janhq/jan · error · RagError

ParseError

ParseError

Error message

Failed to parse document: {0}

What it means

RagError::ParseError is raised when the RAG plugin fails to parse a document's contents (displayed as "Failed to parse document: {0}" with the underlying reason). Document ingestion (PDF, text, etc.) must yield readable text before chunking/embedding; unparsable or damaged files abort the pipeline with this error.

Solutions

1. Read the wrapped message to see which parser stage failed.
2. Verify the file opens correctly in its native application; re-export or repair if not.
3. Convert problematic documents (e.g. re-save the PDF, normalize to UTF-8 text) before ingestion.
4. For image-only PDFs, run OCR first or reject the file with a friendly user message.

Example fix

// before
rag.ingest(path).unwrap();

// after
match rag.ingest(path) {
    Err(RagError::ParseError(msg)) => {
        eprintln!("Skipping {path:?}: not a readable document ({msg})");
    }
    other => other.expect("ingest failed"),
}

// Rust: pre-check file readability before RAG ingestion
fn looks_parseable(path: &Path) -> bool {
    std::fs::read(path).map(|bytes| !bytes.is_empty() && !bytes.starts_with(&[0u8; 4][..])).unwrap_or(false)
}

fn as_parse_error(err: &RagError) -> Option<&str> {
    match err { RagError::ParseError(m) => Some(m), _ => None }
}

match rag.ingest(doc) {
    Err(RagError::ParseError(msg)) => {
        notify_user(format!("Could not read document: {msg}"));
    }
    other => other?,
}

When it happens

Trigger: Ingesting a file into the RAG index whose contents can't be decoded — corrupted PDFs, password-protected documents, binary files mislabeled as text, or encoding failures.

Common situations: Uploading scanned/image-only PDFs without an OCR layer; files with wrong extensions; documents saved with unexpected encodings; truncated uploads.

Understand the failure class

Background: JSON parse error: "Unexpected token" / "not valid JSON" / "failed to parse" — what JSON parsers are really complaining about — this error's family across 45 libraries.

• Parsing and encoding errors: unexpected token, malformed input — why parsers reject input and how to find the real culprit.

Related errors

• Failed to parse document
• IO error
• IoError
• Unsupported file type
• UnsupportedFileType

AI-assisted analysis of janhq/jan@7205d770c1 (2026-09-17). Data as JSON: /api/errors/38b51a23578533dd. Report an issue: GitHub.

Appendix: source

Thrown at src-tauri/plugins/tauri-plugin-rag/src/error.rs:5

use serde::{Deserialize, Serialize};

#[derive(Debug, thiserror::Error, Serialize, Deserialize)]
pub enum RagError {
    #[error("Failed to parse document: {0}")]
    ParseError(String),

    #[error("Unsupported file type: {0}")]
    UnsupportedFileType(String),

    #[error("IO error: {0}")]
    IoError(String),
}

impl From<std::io::Error> for RagError {
    fn from(err: std::io::Error) -> Self {
        RagError::IoError(err.to_string())
    }
}

View on GitHub (pinned to 7205d770c1)