invoice-receipt-parser

Automated invoice and receipt data extraction system using FastAPI, PostgreSQL, and AI-based parsing with confidence-based fallback logic

A new way for AI to search for data

View on GitHub

2GitHub stars

56commits on main

0forks

Python 65.7%, JavaScript 19.6%, CSS 6.9%, HTML 6.8% · created 2026-08-31 · last push 2026-10-31

What XERJ indexed

Snapshot

34 files · 156.0 KB

The whole repository at commit b83e593a6b (2026-10-21). main is 17 commits ahead.

Selected work

Chaitany Mishra
@ChaitanyMishra

“Keep single-stage for Render; add multi-stage reference and interview…”. 3 files, 499 lines in the project root, app.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-29. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

alembicalembic-migrationbackendcelerydockerdocker-composefastapigemini-api

Example questions

How does invoice-receipt-parser implement alembic?
Show the alembic-migration code in invoice-receipt-parser.

Inside the indexed corpus

34 files, 156.0 KB in total, about 4.6 KB per file.
The selected commit changed 3 of those files (8.8%).
Languages by size: Python 65.7%, JavaScript 19.6%, CSS 6.9%, HTML 6.8%, Mako 0.7%.
On GitHub since 2026-08-31, last push 2026-10-31, 56 commits on main.
The pin is 17 commits behind main; the corpus answers from the pinned code, not the newest.

Licence on GitHub and in the corpus

GitHub reported MIT for ChaitanyMishra/invoice-receipt-parser on 2026-10-31, and the LICENSE file at commit b83e593a6b was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

Chaitany Mishra (@ChaitanyMishra) has 1 selected repository on the hub.

Using XERJ with invoice-receipt-parser

Find every place a config key is set in a repo invoice-receipt-parser is tagged docker-compose on GitHub.
Search a SQL dump without restoring it The hub files it under Databases and storage engines.
Best MCP servers for local code search in 2026, compared
Best grep alternative for AI coding agents (2026)

The prompt

Paste it into your AI agent. It clones ChaitanyMishra/invoice-receipt-parser at the pinned commit and indexes it on your machine.

Search the GitHub repository ChaitanyMishra/invoice-receipt-parser with XERJ (https://hub.xerj.org/corpus/chaitanymishra--invoice-receipt-parser).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/ChaitanyMishra/invoice-receipt-parser invoice-receipt-parser && git -C invoice-receipt-parser checkout b83e593a6bfc4a632e726ef4f09f7f2bbf7f6620
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./invoice-receipt-parser --url http://127.0.0.1:9200 --prefix invoice-receipt-parser --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Chaitany Mishra Databases and storage engines corpora agentops ann-benchmarks gemini-cookbook MrKyaw/Onnx_Rust_Web_Assembly_Triton_Promethus_Grafana Arshia-Moghbel/Telegram-VPN-Seller-Bot Midhun-M-git/bulk-certificate-generator

Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.