...
Introduction
Within the scope of the AI chat trial, the platform automatically created a simple WF for you that imported the documents you uploaded, ran an analysis on them that prepared them for RAG and fed their contents into an AI Search index.
Todo: Turn into GIF showing drag&drop and connection of nodes.
...
Document Analysis
In the document collections (1) [todo: Separate screenshot?], you see all the documents you uploaded. When opening a document there, you’re presented with the analysis view, which allows you to configure the analysis and its steps itself (2), as well as interact with the document (3) by editing and annotating the content directly on the page.
...
Custom workspaces provide the complete power and flexibility of the Acodis platform. With custom workflows a big variety of use-cases can be covered end-to-end featuring
custom data point extractions
digital twin workflows
AI Search
Visual workflow editor
and even custom UI for your very unique use-case
to just name a few.
We understand that every use-case and every set of documents is unique. Custom workspaces enable you to build your workflow around this, optimized for your purpose to leverage today’s AI technologies to its fullest potential.
Table of Content
| Table of Contents | ||
|---|---|---|
|
Workflow
In custom workspaces, workflows can be built using the graphical editor based on so-called workflow resources. Simply drag and drop available resources from their panel on the right-hand side into the workflow. Workflow resources can be created using right-click on the workflow editor.
...
Collections
Collections are folders that store your documents for the workflow design- and exploration phase.
Analyses
An essential part of almost every workflow are analyses. In the analysis, you can configure which steps should be run on your documents with the following main purposes:
Pre-processing
Structuring
Semantic Definitions
Post-processing
Most of the steps allow you to visually interact with your documents. This enables you to specify your workflow according to your individual use-case and train a tailored AI-model.
From the collections you can open documents in the analysis document viewer featuring from the left to right:
The steps control panel
A preview of the document with options to interact with the selected step
Various previews for the extracted data
...
Model evaluation
For each analysis, the steps that are trainable generate models, which you can create and manage here. You can evaluate the model performance, decide which model to use as the default active one, add notes and delete them if no longer needed.
Todo: make gif clicking on evaluation showing detailed F1 scores.
...
models. For each trainable step in the analysis, a separate tailored model is trained on the selected training set using the document state as provided by the previous steps. The performance of each model can be evaluated for each step individually.
...