, by using an Array Aggregator module and select the “Target Structure Type” as the future module’s field you have mapped the array into.
Question: Are you mapping your array into a field that accepts more than one “item”?
Here are some useful links and guides you can use to learn more on how to use the Make platform, apps, and app modules. I found these useful when I was learning Make, and hope they might benefit you too —
parseDate | tokens for formatDateHope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Investing some effort into the Make Academy will save you lots of time and frustration using Make.
hi,
after i connect to google download file. It runs successfully. After I connect to iterator module
Should I use the web view link as the accessible file link?
Then for iterator, should i use the web view link as the arregated field for further process by open ai?
If you are only processing a single file you don’t need an iterator or aggregator.
If you have downloaded the file using the “Download a file” module, you can just click on the “Map” radio button as shown in the first screenshot in this thread.
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Investing some effort into the Make Academy will save you lots of time and frustration using Make.
Which output bundle in download a file module should i use for the input for open ai?
And if i wanna analyse several images in 1 go, how can i make use of iterator or aggregator?
sorry for not mentioning well.
What i mean is, which output bundles from the download a file module should be used as the input bundle for open ai.
in the example below i map web view link, but when i run the scenario, the web view link is empty, waiting me to provide more information?
Click this and save.
You cannot individually run each module if you don’t know example values of the “Data”.
Try running the full scenario by clicking the “Run Once” button.
For more information, see these duplicate questions previously asked and answered by other community members:
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Investing some effort into the Make Academy will save you lots of time and frustration using Make.
i select image to map and run once for the scenario.
There is BundleValidationError. So I export the scenario as blueprint.
Any steps i miss in setting up the scenario?
blueprint.json (18.1 KB)
You did not select the field circled in red. Your screenshot has changed. Try to revert to the point where you provided the step which I responded to.
Go to the Epoch Panel, by right-clicking on the trigger module (polling triggers only), and select “Choose where to start” from the list of options in the context menu.
If you select “From now on”, the next time the scenario runs it will only return new data (or nothing if there is no new data).
You can also select other old data to re-run your scenario with next using the “Choose manually” option. This will then show you a list of previous historical items you can select to process the next time the scenario is triggered.
For more information, see
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Investing some effort into the Make Academy will save you lots of time and frustration using Make.
I am now able to run the scenario. Thank you for your guide.
when i choose all to run and it is able to run the whole and analysis the images.
No problem, glad I could help!
1. If anyone has a new question in the future, please start a new thread. This makes it easier for others with the same problem to search for the answers to specific questions, and you are more likely to receive help since newer questions are monitored closely.
2. The Make Community guidelines encourages users to try to mark helpful replies as solutions to help keep the Community organized.
This marks the topic as solved, so that:
To do this, simply click the checkbox at the bottom of the post that answers your question:
3. Don’t forget to like and bookmark this topic so you can get back to it easily in future!
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Investing some effort into the Make Academy will save you lots of time and frustration using Make.
