# Uploading Documents
## Overview
Understanding a patient’s history often means piecing together information from many scattered documents such as old chart notes, imaging results, referral letters, scanned forms, and handwritten notes.
This feature lets you upload multiple patient documents (PDFs, TIFFs, JPGs) so the system can organize, interpret, and make sense of them as one connected patient story. Once the documents are uploaded, you can ask questions in plain language to quickly uncover relevant details, trends, or events hidden across the files.
Rather than reading through each file individually, you get a clear, connected view of the patient’s background which helps you move faster and make more informed decisions.
**Supported files:** PDF, PNG, JPG, JPEG, TIFF, TIF, HEIC, CDA (XML format), FHIR (JSON format)
## 1. Open the upload document tool
## 2. Choose the files you want to include
Select the documents that belong to a patient you are reviewing. You can mix and match file formats: for example, upload a PDF of prior notes, a TIFF of a scanned referral, and a few JPG images of lab reports all at once. You can browse for the files on your computer or simply drag and drop them into the upload window. The system will process them together to build a unified view of that patient’s history.
{% hint style="warning" %}
Make sure you are only uploading documents that belong to the same patient and that there are enough medical files to create a summary. Mixing files from different patients will create incorrect or incomplete results.
{% endhint %}
## 3. Explore the Patient Context
Once the upload is complete, our AI will generate an overview that brings together key details from across all the documents you provided. This view gives you an understanding of the patient’s medical history, showing relevant clinical events, social history, family history, medications, labs, images, surgical history, vitals, upcoming follow-ups and relevant providers so you can quickly get oriented before diving deeper or asking specific questions.
## 4. Ask Questions About the Patient
After reviewing the AI summary, you can dig deeper by asking questions directly from the uploaded documents. Abstractive Health will bring in the most relevant and up-to-date scientific evidence from leading medical journals to give you contextually informed answers.
You might ask questions like:
* *“Based on this patient’s history, what risk factors might increase their likelihood of cardiovascular events?”*
* *“Are there any documented conditions that could affect how this patient responds to anticoagulation therapy?”*
* *“Does the patient’s history support the use of guideline-recommended treatments for heart failure?”*.
The system will analyze the patient’s records alongside trusted clinical evidence to provide focused, reliable answers that assist with your decision-making.
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://resources.abstractivehealth.com/web-app/uploading-documents.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.