llm app

.gitignore

@@ -0,0 +1 @@
+.env

Readme.md

@@ -0,0 +1,11 @@
+---
+title: Invoice Extractor Using Gemini
+emoji: 📈
+colorFrom: yellow
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.39.0
+app_file: app.py
+pinned: false
+---
+

app.py

@@ -0,0 +1,60 @@
+from PIL import Image
+import google.generativeai as genai # type: ignore
+import streamlit as st
+from dotenv import load_dotenv
+import os
+load_dotenv()
+
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+# load gemini pro vision
+model = genai.GenerativeModel("gemini-1.5-flash")
+
+def input_image_details(upload_file):
+    if upload_file is not None:
+        # read the file into bytes
+        bytes_data= upload_file.getvalue()
+        
+        image_parts = [
+            {
+                "mime_type":upload_file.type,
+                "data":bytes_data
+            }
+            
+        ]
+        return image_parts
+    else:
+        raise FileNotFoundError("No file uploaded")
+    
+
+def get_gemni_response(prompt, image,user_input):
+    response = model.generate_content([prompt, image[0], user_input])
+    return response.text
+
+
+#initilize our streamlite app
+st.set_page_config(page_title="Multilanguage Invoice Extractor ")
+st.header("MultiLanguage Invoice Extractor")
+user_input = st.text_input("Input Prompt", key="input")
+upload_file = st.file_uploader("choose an image of the invoice..", type=["jpg","jpeg","png"])
+
+# to show the uploaded image
+if upload_file is not None:
+    image = Image.open(upload_file)
+    st.image(image, caption="upload Image.", use_column_width=True)
+    
+    
+submit = st.button("Tell me about the Invice")
+
+prompt = """
+Your are an expert in understanding invoice. We will upload a image as invoice 
+and you will have to answer any questions based on the upload invoice image
+"""
+
+
+# if submit buttion is clicked
+if submit:
+    image_data = input_image_details(upload_file)
+    response = get_gemni_response(prompt, image_data, user_input)
+    st.subheader("The response is")
+    st.write(response)

pyproject.toml

@@ -0,0 +1,19 @@
+[tool.poetry]
+name = "invoice extractor llm app using google gemini pro vision large image models"
+version = "0.1.0"
+description = ""
+authors = ["Nasir Abbas <akhtarabbas.islamicreaction@gmail.com>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.12"
+streamlit = "^1.39.0"
+python-dotenv = "^1.0.1"
+pypdf2 = "^3.0.1"
+google-generativeai = "^0.8.3"
+
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -0,0 +1,3 @@
+streamlit 
+python-dotenv 
+google-generativeai