Upload 2 files

app.py

@@ -0,0 +1,121 @@
+import streamlit as st
+import pandas as pd
+from azure.core.credentials import AzureKeyCredential
+from azure.ai.formrecognizer import DocumentAnalysisClient
+import time
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+
+# Azure Form Recognizer credentials
+endpoint = st.secrets["endpoint"]
+key = st.secrets["key"]
+
+# Initialize DocumentAnalysisClient
+document_analysis_client = DocumentAnalysisClient(
+    endpoint=endpoint, credential=AzureKeyCredential(key)
+)
+
+# Sidebar for document type selection
+document_type = st.sidebar.selectbox(
+    "Select Document Type", ["Invoice", "Receipt", "Identity Document"]
+)
+
+# Center area for file upload
+uploaded_file = st.file_uploader("Choose or drag a file", type=["pdf", "png", "jpg", "jpeg"])
+
+# Initialize session state for processing results
+if "processed" not in st.session_state:
+    st.session_state.processed = False
+    st.session_state.tables = []
+    st.session_state.kv_df = pd.DataFrame()
+
+# Process the uploaded file if the button is clicked
+if uploaded_file is not None:
+    if st.button("Upload and Process"):
+        with st.spinner("Processing..."):
+            time.sleep(1)  # Simulate some delay to show the spinner
+
+            # Analyze the document
+            poller = document_analysis_client.begin_analyze_document(
+                "prebuilt-document", document=uploaded_file
+            )
+            result = poller.result()
+
+            # Extract key-value pairs and store them in a dictionary
+            kv_dict = {}
+            for kv_pair in result.key_value_pairs:
+                if kv_pair.key and kv_pair.value:  # Ensure both key and value exist
+                    kv_dict[kv_pair.key.content] = kv_pair.value.content
+
+            kv_df = pd.DataFrame(list(kv_dict.items()), columns=["Key", "Value"]).T
+
+            # Set the first row as the header
+            header = kv_df.iloc[0]
+
+            # Create a new DataFrame with the header and the remaining rows
+            kv_df = kv_df[1:].reset_index(drop=True)
+
+            # Insert the new header row
+            header_df = pd.DataFrame([header], columns=range(len(header)))
+
+            # Concatenate the header row DataFrame with the original DataFrame
+            kv_df = pd.concat([header_df, kv_df], ignore_index=True)
+
+            st.session_state.kv_df = kv_df
+            st.session_state.tables = []
+
+            if result.tables:
+                for table in result.tables:
+                    temp_kv_df = kv_df.copy()
+
+                    data = []
+                    for cell in table.cells:
+                        data.append([cell.row_index, cell.column_index, cell.content])
+
+                    table_df = pd.DataFrame(data, columns=["row_index", "column_index", "content"])
+                    table_df = table_df.pivot(index="row_index", columns="column_index", values="content")
+
+                    rows_to_add = len(table_df) - len(temp_kv_df)
+                    if rows_to_add > 0:
+                        last_row = temp_kv_df.iloc[-1]
+                        additional_rows = pd.DataFrame([last_row] * rows_to_add, columns=temp_kv_df.columns)
+                        temp_kv_df = pd.concat([temp_kv_df, additional_rows], ignore_index=True)
+
+                    table_with_kv = pd.concat([temp_kv_df, table_df], axis=1, ignore_index=True)
+                    st.session_state.tables.append(table_with_kv)
+
+            st.session_state.processed = True
+
+# Display the results if processing is done
+if st.session_state.processed:
+    st.write("Extracted Key-Value Pairs:")
+    st.dataframe(st.session_state.kv_df)
+
+    if st.session_state.tables:
+        for i, table_with_kv in enumerate(st.session_state.tables):
+            st.write(f"Table {i + 1} with Key-Value Pairs:")
+            st.dataframe(table_with_kv)
+
+            st.download_button(
+                label=f"Download Table {i + 1} as CSV",
+                data=table_with_kv.to_csv(index=False, header=False).encode('utf-8'),
+                file_name=f"table_with_kv_{i + 1}.csv",
+                mime='text/csv',
+            )
+    else:
+        st.write("No tables found in the document.")
+        st.download_button(
+            label="Download Key-Value Pairs as CSV",
+            data=st.session_state.kv_df.to_csv(index=False, header=False).encode('utf-8'),
+            file_name="kv_df.csv",
+            mime='text/csv',
+        )
+
+# Option to remove the file and clear the session
+if st.session_state.processed and st.button("Remove File"):
+    st.session_state.processed = False
+    st.session_state.tables = []
+    st.session_state.kv_df = pd.DataFrame()
+    st.rerun()

requirements.txt

@@ -0,0 +1,52 @@
+altair==5.4.1
+attrs==24.2.0
+azure-ai-documentintelligence==1.0.0b2
+azure-ai-formrecognizer==3.3.3
+azure-ai-vision-imageanalysis==1.0.0b3
+azure-common==1.1.28
+azure-core==1.30.2
+blinker==1.8.2
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+gitdb==4.0.11
+GitPython==3.1.43
+idna==3.8
+isodate==0.6.1
+Jinja2==3.1.4
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+msrest==0.7.1
+narwhals==1.6.0
+numpy==2.1.0
+oauthlib==3.2.2
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+protobuf==5.28.0
+pyarrow==17.0.0
+pydeck==0.9.1
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.1
+referencing==0.35.1
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==13.8.0
+rpds-py==0.20.0
+six==1.16.0
+smmap==5.0.1
+streamlit==1.38.0
+tenacity==8.5.0
+toml==0.10.2
+tornado==6.4.1
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+watchdog==4.0.2