stanford-oval/storm · error · ValueError

Content column {content_column} not found in the csv file.

Error message

Content column {content_column} not found in the csv file.

What it means

After reading the CSV with pandas, the requested content_column is not among df.columns. The header-based lookups are case- and whitespace-sensitive, so even similar names fail.

Source

Thrown at knowledge_storm/utils.py:245

            qdrant = QdrantVectorStoreManager._init_offline_vector_db(
                vector_store_path=vector_store_path,
                collection_name=collection_name,
                model=model,
            )
        else:
            raise ValueError(
                "Invalid vector_db_mode. Please provide either 'online' or 'offline'."
            )
        if qdrant is None:
            raise ValueError("Qdrant client is not initialized.")

        # read the csv file
        import pandas as pd

        df = pd.read_csv(file_path)
        # check that content column exists and url column exists
        if content_column not in df.columns:
            raise ValueError(
                f"Content column {content_column} not found in the csv file."
            )
        if url_column not in df.columns:
            raise ValueError(f"URL column {url_column} not found in the csv file.")

        documents = [
            Document(
                page_content=row[content_column],
                metadata={
                    "title": row.get(title_column, ""),
                    "url": row[url_column],
                    "description": row.get(desc_column, ""),
                },
            )
            for row in df.to_dict(orient="records")
        ]

        # split the documents

View on GitHub (pinned to fb951af774)

Solutions

1. Inspect df.columns (e.g. print(list(df.columns))) and match the exact string
2. Load with encoding='utf-8-sig' to strip BOM, or normalize headers: df.columns = df.columns.str.strip()
3. Regenerate the CSV with the expected header if the column is truly absent

Example fix

# before
df = pd.read_csv('d.csv')
create_or_update_vector_store('c', 'offline', 'd.csv', 'Content', 'url')
# after
df = pd.read_csv('d.csv', encoding='utf-8-sig')
df.columns = df.columns.str.strip()
df.to_csv('d.csv', index=False)
create_or_update_vector_store('c', 'offline', 'd.csv', 'content', 'url')

import pandas as pd
df = pd.read_csv(file_path, nrows=0)
df.columns = df.columns.str.strip()
assert content_column in df.columns, f'{content_column!r} not in {list(df.columns)}'

def content_column_exists(csv_path: str, col: str) -> bool:
    import pandas as pd
    headers = pd.read_csv(csv_path, nrows=0, encoding='utf-8-sig').columns.str.strip()
    return col in headers

try:
    create_or_update_vector_store('c', mode, f, content_column, url_column, ...)
except ValueError as e:
    if 'not found in the csv file' in str(e):
        import pandas as pd
        raise SystemExit(f'Bad column; available: {pd.read_csv(f, nrows=0).columns.tolist()}') from e
    raise

When it happens

Trigger: Passing content_column='Content' when the header is 'content', a name with trailing whitespace/BOM (common with Excel-exported CSVs), or a column that simply does not exist.

Common situations: Vendor CSVs with BOM-prefixed first header (pd.read_csv yields '\ufeffcontent'), renamed headers, or dialect differences between the exporting and ingesting teams.

Related errors

• Please provide the name of the content column.
• Please provide the name of the url column.
• Please provide a file path.
• Not valid file format. Please provide a csv file.
• URL column {url_column} not found in the csv file.

AI-assisted analysis of stanford-oval/storm@fb951af774 (2026-08-28). Data as JSON: /api/errors/5c6b518159184ccc. Report an issue: GitHub.