WIP

app/agents/invoice_agent.py

@@ -15,11 +15,14 @@ The document's primary language is '{language}'.
 ## Instructions:
 Carefully analyze the invoice image and extract the following fields according to these specific rules. Do not invent information. If a field is not found or is unclear, follow the specific instruction for that field.
 
-- `date`: Extract in YYYY-MM-DD format. If unclear, leave as an empty string.
+- `invoice_date`: The invoice date. Extract in YYYY-MM-DD format. If unclear, leave as an empty string.
+- `invoice_due_date`: The invoice due date.Extract in YYYY-MM-DD format. If unclear, leave as an empty string.
 - `invoice_number`: If not found or unclear, leave as an empty string.
+- `ocr_number`: The OCR number from the invoice. If not found or unclear, leave as an empty string.
 - `supplier_number`: This is the organisation number. If not found or unclear, leave as an empty string.
 - `biller_name`: This is the sender's name. If not found or unclear, leave as an empty string.
 - `amount`: Extract the final total amount and format it to a decimal number. If not present, leave as null.
+- `tax_exclusive_amount`: Extract the the amount excluding taxes and format it to a decimal number. If not present, leave as null.
 - `customer_name`: This is the receiver's name. Ensure it is a name and clear any special characters. If not found or unclear, leave as an empty string.
 - `customer_address`: This is the receiver's full address. Put it in one line. If not found or unclear, leave as an empty string.
 - `customer_address_line`: This is only the street address line from the receiver's address. If not found or unclear, leave as an empty string.
@@ -33,7 +36,7 @@ Carefully analyze the invoice image and extract the following fields according t
 - `bank_giro`: If found, extract the bank giro number. It often follows patterns like 'ddd-dddd', 'dddd-dddd', or 'dddddddd #41#'. If not found or unclear, leave as an empty string.
 - `plus_giro`: If found, extract the plus giro number. It often follows patterns like 'ddddddd-d #16#', 'ddddddd-d', or 'ddd dd dd-d'. If not found or unclear, leave as an empty string.
 - `customer_ssn`: If found, extract the customer social security number (personnummer). It follows the pattern 'YYYYMMDD-XXXX' or 'YYMMDD-XXXX'. If not found or unclear, leave as an empty string.
-- `line_items`: Extract all line items from the invoice. For each item, extract the `description`, `quantity`, `unit_price`, and `total_price`. If a value is not present, leave it as null.
+- `line_items`: Extract all line items from the invoice. For each item, extract the `description`, `quantity`, `unit_price`, and `total_price`. A list of all line items from the invoice. Make sure all of them are extracted. If a value is not present, leave it as null.
 
 ## Example:
 If the invoice shows a line item "Consulting Services | 2 hours | $100.00/hr | $200.00", the output for that line item should be:

app/core/ocr.py

@@ -4,20 +4,16 @@ from typing import List
 
 
 def extract_text_from_images(images: List[Image.Image]) -> str:
-    """
-    使用Tesseract OCR从一系列图片中提取并合并所有文本。
-    """
-    print("--- [Core OCR] 正在从图片中提取文本用于向量化...")
+    print("--- [Core OCR] Extracting text...")
     full_text = []
     for img in images:
         try:
-            # lang='chi_sim+eng' 表示同时识别简体中文和英文
             text = pytesseract.image_to_string(img, lang='chi_sim+eng')
             full_text.append(text)
         except Exception as e:
-            print(f"--- [Core OCR] 单页处理失败: {e}")
+            print(f"--- [Core OCR] Processing image failed: {e}")
             continue
 
     combined_text = "\n\n--- Page Break ---\n\n".join(full_text)
-    print("--- [Core OCR] 文本提取成功。")
+    print("--- [Core OCR] Text extraction completed.")
     return combined_text

app/schemas.py

@@ -32,11 +32,14 @@ class LineItem(BaseModel):
 
 class InvoiceInfo(BaseModel):
     """Defines the detailed, structured information to be extracted from an invoice."""
-    date: Optional[str] = Field("", description="Extract in YYYY-MM-DD format. If unclear, leave as an empty string.")
+    invoice_date: Optional[str] = Field("", description="The invoice date. Extract in YYYY-MM-DD format. If unclear, leave as an empty string.")
+    invoice_due_date: Optional[str] = Field("", description="The invoice due date.Extract in YYYY-MM-DD format. If unclear, leave as an empty string.")
     invoice_number: Optional[str] = Field("", description="If not found or unclear, leave as an empty string.")
+    ocr_number: Optional[str] = Field("", description="The OCR number from the invoice. If not found or unclear, leave as an empty string.")
     supplier_number: Optional[str] = Field("", description="It's the organisation number. If not found or unclear, leave as an empty string.")
     biller_name: Optional[str] = Field("", description="It's the sender's name. If not found or unclear, leave as an empty string.")
     amount: Optional[float] = Field(None, description="Extract and format to decimal. If not present, leave as null.")
+    tax_exclusive_amount: Optional[float] = Field(None, description="Extract the the amount excluding taxes and format it to a decimal number. If not present, leave as null.")
     customer_name: Optional[str] = Field("", description="It's the receiver's name. Clean any special chars from the name. If not found or unclear, leave as an empty string.")
     customer_address: Optional[str] = Field("", description="It's the receiver's address. Put it in one line. If not found or unclear, leave as an empty string.")
     customer_address_line: Optional[str] = Field("", description="It's the receiver's address line, not the whole address. If not found or unclear, leave as an empty string.")
@@ -50,4 +53,4 @@ class InvoiceInfo(BaseModel):
     bank_giro: Optional[str] = Field("", description="BankGiro number, e.g., '123-4567'. If not found, leave as an empty string.")
     plus_giro: Optional[str] = Field("", description="PlusGiro number, e.g., '123456-7'. If not found, leave as an empty string.")
     customer_ssn: Optional[str] = Field("", description="Customer's social security number, e.g., 'YYYYMMDD-XXXX'. If not found, leave as an empty string.")
-    line_items: List[LineItem] = Field([], description="A list of all line items from the invoice.")
+    line_items: List[LineItem] = Field([], description="A list of all line items from the invoice. Make sure all of them are extracted.")