scripts/process.py

import streamlit as st
import os
from haystack.utils import fetch_archive_from_http, clean_wiki_text, convert_files_to_docs
from haystack.schema import Answer
from haystack.document_stores import InMemoryDocumentStore
from haystack.pipelines import ExtractiveQAPipeline
from haystack.nodes import FARMReader, TfidfRetriever
import logging
from markdown import markdown
from annotated_text import annotation
from PIL import Image

os.environ['TOKENIZERS_PARALLELISM'] ="false"



#def load_and_write_data(document_store):
#    doc_dir = './article_txt_got'
#    docs = convert_files_to_docs(dir_path=doc_dir, clean_func=clean_wiki_text, split_paragraphs=True)
#    document_store.write_documents(docs)

#pipeline = start_haystack()
def load_document(
    file_path: str,
    file_name,
    id_hash_keys: Optional[List[str]] = None,
) -> List[Document]:
    
    """
    takes docx, txt and pdf files as input and \
    extracts text as well as the filename as metadata. \
    Since haystack does not take care of all pdf files, \
    pdfplumber is attached to the pipeline in case the pdf \ 
    extraction fails via Haystack.
    Returns a list of type haystack.schema.Document
    """

    if file_name.endswith('.pdf'):
        converter = PDFToTextConverter(remove_numeric_tables=True)
    if file_name.endswith('.txt'):
        converter = TextConverter()
    if file_name.endswith('.docx'):
        converter = DocxToTextConverter()


    documents = []
    logger.info("Converting {}".format(file_name))
    # PDFToTextConverter, TextConverter, and DocxToTextConverter 
    # return a list containing a single Document
    document = converter.convert(
                file_path=file_path, meta=None, 
                 id_hash_keys=id_hash_keys
                )[0]
    text = document.content
    documents.append(Document(content=text, 
                              meta={"name": file_name}, 
                              id_hash_keys=id_hash_keys))
    
    return documents
 
def preprocessing(document):
    """
    takes in haystack document object and splits it into paragraphs and applies simple cleaning.
    Returns cleaned list of haystack document objects. One paragraph per object. Also returns pandas df and 
    list that contains all text joined together.
    """    

    preprocessor = PreProcessor(
        clean_empty_lines=True,
        clean_whitespace=True,
        clean_header_footer=True,
        split_by="sentence",
        split_length=3,
        split_respect_sentence_boundary=False,
        split_overlap=1
    )
    for i in document:
        docs_processed = preprocessor.process([i])
        for item in docs_processed:
            item.content = basic(item.content)

    st.write("your document has been splitted to", len(docs_processed), "paragraphs")
    
    # create dataframe of text and list of all text
    #df = pd.DataFrame(docs_processed)
    #all_text = " ".join(df.content.to_list())
    #par_list = df.content.to_list()

    return docs_processed #, df, all_text, par_list