Chaim 9e7492e761 Make classification and reference extraction non-fatal in document pipeline ...

Text extraction, chunking and embedding proceed even if Claude API
classification or reference extraction fails (e.g. API quota exceeded).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-04 13:00:34 +00:00

.claude/commands

Initial commit: MCP server + web upload interface

2026-03-23 12:33:07 +00:00

mcp-server

Make classification and reference extraction non-fatal in document pipeline

2026-04-04 13:00:34 +00:00

scripts

Add full decision writing pipeline: classify, extract, brainstorm, write, QA, export

2026-04-03 10:21:47 +00:00

web

Keep original filename when doc_type is auto instead of 'auto-{case}.ext'

2026-04-04 12:52:18 +00:00

.dockerignore

Initial commit: MCP server + web upload interface

2026-03-23 12:33:07 +00:00

.gitignore

Initial commit: MCP server + web upload interface

2026-03-23 12:33:07 +00:00

.mcp.json

Initial commit: MCP server + web upload interface

2026-03-23 12:33:07 +00:00

CLAUDE.md

Redesign upload UI + update Gitea org references

2026-04-04 08:10:18 +00:00

Dockerfile

Remove din-leumi: fully separate into standalone service

2026-04-04 08:34:35 +00:00

Description

AI Legal Decision Drafting System — MCP server, web upload, RAG search

37 MiB

Languages

Python 65.8%

TypeScript 32.2%

JavaScript 1%

Shell 0.7%

CSS 0.2%