feat: Implement report generator service for medical reports

- Added ReportGeneratorService to handle generation of medical reports from uploaded files. - Implemented methods for processing Pnoe CSV data, generating graphs, and calculating analysis metrics. - Integrated Jinja2 for HTML report generation with customizable templates. - Added functionality to convert HTML content to PDF using Playwright. - Ensured proper directory structure for saving generated graphs and reports.
2025-10-03 21:41:00 +01:00
parent 1d8136d6ad
commit 11ee6b192f
13 changed files with 896 additions and 658 deletions
@@ -0,0 +1,64 @@
+import base64
+import os
+
+import requests
+from dotenv import load_dotenv
+
+load_dotenv()
+API_KEY_REF = os.getenv("OPENROUTER_API_KEY")
+
+
+def encode_pdf_to_base64(pdf_path):
+    with open(pdf_path, "rb") as pdf_file:
+        return base64.b64encode(pdf_file.read()).decode("utf-8")
+
+
+def extract_spirometry_table_from_pdf(pdf_path):
+    url = "https://openrouter.ai/api/v1/chat/completions"
+    headers = {
+        "Authorization": f"Bearer {API_KEY_REF}",
+        "Content-Type": "application/json",
+    }
+
+    # Read and encode the PDF
+    base64_pdf = encode_pdf_to_base64(pdf_path)
+    data_url = f"data:application/pdf;base64,{base64_pdf}"
+
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "Please extract the Spirometry table from the pdf and return the values in csv format, "
+                    "note that it is the unit of parameter that is beside it and it should not be a column. "
+                    "The '-' Should be treated as empty values."
+                    "do not add 'csv' at the start or end of the response",
+                },
+                {
+                    "type": "file",
+                    "file": {"filename": "document.pdf", "file_data": data_url},
+                },
+            ],
+        }
+    ]
+
+    payload = {
+        "model": "google/gemini-2.5-flash-lite",
+        "messages": messages,
+    }
+
+    response = requests.post(url, headers=headers, json=payload)
+    response_data = response.json()
+
+    if "choices" in response_data and len(response_data["choices"]) > 0:
+        content = response_data["choices"][0]["message"]["content"]
+
+        # Save to a CSV file
+        output_file = "extracted_spirometry_table.csv"
+        with open(output_file, "w", encoding="utf-8") as f:
+            f.write(content)
+
+        return f"Extracted table saved to {output_file}"
+    else:
+        return "No content found in response"