Haystack code - Add a table to document store

PHOTO EMBED

Tue Sep 13 2022 08:15:03 GMT+0000 (UTC)

Saved by @edubrigham #ffmpeg #audio #wav #convert

# Add the tables to the DocumentStore

import json
from haystack import Document
import pandas as pd


def read_tables(filename):
    processed_tables = []
    with open(filename) as tables:
        tables = json.load(tables)
        for key, table in tables.items():
            current_columns = table["header"]
            current_rows = table["data"]
            current_df = pd.DataFrame(columns=current_columns, data=current_rows)
            document = Document(content=current_df, content_type="table", id=key)
            processed_tables.append(document)

    return processed_tables


tables = read_tables(f"{doc_dir}/tables.json")
document_store.write_documents(tables, index=document_index)

# Showing content field and meta field of one of the Documents of content_type 'table'
print(tables[0].content)
print(tables[0].meta)
content_copyCOPY