initial

code/main.py

@@ -0,0 +1,65 @@
+
+#!/usr/bin/env python3
+import openai
+import json
+
+openai.api_key = "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"
+def slurp_file(filename):
+    with open(filename, 'r') as file:
+        data = file.read()
+    return data
+
+BASE_PROMPT="""You extract invoice details from pdfs. Always follow this json schema. Do not respond with anything except the raw json response. Do not respond in code blocks(```).
+```
+{}
+```
+""".format(slurp_file('schema.json'))
+
+import sys
+# context = sys.argv[1]
+# problem = sys.argv[2]
+# other = sys.argv[3]
+client = openai.OpenAI(api_key= "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")
+client.api_key = "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"
+def handler(event, context):
+    assistant = client.beta.assistants.create(
+      name="pdf-reader",
+      instructions=BASE_PROMPT,
+      model="gpt-4o",
+      tools=[{"type": "file_search"}],
+    )
+    import urllib.request
+
+    url = event.url
+    with urllib.request.urlopen(url) as response:
+        data = response.read()
+    with open("/tmp/test.pdf", "wb") as f:
+        f.write(data)
+
+    # Upload the user provided file to OpenAI
+    message_file = client.files.create(
+      file=open("/tmp/test.pdf", "rb"), purpose="assistants"
+    )
+     
+    # Create a thread and attach the file to the message
+    thread = client.beta.threads.create(
+      messages=[
+        {
+          "role": "user",
+          "content": "extract the details from this invoice",
+          # Attach the new file to the message.
+          "attachments": [
+            { "file_id": message_file.id, "tools": [{"type": "file_search"}] }
+          ],
+        }
+      ]
+    )
+    run = client.beta.threads.runs.create_and_poll(
+        thread_id=thread.id, assistant_id=assistant.id
+    )
+
+    messages = list(client.beta.threads.messages.list(thread_id=thread.id, run_id=run.id))
+
+    print(run.usage)
+
+    return json.loads(messages[0].content[0].text.value)

code/schema.json

@@ -0,0 +1,32 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema#",
+    "title": "Invoice Data Schema",
+    "description": "A schema to validate invoice data",
+    "type": "object",
+    "properties": {
+        "customer_identifier": {
+            "description": "The customer's name. e.g., ABC Corporation, Microsoft, etc.",
+            "type": "string"
+        },
+        "date": {
+            "description": "Invoice date in ISO 8601 format (YYYY-MM-DD).",
+            "type": "string",
+            "format": "date"
+        },
+        "invoice_number": {
+            "description": "Unique invoice number for the transaction.",
+            "type": "string"
+        },
+        "account_number": {
+            "description": "Customer's account number associated with the invoice.",
+            "type": "string"
+        },
+        "total": {
+            "description": "Total amount of the invoice, including taxes and fees. It should be a decimal number as a string.",
+            "type": "string",
+            "pattern": "^\\d+(\\.\\d{1,2})?$" 
+        }
+    },
+    "required": ["customer_identifier", "date", "invoice_number", "account_number", "total"],
+    "additionalProperties": false
+}