Video

Thank you bro🙏

Thank you so much! :)

Hello Akshay< Thank you for the comment and a great question. Yes, the recommended one is to always use the base version (version 0) for the minor version. It was a small mistake on my side when I created the video.. Unfortunately I cannot edit that part on this one. But I published a separate video following this explaining which one to go with. So you are correct. it should always be zero for the minor version.

Hello.. Sorry for the late response. You can use the latest Document Understanding activities to perform this task. It’s possible to dynamically assign prompts in the latest one. I also built similar workflows and it’s working perfectly 😊

Hi Shirish, In the Generate Data Table Wizard (timestamp 16:08), im using the option "[NewLine]" from the dropdown o specify the line separator.

Hello.. Hmm... I used it recently as well for something similar and it worked as usual. I don't think anything changed to not give you the JSON output. Maybe try with different prompts to see if it works?

Thank you bro!

Yes... more videos are coming in the next few days. I got busy with some project work and that's why the delay!! :)

Hello, Hmm.. I would like to see your code. Maybe you can share a screenshot on WhatsApp or my email?

Sure. Will send you via WhatsApp

Sure. I have texted you on linkedin.

Hi.. Classification is not a part of this as it is very well explained in the Advanced Document Understanding course. It’s exactly the same. Suggest you look for the classification video set in that series my friend

Hey Rohit, Seems like you are writing the output into a single excel file. I think what you can do is: before writing you can check whether the file is in use by another process. You can use a Retry activity inside a try catch. This way you can attempt to write, if fails wait for sometime and then try again in a loop.. What are your thoughts?

Hi Lahiru, Thank you so much for quick response. I tried adding the append activity in the retry scope and it worked seamlessly.

Anchors help adjust your template for slight changes like changes that happen while scanning. For example, scaling into smaller sizes, skewing, landscape, portrait page changes etc.

@@LahiruFernando Is it possible to have combination of anchor and custom area?

@@Kalbo07 Yes it is possible to have a custom area along with an Anchor. Al you have to do is the following: Once you are in the template editor, on the top there is an option to select Custom Area, Anchor, Token, etc. Select Anchor option. Now highlight the custom area that you want to extract (also known as the Target) and then indicate the anchors you want to include for the target. You can have one or many anchors depending on your use cases for a target

Hello, At the moment retraining is only available for Machine Learning extractor because it uses AI models. The other extractors (regex and Form Extractor) are more rule based. Hence, those cannot be retrained. However, you can of course update the regex/ template configurations to make it capture more variations. For example: - add more dynamic regex patterns to capture text - add dynamic capabilities in templates like Anchors to allow slight variations in the structure (especially for scanned documents) - refine the capture regions in templates

@@LahiruFernando Thanks a lot man

Thank you so much 😀

Hey.. Im not sure how I missed your comment. Sorry for the late reply.. I'm referring to this one: "/" You can actually download Form 4 documents online for any company. It's publicly available. Do a quick Google search for SEC Form 4 for any company.

Communication mining is coming soon!! I’m just a little bit slow until DevCon is over 😀

Please Lahiru my exam is in 11 days, I need you man!@@LahiruFernando

Hi.. Well, I don't think a developer should be an expert in UiPath Insights. Its a different product used for monitoring the automations. If I'm a developer, I haven't seen any requirement for me to know Insights as of now. However, its something good to know and have an understanding about what happens there. But for an Architect, yes they need to know about Insights.

@@LahiruFernando Thanks for the reply.

Thank you so much 😀

Hi, Thank you so much for sharing your thoughts. This means a lot. Yes, the video is a bit old now and things are slightly different. But still, the concept we follow is the same. That’s the main thing we need to learn.. Great to hear you still find it helpful. Thanks once again for sharing

There will be quite a lot actually. We have to cover everything about AI Center, DU, and Communication mining. I also refer to old videos I already have so we don’t need to repeat the content. Every video has a lot of related videos and documentation links that you can refer to for additional in-depth knowledge.. But do you think it’s a good idea to post something that includes the list of topics in this series (including the ones that are yet to be published)?

Hello, In the machine learning extractor activity, have you retrieved the latest fields from the model? You can do this by clicking on Configure Extractors on the data extraction scope and clicking on the settings button for ML extractor. There you’ll see a button called Get Capabilities

@@LahiruFernando Thanks for your quick reply sir.. after retrain the model I can able to see the fields

@@bhavanakoturu597 Awesome... So its sorted :)

Actually, I found an invoice in one of the folders from the performer. Not sure if there are any others besides this one, but at least I have this one.

HI.. thanks for the feedback. Im working on it.. You'll get improved audio soon :)

@@LahiruFernando thank you sir...one more thing please upload a end to end use case project in du with ai center...and du framework also it will very helpfull for us...thanks

@@user-nh5ot9fq1j will surely do along with these videos. Thanks for your suggestion my friend

Hello my friend, Really happy to know you love the videos. Thank you so much for the awesome feedback and improvement ideas. I’m always happy to hear it and it means a lot. I will consider this and do my best to improve. I just started my vacation. So have time to look into it more 😀 Thanks again for the awesome tips my friend..

Hello.. That’s a weird error.. Have you used the schema from out of the box model or did you create it from scratch?

@@LahiruFernando I used India invoice scheme from box model

@@j.v.manojkumar2673 Can you try the Normal Invoice model and see if that works?

@@LahiruFernando Sure I will try it and let you know. Thanks for responding.

Hello, Have you enabled the Extractor to extract the fields through the Configure Extractors option in the Data Extraction Scope? If that doesn't work, try whether it is working on a trained document. If not, you may need more sample documents to train the model better. Let me know if this helps

Yes Sir I have configured the extractor and on get capability I am getting all the required fields

On the invoice type document it is working but then on generic it is not working, I have 20 sample data so I just used 10 let me add a few more and check

It is already available in the UiPath Academy under Learning Plans

HI, You can use the File Exists activity. It gives the IResource output for all files stored in the local drives.

Hi.. You can go through the advanced document understanding course to understand how to create workflows. You can also check the model training playlist for ml training.. This video has a QR that you can use to connect with me on WhatsApp. Scan and let’s connect 😊