support output tables as markdown format from pdf documents

instructions/table_extraction_prompts.txt

@@ -0,0 +1,21 @@
+Context:
+{page_text}
+
+Instructions:
+Please read the contex carefully.
+Answer below questions:
+1. Please find the table or tables in the context.
+2. Output the table contents as markdown format, it's like: 
+|name|age|hobby|
+|Annie|18|music|
+The contents should be exactly precise as the context.
+3. Please output the results as JSON format, the result member is with legal markdown table format, the example is:
+{
+"tables": ["
+|name|age|hobby|
+|Annie|18|music|
+"]
+}
+4. Only output JSON with tables
+
+Answer:

main.py

@@ -0,0 +1,5 @@
+def main():
+    print("Hello World!")
+    
+if __name__ == "__main__":
+    main()

pdf_table_extraction.py

@@ -0,0 +1,99 @@
+import pandas as pd
+import os
+import tqdm
+import json
+from glob import glob
+import fitz
+import re
+import time
+
+from utils.logger import logger
+from utils.pdf_download import download_pdf_from_documents_warehouse
+from utils.pdf_util import PDFUtil
+from utils.gpt_utils import chat
+
+
+class PDFTableExtraction:
+    """
+    Iterate PDF pages
+    Extract tables from PDF pages
+    Save these tables as markdown files
+    """
+    def __init__(self, 
+                 pdf_file: str,
+                 output_folder: str) -> None:
+        self.pdf_file = pdf_file
+        self.pdf_file_name = os.path.basename(pdf_file)
+        self.table_extraction_prompts = self.get_table_extraction_prompts()
+        
+        self.output_folder = output_folder
+        os.makedirs(output_folder, exist_ok=True)
+        
+        self.prompts_output_folder = os.path.join(output_folder, 'pdf_table_prompts/')
+        os.makedirs(self.prompts_output_folder, exist_ok=True)
+        
+        self.json_output_folder = os.path.join(output_folder, 'pdf_table_json/')
+        os.makedirs(self.json_output_folder, exist_ok=True)
+        
+        self.table_md_output_folder = os.path.join(output_folder, 'pdf_table_markdown/')
+        os.makedirs(self.table_md_output_folder, exist_ok=True)
+    
+    def get_table_extraction_prompts(self):
+        instructions_file = r'./instructions/table_extraction_prompts.txt'
+        with open(instructions_file, 'r', encoding='utf-8') as file:
+            return file.read()
+    
+    def extract_tables(self):
+        try:
+            if self.pdf_file is None or len(self.pdf_file) == 0 or not os.path.exists(self.pdf_file):
+                logger.error(f"Invalid pdf_file: {self.pdf_file}")
+                return
+            logger.info(f"Start processing {self.pdf_file}")
+            pdf_util = PDFUtil(self.pdf_file)
+            success, text, page_text_dict = pdf_util.extract_text(output_folder=self.output_folder)
+            if success:
+                logger.info(f"Successfully extracted text from {self.pdf_file}")
+            
+            for page_num, page_text in page_text_dict.items():
+                try:
+                    self.extract_tables_from_page(page_text, page_num)
+                except Exception as e:
+                    logger.error(f"Error in extracting tables from page {page_num}: {str(e)}")
+        except Exception as e:
+            logger.error(f"Error in extracting PDF tables: {str(e)}")
+    
+    
+    def extract_tables_from_page(self, page_text: str, page_num: int):
+        table_extraction_prompts = self.table_extraction_prompts.replace(r'{page_text}', page_text)
+        response, with_error = chat(table_extraction_prompts)
+        if with_error:
+            logger.error(f"Error in extracting tables from page")
+            return
+        prompts_response = f'{table_extraction_prompts}\n\n{response}'
+        
+        pure_pdf_name = self.pdf_file_name.replace('.pdf', '')
+        prompts_response_file = os.path.join(self.prompts_output_folder, f'{pure_pdf_name}_{page_num}.txt')
+        with open(prompts_response_file, 'w', encoding='utf-8') as file:
+            file.write(prompts_response)
+        
+        json_response = re.search(r'\`\`\`json([\s\S]*)\`\`\`', response)
+        if json_response is None:
+            logger.info(f"Can't extract tables from page")
+            return
+        
+        table_json_text = json_response.group(1)
+        table_data = json.loads(table_json_text)
+        prompts_response
+        self.save_table_data(table_data, page_num)
+
+    def save_table_data(self, table_data: dict, page_num: int):
+        pdf_pure_name = self.pdf_file_name.replace('.pdf', '')
+        json_output_file = os.path.join(self.json_output_folder, f'{pdf_pure_name}_{page_num}.json')
+        with open(json_output_file, 'w', encoding='utf-8') as file:
+            file.write(json.dumps(table_data, indent=4))
+        
+        table_list = table_data.get('tables', [])
+        for table_num, table in enumerate(table_list):
+            table_md_file = os.path.join(self.table_md_output_folder, f'{pdf_pure_name}_{page_num}_{table_num}.md')
+            with open(table_md_file, 'w', encoding='utf-8') as file:
+                file.write(table)

prepare_data.py

@@ -0,0 +1,85 @@
+import pandas as pd
+import os
+import tqdm
+import json
+from glob import glob
+import fitz
+import re
+import time
+
+from utils.logger import logger
+from utils.pdf_download import download_pdf_from_documents_warehouse
+from utils.pdf_util import PDFUtil
+from pdf_table_extraction import PDFTableExtraction
+
+def get_unique_docids_from_doc_provider_data(doc_provider_file_path: str):
+    doc_provider_data = pd.read_excel(doc_provider_file_path)
+    # get new data by grouping by docid, and count the number of rows for each docid,
+    # set the new data with 2 columns: docid and provider_count
+    doc_provider_count = doc_provider_data.groupby('DocumentId').size().reset_index(name='provider_count')
+    # sort new data by provider_count in descending order
+    doc_provider_count = doc_provider_count.sort_values(by='provider_count', ascending=False)
+    
+    # save excel by doc_provider_data and new_data
+    with pd.ExcelWriter(doc_provider_file_path) as writer:
+        doc_provider_data.to_excel(writer, sheet_name='doc_provider_details', index=False)
+        doc_provider_count.to_excel(writer, sheet_name='doc_provider_count', index=False)
+
+def download_pdf(doc_provider_file_path: str, sheet_name: str, pdf_path: str):
+    document_data = pd.read_excel(doc_provider_file_path, sheet_name=sheet_name)
+    # get all unique docids as list
+    doc_id_list = [str(doc_id) for doc_id 
+              in document_data['DocumentId'].unique().tolist()]
+    # download pdfs
+    logger.info(f"Start downloading {len(doc_id_list)} pdfs")
+    os.makedirs(pdf_path, exist_ok=True)
+    for doc_id in tqdm.tqdm(doc_id_list):
+        logger.info(f"Downloading pdf for docid: {doc_id}")
+        download_pdf_from_documents_warehouse(pdf_directory=pdf_path, doc_id=doc_id)
+        time.sleep(1)
+
+
+def output_pdf_page_text(pdf_folder: str, output_folder: str):
+    if pdf_folder is None or len(pdf_folder) == 0 or not os.path.exists(pdf_folder):
+        logger.error(f"Invalid pdf_folder: {pdf_folder}")
+        return
+    if output_folder is None or len(output_folder) == 0:
+        logger.error(f"Invalid output_folder: {output_folder}")
+        return
+    
+    os.makedirs(output_folder, exist_ok=True)
+    pdf_files = glob(os.path.join(pdf_folder, '*.pdf'))
+    logger.info(f"Total {len(pdf_files)} pdf files found in {pdf_folder}")
+    for pdf_file in pdf_files:
+        logger.info(f"Start processing {pdf_file}")
+        pdf_util = PDFUtil(pdf_file)
+        success, text, page_text_dict = pdf_util.extract_text(output_folder=output_folder)
+        if success:
+            logger.info(f"Successfully extracted text from {pdf_file}")
+
+
+def extract_pdf_table(pdf_folder: str, output_folder: str):
+    if pdf_folder is None or len(pdf_folder) == 0 or not os.path.exists(pdf_folder):
+        logger.error(f"Invalid pdf_folder: {pdf_folder}")
+        return
+    if output_folder is None or len(output_folder) == 0:
+        logger.error(f"Invalid output_folder: {output_folder}")
+        return
+    os.makedirs(output_folder, exist_ok=True)
+    
+    pdf_files = glob(os.path.join(pdf_folder, '*.pdf'))
+    logger.info(f"Total {len(pdf_files)} pdf files found in {pdf_folder}")
+    for pdf_file in pdf_files:
+        logger.info(f"Start processing {pdf_file}")
+        pdf_table_extraction = PDFTableExtraction(pdf_file, output_folder)
+        pdf_table_extraction.extract_tables()
+
+
+if __name__ == '__main__':
+    doc_provider_file_path = r"/data/emea_ar/basic_information/English/latest_provider_ar_document.xlsx"
+    pdf_folder = r"/data/emea_ar/pdf/"
+    output_folder = r"/data/emea_ar/output/"
+    # get_unique_docids_from_doc_provider_data(doc_provider_file_path)
+    # download_pdf(doc_provider_file_path, 'doc_provider_count', pdf_folder)
+    # output_pdf_page_text(pdf_folder, output_folder)
+    extract_pdf_table(pdf_folder, output_folder)

utils/gpt_utils.py

@@ -8,31 +8,8 @@ import dotenv
 # loads .env file with your OPENAI_API_KEY
 dotenv.load_dotenv()
 
-
-def set_environment_variables(engine=os.getenv("Engine_0613_16k")):
-    if engine.startswith('gpt4') or engine.startswith('gpt-4'):
-        openai.api_base = os.getenv("OPENAI_API_BASE_DC")
-        openai.api_key = os.getenv("OPENAI_API_KEY_GPT4")
-    elif engine.startswith('modc-stg-gpt4'):
-        openai.api_base = os.getenv("OPENAI_API_BASE_GPT4_MODC")
-        openai.api_key = os.getenv("OPENAI_API_KEY_GPT4_MODC")
-    elif engine.upper() == 'ENGINE_GPT4_TURBO':
-        openai.api_base = os.getenv("OPENAI_API_BASE_GPT4_TURBO")
-        openai.api_key = os.getenv("OPENAI_API_KEY_GPT4_TURBO")
-    elif engine.startswith('modc-stg-gpt35turbo16k'):
-        openai.api_base = os.getenv("OPENAI_API_BASE_GPT3_MODC")
-        openai.api_key = os.getenv("OPENAI_API_KEY_GPT3_MODC")
-    else:
-        openai.api_base = os.getenv("OPENAI_API_BASE")
-        openai.api_key = os.getenv("OPENAI_API_KEY")
-    openai.Engine = engine
-    openai.api_type = os.getenv("OPENAI_API_TYPE")
-    openai.api_version = os.getenv("OPENAI_API_VERSION")
-
 # tokenizer = GPT2TokenizerFast.from_pretrained("gpt2")
 tokenizer = tiktoken.get_encoding("cl100k_base")
-
-
 def get_embedding(text, engine=os.getenv("EMBEDDING_ENGINE")):
     count = 0
     error = ''

utils/pdf_util.py

@@ -63,7 +63,7 @@ class PDFUtil:
         pdf_doc.close()
         return True, output
 
-    def extract_text(self, output_file: str = None) -> Tuple[bool, str, dict]:
+    def extract_text(self, output_folder: str = None) -> Tuple[bool, str, dict]:
         """
         Extracts text from PDF
         """
@@ -92,9 +92,18 @@ class PDFUtil:
             #     "######################################################################"
             # )
             # Save to file
-            if output_file:
+            if output_folder:
-                with open(output_file, "w", encoding="utf-8") as file:
+                txt_output_folder = os.path.join(output_folder, 'pdf_text/')
+                os.makedirs(txt_output_folder, exist_ok=True)
+                txt_file = os.path.join(txt_output_folder, self.simple_pdf_file.replace(".pdf", ".txt"))
+                with open(txt_file, "w", encoding="utf-8") as file:
                     file.write(text.strip())
+                    
+                json_output_folder = os.path.join(output_folder, 'pdf_json/')
+                os.makedirs(json_output_folder, exist_ok=True)
+                json_file = os.path.join(json_output_folder, self.simple_pdf_file.replace(".pdf", ".json"))
+                with open(json_file, "w", encoding="utf-8") as file:
+                    json.dump(page_text_dict, file, indent=4)
             pdf_doc.close()
             return True, text, page_text_dict
         except Exception as e: