Skip to content

armgit / xerj

Public Imported from GitHub
0

AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

842 B
Raw Blame

title: "How do I read email and PDFs after indexing a folder of .eml files?" target_format: eml evidence:

  • claim: "eml.rs extracts headers, the text body and attachments from one RFC 822 / MIME message file" source: "engine/crates/xerj-autoindex/src/extract/eml.rs"
  • claim: "autoindex walks a local filesystem and types each file" source: "engine/crates/xerj-autoindex/src/lib.rs"

How do I read email and PDFs after indexing a folder of .eml files?

Point xerj autoindex at the directory. XERJ types each .eml file, extracts the headers, the text body and the attachments, and writes them as searchable documents on a single-node install.

xerj autoindex ./inbox

The files must already be on local disk, one message per file. There is no reader for a mail archive and no connection to a mail server.