llama-index-readers-cvfile

LlamaIndex reader for the .cv open file format.

A .cv file is a PDF/A-3u file carrying a Markdown copy of the same content (plus optional HTML and JSON Resume) as PDF Associated Files. Instead of OCR ing the PDF, this reader pulls the embedded text payloads directly.

Install

pip install llama-index-readers-cvfile

Use

from pathlib import Path
from llama_index.readers.cvfile import CVFileReader

reader = CVFileReader()
docs = reader.load_data(file=Path("resume.cv"))

for doc in docs:
    print(doc.metadata["payload"], doc.metadata["mime_type"], len(doc.text))

You get one Document per textual payload found in the file. The Markdown copy (typically resume.md) is the one flagged with metadata["primary"] = True.

Untrusted files

By default the reader runs cvfile.validate() before extracting anything. Files carrying forbidden active content (JavaScript, launch or submit actions, external references), encryption, integrity digest mismatches, or payloads over the spec size cap raise ValueError listing the issue codes. Resumes are classic untrusted input, so keep the default when loading files you did not produce yourself.

reader = CVFileReader()              # verify=True (default)
reader = CVFileReader(verify=False)  # trusted files only

Metadata fields

License

Apache-2.0.