Upload app.py

app.py

@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+"""API prog
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1dwnXx2hUYegX54dlWrXEF8uF_Jj7QxX5
+"""
+
+!pip install groq pypdf gradio
+
+from groq import Groq
+from pypdf import PdfReader
+import gradio as gr
+
+# ---------------------------------------
+# 1. Initialize Groq Client
+# ---------------------------------------
+client = Groq(api_key="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")
+
+
+# ---------------------------------------
+# 2. Extract text from PDF
+# ---------------------------------------
+def extract_pdf_text(pdf_file):
+    reader = PdfReader(pdf_file.name)
+    text = ""
+    for page in reader.pages:
+        extracted = page.extract_text()
+        if extracted:
+            text += extracted + "\n"
+    return text
+
+
+# ---------------------------------------
+# 3. Ask Groq to classify + extract fields
+# ---------------------------------------
+def analyze_document(text):
+    prompt = f"""
+You are an expert document analysis AI.
+
+Given the following document text, do 3 things:
+
+1. Identify the document type (invoice, receipt, contract, report, certificate, etc.)
+2. Extract key fields in JSON format.
+3. Provide a short summary.
+
+Document text:
+{text}
+
+Return your answer in this JSON structure:
+
+{{
+  "document_type": "",
+  "fields": {{}},
+  "summary": ""
+}}
+"""
+
+    response = client.chat.completions.create(
+        model="llama-3.1-8b-instant",
+        messages=[{"role": "user", "content": prompt}],
+        temperature=0
+    )
+
+    return response.choices[0].message.content