Update app.py

app.py

@@ -12,7 +12,7 @@ import av
 from streamlit_webrtc import webrtc_streamer, VideoProcessorBase, RTCConfiguration
 import cv2
 from typing import List, Union
-from google.cloud import documentai_v1 as documentai
+from google.cloud import documentai
 import pandas as pd
 from google.cloud import bigquery
 from google.cloud.exceptions import NotFound
@@ -243,18 +243,21 @@ def analyze_document(file_content, processor_id, location="us"):
     client = documentai.DocumentProcessorServiceClient(credentials=credentials)
     
     # The full resource name of the processor
-    name = f"projects/{credentials.project_id}/locations/{location}/processors/{processor_id}"
+    processor_name = f"projects/{credentials.project_id}/locations/{location}/processors/{processor_id}"
     
-    # Create document object
-    document = documentai.Document(
-        content=file_content,
-        mime_type="application/pdf"  # Adjust based on input type
-    )
+    # Determine the mime type based on input file type
+    if file_content[:4] == b'%PDF':
+        mime_type = "application/pdf"
+    else:  # Default to image for other types
+        mime_type = "image/jpeg"
+    
+    # Create the request
+    raw_document = documentai.RawDocument(content=file_content, mime_type=mime_type)
     
-    # Configure the process request
+    # Updated API request format
     request = documentai.ProcessRequest(
-        name=name,
-        document=document
+        name=processor_name,
+        raw_document=raw_document
     )
     
     # Process the document
@@ -274,24 +277,32 @@ def analyze_document(file_content, processor_id, location="us"):
     for page in document.pages:
         for table in page.tables:
             table_data = []
-            # Get header row
+            # Get header row if available
             headers = []
-            for cell in table.header_rows[0].cells:
-                headers.append(text[cell.layout.text_anchor.text_segments[0].start_index:
-                                   cell.layout.text_anchor.text_segments[0].end_index])
+            if hasattr(table, 'header_rows') and table.header_rows:
+                for cell in table.header_rows[0].cells:
+                    if cell.layout.text_anchor.text_segments:
+                        segment = cell.layout.text_anchor.text_segments[0]
+                        headers.append(text[segment.start_index:segment.end_index])
+                    else:
+                        headers.append("")
             
             # Get data rows
             for row in table.body_rows:
                 row_data = []
                 for cell in row.cells:
-                    if len(cell.layout.text_anchor.text_segments) > 0:
-                        cell_text = text[cell.layout.text_anchor.text_segments[0].start_index:
-                                       cell.layout.text_anchor.text_segments[0].end_index]
+                    if cell.layout.text_anchor.text_segments:
+                        segment = cell.layout.text_anchor.text_segments[0]
+                        cell_text = text[segment.start_index:segment.end_index]
                         row_data.append(cell_text)
                     else:
                         row_data.append("")
                 table_data.append(row_data)
             
+            # If no header found, create generic column names
+            if not headers and table_data:
+                headers = [f"Column_{i+1}" for i in range(len(table_data[0]))]
+                
             tables.append({"headers": headers, "data": table_data})
     
     return text, entities, tables
@@ -335,6 +346,9 @@ def upload_csv_to_bigquery(file, dataset_id, table_id, append=False):
     # Create client
     bq_client = bigquery.Client(credentials=credentials, project=credentials.project_id)
     
+    # First, ensure dataset and table exist
+    table_ref = create_bigquery_table(dataset_id, table_id)
+    
     # Create a temporary file
     with tempfile.NamedTemporaryFile(delete=False, suffix='.csv') as temp_file:
         temp_file.write(file.getvalue())
@@ -352,10 +366,6 @@ def upload_csv_to_bigquery(file, dataset_id, table_id, append=False):
     else:
         job_config.write_disposition = bigquery.WriteDisposition.WRITE_TRUNCATE
     
-    # Create table reference
-    dataset_ref = bq_client.dataset(dataset_id)
-    table_ref = dataset_ref.table(table_id)
-    
     # Load the file
     with open(temp_file_path, "rb") as source_file:
         job = bq_client.load_table_from_file(