Update services/ocr_service.py

services/ocr_service.py

@@ -8,7 +8,8 @@ from pdf2image import convert_from_path
 
 
 class OCRService:
-    def __init__(self):
+    def __init__(self, LLAMAPARSE_API_KEY):
+        self.llama_parse_key = LLAMAPARSE_API_KEY
         return
 
     def extract_ocrless_pdf(self, filepath):
@@ -85,3 +86,29 @@ class OCRService:
                 del chunks[id]
 
         return chunks
+
+    def llama_parse_ocr(self, file_path):
+        llamaparse_url = 'https://api.cloud.llamaindex.ai/api/parsing/upload'
+        headers = {
+            'accept': 'application/json',
+            'Authorization': f'Bearer {self.llama_parse_key}'
+        }
+        files = {
+            'file': (file_path, open(file_path, 'rb'), 'application/pdf')
+        }
+        response = requests.post(llamaparse_url, headers=headers, files=files)
+        print(response.json())  # If you want to print the JSON response
+
+        job_id = response.json()["id"]
+        result_type = "markdown"
+
+        llamaparse_result_url = f"https://api.cloud.llamaindex.ai/api/parsing/job/{job_id}/result/{result_type}"
+
+        # check for the result until its ready
+        while True:
+            response = requests.get(llamaparse_result_url, headers=headers)
+            if response.status_code == 200:
+                break
+
+
+        return response.json()['markdown']