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.

730 B
Raw Blame

title: "How do I search a folder of PDFs?" target_format: pdf evidence:

  • claim: "pdf.rs extracts text from PDF files during autoindex" source: "engine/crates/xerj-autoindex/src/extract/pdf.rs"
  • claim: "autoindex walks a local filesystem and types each file" source: "engine/crates/xerj-autoindex/src/lib.rs"

How do I search a folder of PDFs?

Point xerj autoindex at the directory. XERJ types each file, extracts the text with its PDF extractor, and writes one searchable document per file on a single-node install.

xerj autoindex ./papers

Query it over the Elasticsearch-shaped API on the same box. There is no crawler and no object-store reader: the files must already be on local disk.