stanford-oval/storm · error · ValueError

Please provide the name of the content column.

Error message

Please provide the name of the content column.

What it means

content_column is None; the function needs to know which CSV column holds document text to build the documents and metadata for embedding.

Source

Thrown at knowledge_storm/utils.py:213

            raise ValueError("Please provide a collection name.")

        model_kwargs = {"device": device}
        encode_kwargs = {"normalize_embeddings": True}
        from langchain_huggingface import HuggingFaceEmbeddings

        model = HuggingFaceEmbeddings(
            model_name=embedding_model,
            model_kwargs=model_kwargs,
            encode_kwargs=encode_kwargs,
        )

        if file_path is None:
            raise ValueError("Please provide a file path.")
        # check if the file is a csv file
        if not file_path.endswith(".csv"):
            raise ValueError(f"Not valid file format. Please provide a csv file.")
        if content_column is None:
            raise ValueError("Please provide the name of the content column.")
        if url_column is None:
            raise ValueError("Please provide the name of the url column.")

        # try to initialize the Qdrant client
        qdrant = None
        if vector_db_mode == "online":
            qdrant = QdrantVectorStoreManager._init_online_vector_db(
                url=url,
                api_key=qdrant_api_key,
                collection_name=collection_name,
                model=model,
            )
        elif vector_db_mode == "offline":
            qdrant = QdrantVectorStoreManager._init_offline_vector_db(
                vector_store_path=vector_store_path,
                collection_name=collection_name,
                model=model,
            )

View on GitHub (pinned to fb951af774)

Solutions

1. Pass the exact header name of the text column, e.g. content_column='content'
2. Print df.columns first to confirm the header spelling
3. If the column is missing from the CSV, regenerate the CSV with the expected header

Example fix

# before
create_or_update_vector_store('c', 'offline', 'd.csv', None, 'url')
# after
create_or_update_vector_store('c', 'offline', 'd.csv', 'content', 'url')

import pandas as pd
cols = pd.read_csv(file_path, nrows=0).columns.tolist()
assert content_column in cols, f'{content_column} not in {cols}'

def has_column(csv_path: str, col: str) -> bool:
    import pandas as pd
    return col in pd.read_csv(csv_path, nrows=0).columns

try:
    create_or_update_vector_store('c', mode, f, content_column, url_column, ...)
except ValueError as e:
    if 'Content column' in str(e):
        show_available_columns(f)
        raise
    raise

When it happens

Trigger: Calling create_or_update_vector_store without content_column, or with it set to None via a config dict.

Common situations: CSV header renamed by a data vendor (e.g. 'text' vs 'body'), or the column name is parameterized and the default was removed during refactor.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

• Please provide the name of the url column.
• Please provide a file path.
• Content column {content_column} not found in the csv file.
• Please provide a folder path.
• Please provide a collection name.

AI-assisted analysis of stanford-oval/storm@fb951af774 (2026-08-28). Data as JSON: /api/errors/7af722fec231693c. Report an issue: GitHub.