FoundationAgents/MetaGPT · error · NotImplementedError

File format not supported.

Error message

File format not supported.

What it means

read_data in metagpt/document.py dispatches on file suffix and only accepts .xlsx, .csv, .json, .docx/.doc, .txt, and .pdf. Any other suffix falls through to raise NotImplementedError('File format not supported.'), so IndexableDocument.from_path cannot ingest that file type.

Source

Thrown at metagpt/document.py:46

def read_data(data_path: Path) -> Union[pd.DataFrame, list[Document]]:
    suffix = data_path.suffix
    if ".xlsx" == suffix:
        data = pd.read_excel(data_path)
    elif ".csv" == suffix:
        data = pd.read_csv(data_path)
    elif ".json" == suffix:
        data = pd.read_json(data_path)
    elif suffix in (".docx", ".doc"):
        data = SimpleDirectoryReader(input_files=[str(data_path)]).load_data()
    elif ".txt" == suffix:
        data = SimpleDirectoryReader(input_files=[str(data_path)]).load_data()
        node_parser = SimpleNodeParser.from_defaults(separator="\n", chunk_size=256, chunk_overlap=0)
        data = node_parser.get_nodes_from_documents(data)
    elif ".pdf" == suffix:
        data = PDFReader.load_data(str(data_path))
    else:
        raise NotImplementedError("File format not supported.")
    return data


class DocumentStatus(Enum):
    """Indicates document status, a mechanism similar to RFC/PEP"""

    DRAFT = "draft"
    UNDERREVIEW = "underreview"
    APPROVED = "approved"
    DONE = "done"


class Document(BaseModel):
    """
    Document: Handles operations related to document files.
    """

    path: Path = Field(default=None)

View on GitHub (pinned to 11cdf466d0)

Solutions

1. Convert the file to a supported format (pdf/txt/docx) before indexing.
2. Normalize the suffix: p = p.with_suffix(p.suffix.lower()).
3. For formats llama_index supports (e.g. markdown), load documents yourself with SimpleDirectoryReader and construct the IndexableDocument from data instead of from_path.

Example fix

# before
doc = IndexableDocument.from_path(Path('kb.MD'))  # NotImplementedError

# after
p = Path('kb.MD')
doc = IndexableDocument.from_path(p.with_suffix(p.suffix.lower())) if p.suffix.lower() in {'.xlsx','.csv','.json','.docx','.doc','.txt','.pdf'} else convert_first(p)

SUPPORTED = {'.xlsx', '.csv', '.json', '.docx', '.doc', '.txt', '.pdf'}
p = p.with_suffix(p.suffix.lower())
if p.suffix not in SUPPORTED:
    p = convert_document(p, target='.pdf')
doc = IndexableDocument.from_path(p)

def is_supported_data_file(p: Path) -> bool:
    return p.suffix.lower() in {'.xlsx', '.csv', '.json', '.docx', '.doc', '.txt', '.pdf'}

try:
    doc = IndexableDocument.from_path(p)
except NotImplementedError:
    from llama_index.core import SimpleDirectoryReader
    data = SimpleDirectoryReader(input_files=[str(p)]).load_data()

When it happens

Trigger: IndexableDocument.from_path(Path('notes.md')), .html, .pptx, .eml, or extension-less files. Note the check is exact-suffix: '.MD' or '.PDF' in uppercase also fail the comparison.

Common situations: Trying to index markdown or HTML knowledge bases; uppercase extensions from Windows; assuming llama_index readers cover arbitrary formats because .docx/.txt use SimpleDirectoryReader.

Related errors

• File {data_path} not found.
• The invoice format is not zip, pdf, png, or jpg
• Content column not found in DataFrame.
• File {path} not found.
• File path is not set.

AI-assisted analysis of FoundationAgents/MetaGPT@11cdf466d0 (2026-08-14). Data as JSON: /api/errors/103da3c62cc92bdf. Report an issue: GitHub.