Spaces:
Sleeping
Sleeping
Update extract_and_store_supabase.py
Browse files
extract_and_store_supabase.py
CHANGED
|
@@ -1,17 +1,81 @@
|
|
| 1 |
from supabase_models import Supabase_Client
|
| 2 |
|
| 3 |
|
| 4 |
-
def
|
|
|
|
| 5 |
if attachment_id and message_id:
|
|
|
|
|
|
|
|
|
|
| 6 |
extension = attachment.filename.split(".")[-1]
|
| 7 |
file_name = f"{message.id}_{attachment.attachment_id}.{extension}"
|
| 8 |
print(f"file_name: {file_name}")
|
| 9 |
supabase = Supabase_Client().instance
|
| 10 |
try:
|
| 11 |
-
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
)
|
| 14 |
-
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
except Exception as e:
|
| 17 |
print(f"Error downloading or encoding file: {e}")
|
|
|
|
| 1 |
from supabase_models import Supabase_Client
|
| 2 |
|
| 3 |
|
| 4 |
+
def extract_structure_store_message(user_id:str,message_id:str , attachment_id:str):
|
| 5 |
+
|
| 6 |
if attachment_id and message_id:
|
| 7 |
+
project_id = os.getenv('PROJECT_ID')
|
| 8 |
+
processor_id = os.getenv('PROCESSOR_ID')
|
| 9 |
+
document_entities = {}
|
| 10 |
extension = attachment.filename.split(".")[-1]
|
| 11 |
file_name = f"{message.id}_{attachment.attachment_id}.{extension}"
|
| 12 |
print(f"file_name: {file_name}")
|
| 13 |
supabase = Supabase_Client().instance
|
| 14 |
try:
|
| 15 |
+
response = supabase.storage.from_("receipt_radar").download(
|
| 16 |
+
file_name
|
| 17 |
+
)
|
| 18 |
+
base64_data = urlsafe_b64encode(response).decode('utf-8')
|
| 19 |
+
|
| 20 |
+
payload = {
|
| 21 |
+
"skipHumanReview": True,
|
| 22 |
+
"rawDocument": {
|
| 23 |
+
"mimeType": f"application/{file_type}",
|
| 24 |
+
"content": base64_content
|
| 25 |
+
}
|
| 26 |
+
}
|
| 27 |
+
|
| 28 |
+
access_token = get_access_token_v1()
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
headers = {
|
| 32 |
+
'Authorization': f'Bearer {access_token}',
|
| 33 |
+
'Content-Type': 'application/json; charset=utf-8'
|
| 34 |
+
}
|
| 35 |
+
|
| 36 |
+
response = requests.post(
|
| 37 |
+
f'https://us-documentai.googleapis.com/v1/projects/{project_id}/locations/us/processors/{processor_id}:process',
|
| 38 |
+
headers=headers,
|
| 39 |
+
json=payload
|
| 40 |
)
|
| 41 |
+
response_json = response.json()
|
| 42 |
+
allowed_entities = [
|
| 43 |
+
"due_date",
|
| 44 |
+
"invoice_date",
|
| 45 |
+
"total_amount",
|
| 46 |
+
"total_tax_amount",
|
| 47 |
+
"receiver_name",
|
| 48 |
+
"invoice_id",
|
| 49 |
+
"currency",
|
| 50 |
+
"receiver_address",
|
| 51 |
+
"invoice_type",
|
| 52 |
+
"supplier_name",
|
| 53 |
+
"payment_terms",
|
| 54 |
+
"line_item",
|
| 55 |
+
"line_item/description",
|
| 56 |
+
"line_item/quantity",
|
| 57 |
+
"line_item/amount",
|
| 58 |
+
"line_item/unit_price"
|
| 59 |
+
]
|
| 60 |
+
raw_text = response_json.get('document').get('text' , None)
|
| 61 |
+
entities = response_json.get('document').get('entities' , None)
|
| 62 |
+
document_entities['user_id'] = user_id
|
| 63 |
+
document_entities['raw_text'] = raw_text
|
| 64 |
+
print('Printing entities')
|
| 65 |
+
print(entities)
|
| 66 |
+
if entities is not None:
|
| 67 |
+
for ent in entities:
|
| 68 |
+
if ent.get('type') is not None:
|
| 69 |
+
if entity_type in allowed_entities:
|
| 70 |
+
mention_text = ent.get('mentionText')
|
| 71 |
+
normalised_values = ent.get('normalizedValue') if 'normalizedValue' in ent else None
|
| 72 |
+
document_entities[ent.get('type')] = {"mention_text":mention_text,"normalizedValue":normalised_values}
|
| 73 |
+
|
| 74 |
+
print(document_entities)
|
| 75 |
+
insert_data_response = response = (
|
| 76 |
+
supabase.table("countries")
|
| 77 |
+
.insert(document_entities)
|
| 78 |
+
.execute()
|
| 79 |
+
)
|
| 80 |
except Exception as e:
|
| 81 |
print(f"Error downloading or encoding file: {e}")
|