my-aws-helpers 2.6.4__tar.gz → 3.0.0__tar.gz

{my_aws_helpers-2.6.4 → my_aws_helpers-3.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: my_aws_helpers
-Version: 2.6.4
+Version: 3.0.0
 Summary: AWS Helpers
 Home-page: https://github.com/JarrodMccarthy/aws_helpers.git
 Author: Jarrod McCarthy

{my_aws_helpers-2.6.4 → my_aws_helpers-3.0.0}/my_aws_helpers/bedrock.py

@@ -12,7 +12,9 @@ import concurrent.futures
 from dataclasses import dataclass
 
 class PromptType(str, Enum):
-    json = "json_system_prompt.txt"
+    transaction_headers = "transactions_headers_prompt_v2.txt"
+    transactions = "transactions_prompt.txt"
+    # json = "json_system_prompt.txt"
     markdown = "markdown_system_prompt.txt"
 
 
@@ -49,7 +51,7 @@ class OCRResult:
 class Bedrock:
     def __init__(
         self,
-        model_id: str = "apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
+        model_id: str = "anthropic.claude-3-5-sonnet-20241022-v2:0",
         logger = None,
     ):
 
@@ -181,12 +183,30 @@ class Bedrock:
                 except Exception as e:
                     self.logger.error(f"Could not get pix map for page {i}")
                     continue
-            prompt = self._get_prompt(prompt_type=prompt_type)
+            header_ocr_result = None
+            if len(image_bytes_list) > 1:
+                headers_prompt = self._get_prompt(prompt_type=PromptType.transaction_headers.value)
+                for i in range(2):
+                    # try to get headers from the first or second page
+                    header_ocr_result = self._ocr(prompt=headers_prompt, image_bytes=image_bytes_list[i])
+                    if header_ocr_result is None:
+                        self.logger.info(f"No ocr result returned when getting headers {PromptType.transaction_headers.value}")
+                    headers = header_ocr_result.content.get("headers")
+                    if (len(headers) < 1) or (headers is None):
+                        continue
+                    else:
+                        break
+
+            transactions_prompt = self._get_prompt(prompt_type=prompt_type)
+            if header_ocr_result:
+                transactions_prompt = transactions_prompt.replace("#### TABLE HEADERS ####", json.dumps(header_ocr_result.content))
+
             self.logger.info("Got Prompt")
             results = list()
+
             for i, image_bytes in enumerate(image_bytes_list):
                 self.logger.info(f"Starting OCR for page: {i}")
-                results.append(self._ocr(image_bytes=image_bytes, prompt=prompt))
+                results.append(self._ocr(image_bytes=image_bytes, prompt=transactions_prompt))
             return results
         except Exception as e:
             self.logger.exception(e)

my_aws_helpers-3.0.0/my_aws_helpers/prompts/transactions_headers_prompt.txt

@@ -0,0 +1,32 @@
+You are an intelligent document and image interpreter.
+
+Your task is to analyze the provided image and extract the headers of a table that contains transactions.
+
+## Output Requirements
+
+- Return **only valid JSON**.
+- If the image contains one or more **tables**, use only the transactions table represent the headers as a JSON object.
+- **If there is no table containing transactions, return an empty array for the headers**
+- **Do not fabricate** values not visible in the image
+- Do not return anything except the json content
+
+## Example
+
+If the image contains this table:
+
+|  Date  |          | Price |
+| ------ |----------|-------|
+| June 6 | desc 1   | $2.00 |
+| June 5 | misc 2   | $1.70 |
+|        | item x   | $1.50 |
+
+Return:
+
+```json
+{
+  "headers": [
+    { "date": "column 1"},
+    { "description": "column 2"},
+    { "price": "column 3"},
+  ]
+}

my_aws_helpers-3.0.0/my_aws_helpers/prompts/transactions_headers_prompt_v2.txt

@@ -0,0 +1,55 @@
+You are an intelligent document and image interpreter.
+
+Your task is to extract the headers of a table **only if it represents financial transactions**, such as those with dates, descriptions, amounts, or balances.
+
+## Output Format (JSON only)
+
+Return a JSON object in the following structure:
+
+{
+  "headers": [ 
+    { "header_name": "column number" }
+  ]
+}
+
+## Rules
+- DO NOT USE DETAILS sections, DO NOT use Account Summary, Do NOT use Account Details, DO NOT use payment details
+- ONLY Use tables that contain transaction to acquire headers, if you cannot find a table that contains a list of transactions, return:
+{
+  "headers": []
+}
+- Only return headers **if there is a table with transaction-like data** (e.g. purchases, sales, account activity).
+- There will likely be MORE THAN 1 transaction in this table name, if that is not the case, return:
+{
+  "headers": []
+}
+- If no such table exists, return:
+{
+  "headers": []
+}
+- The output must be strictly valid JSON. Do not include markdown, comments, or extra text.
+- Do not fabricate or infer column names. Only return headers that are clearly **visible** in the image.
+- Do not guess. If unsure or incomplete, treat it as missing and return an empty array.
+
+## Examples
+
+✅ If the image contains a table with row headers like:
+| Date | Description | Amount |
+Return:
+{
+  "headers": [
+    { "date": "column 1" },
+    { "description": "column 2" },
+    { "amount": "column 3" }
+  ]
+}
+
+❌ If no table with transaction data is present, return:
+{
+  "headers": []
+}
+
+Do not return anything else, if you are not sure, return:
+{
+  "headers": []
+}

my_aws_helpers-2.6.4/my_aws_helpers/prompts/json_system_prompt.txt → my_aws_helpers-3.0.0/my_aws_helpers/prompts/transactions_prompt.txt

@@ -7,10 +7,13 @@ Your task is to analyze the provided image and extract all meaningful data as st
 - Return **only valid JSON**.
 - If the image contains one or more **tables**, represent each row as a JSON object.
 - Use **the table headers as keys**.
+- if the table headers are not present use:
+#### TABLE HEADERS ####
+- if i have just told you to use "TABLE HEADERS", ignore that instruction
 - if there are multiple sections, only include the row data in transactions
 - Every row should have the consistent headers
 - If content is unclear, use: `"[Unclear]"`.
-- **Do not fabricate** values not visible in the image.
+- **Do not fabricate** values not visible in the image, if the image is empty, return an empty array for the transactions
 - if a descripion contains 2 lines of text, only include the most important text and the text should reside in 1 key in json response, do not split it
 - Do not return anything except the json content
 

{my_aws_helpers-2.6.4 → my_aws_helpers-3.0.0}/my_aws_helpers.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: my-aws-helpers
-Version: 2.6.4
+Version: 3.0.0
 Summary: AWS Helpers
 Home-page: https://github.com/JarrodMccarthy/aws_helpers.git
 Author: Jarrod McCarthy

{my_aws_helpers-2.6.4 → my_aws_helpers-3.0.0}/my_aws_helpers.egg-info/SOURCES.txt

@@ -19,6 +19,8 @@ my_aws_helpers.egg-info/requires.txt
 my_aws_helpers.egg-info/top_level.txt
 my_aws_helpers.egg-info/zip-safe
 my_aws_helpers/prompts/__init__.py
-my_aws_helpers/prompts/json_system_prompt.txt
 my_aws_helpers/prompts/markdown_system_prompt.txt
+my_aws_helpers/prompts/transactions_headers_prompt.txt
+my_aws_helpers/prompts/transactions_headers_prompt_v2.txt
+my_aws_helpers/prompts/transactions_prompt.txt
 tests/test_event.py

{my_aws_helpers-2.6.4 → my_aws_helpers-3.0.0}/setup.py

@@ -3,7 +3,7 @@ from setuptools import find_namespace_packages, setup
 
 base_path = os.path.abspath(os.path.dirname(__file__))
 
-version = "2.6.4"
+version = "3.0.0"
 
 setup(
     name="my_aws_helpers",