Yes, we have been populated mineral concentration databases for our mining sector customers with tabular and textual data captured from PDFs and images.

Yes we provide search and metadata-based filtering options to route your natural language questions to the right documents, and then utilize retrieval augmented generation (RAG) to find the best text for an LLM to answer your question.

Yes we always attend PDAC and would be happy to meet you there to demonstrate our AI technology to capture structured data from mining exploration documents.

Sure! Our platform proposes a very advanced table detection, classification and segmentation which can be applied on any tabular data.

We also know that the accuracy for table data capture must be close to 100%, therefore our user interface proposes a set of tools to refine the table detection and segmentation when needed.

The detection of relationships between the assays, the sample tables and the collar tables is done by some post-processing APIs.

This APIs are designed to produce huge volume of structured (DB, json or csv) and trustable data.

Absolutely! The AgileDD solution provides a chatbot to you to query your documents in natural language. Thanks to an advanced search tool and the RAG technology (Retrieval Augmented Generation), it is possible to query one or several documents with very satisfactory replies. Using the AgileDD chatbot you will be fascinated with the possibility to discuss some subsurface topics with all the geologists who have been working on your assets in the past!

Certainly. Classifying documents into pre-defined categories is frequently the first step a data management process.

It has to be done accurately because the classification may be the foundation of future document management automation.

The AgileDD platform authorizes you to define a set of categories for documents, pages, figures, tables or paragraphs and train some adapted supervised models.

The models start to learn with less than 20 documents.

This makes possible an iteration where you will benefit from the early stage of the models to rapidly label other documents, inject your feedback on the initial classification result and rapidly reach the classification accuracy level you need.

And remember, classification taxonomies frequently need to be adjusted over time.

The AgileDD platform authorizes the adjustment of your classification over the time for each of your projects.

AgileDD is agile!

This platform is made-up of a set of APIs used for the UI and all the AI tasks.

Using the APIs you can build workflows to extract the information from documents using existing models or to access pre-captured information and to output into structured formats such as CSV or JSON formats or SQL input records.

Maturing a model may be a continuous and iterative process which is important to monitor.

Versioning the models and knowing their main characteristics is also very important.

Therefore, we have developed a model governance tool to access the characteristics of the models such as their training data, the performance (precision, recall, F1-score) or the way they converge in the case of a computer vision model.

All this information is important for the project manager to select the right model version, the one which has the best performance for it needs.

Definitively, yes. The geology of the drill hole is frequently reported as a log with text description and/or graphical intervals.

AgileDD can be trained to capture the graphical pattern describing the intervals but also to detect the geological descriptions.

The descriptions can be analyzed to recognize the lithology, the alteration, the structuration, and eventually the type and strength of the mineralization.

As with any capture of information done by the AgileDD platform, the information is sourced by its location in the document and can be exported along a depth axis per drill hole.

Once injected into our platform, you can directly start exploring your data set and be guided for this type of “needle in the haystack” data capture.

At first, you can use our advanced search which not only uses the full-text index of your documents but also integrates some filtering options on the classification and the textual or graphical detections you may have done earlier.

You can also continue the search using the chatbot and get more detailed and sourced occurrences of the mineralization you are looking for.

Thanks to RAG (Retrieval Augmented Generation) and advanced prompts for In-Context Learning, your information capture strategy will be based on some geological reasoning and not only keyword filtering.

If needed, this can be completed by fine-tuning a generative AI model to specialize it run very accurately this type of search with a very high level of accuracy and exhaustivity.