Hi Team,
I’m working on an invoice automation where we have 150+ vendors and each vendor uses a different invoices format. In document understanding, we can train ML extractor by uploading sample invoices.
I want to understand how we can “train” an LLM Model for this use case.
My Questions:
Is there any way to train the LLM Extractor in UiPath similar to ML Extractor?
Can we upload multiple sample invoices to improve the LLM aacuracy?
Do LLMs support Fine-Tuning for document extraction scenerios?
Should we use RAG(Vector database) or vendor master data instead of training the model?
Is there any recommended approach for large variations(Logos, OCR Differences, missing names etc.)?
My goal is to understand whether LLMs can be trained on vendor invoices formats or if we must rely on:
Prompt engineering
Few-shot examples
RAG(Retrieval Augmented Generation)
Vendor Master Mapping
External LLM Fine-Tuning(OpenAI/Azure)
Any guidance or best practices from the community would be very helpful.
It seems that you have trouble getting an answer to your question in the first 24 hours.
Let us give you a few hints and helpful links.
First, make sure you browsed through our Forum FAQ Beginner’s Guide. It will teach you what should be included in your topic.
You can check out some of our resources directly, see below:
Always search first. It is the best way to quickly find your answer. Check out the icon for that.
Clicking the options button will let you set more specific topic search filters, i.e. only the ones with a solution.
Topic that contains most common solutions with example project files can be found here.
Read our official documentation where you can find a lot of information and instructions about each of our products:
Hopefully this will let you easily find the solution/information you need. Once you have it, we would be happy if you could share your findings here and mark it as a solution. This will help other users find it in the future.
Thank you for helping us build our UiPath Community!
