Chaim bc72a83a71 Switch embedding model from voyage-3-large to voyage-law-2 ...

Benchmark on case 1130-25 (4 Hebrew legal docs, 8 queries) showed:
- voyage-law-2: avg top-1 score 0.5839 (+27% over voyage-3-large)
- voyage-4-large: avg top-1 score 0.4119 (worse than current)
- voyage-3-large: avg top-1 score 0.4589 (baseline)

voyage-law-2 costs ~4.6x more per run but delivers significantly
better retrieval quality for Hebrew legal text. Model is now
configurable via VOYAGE_MODEL env var.

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

2026-04-08 19:05:58 +00:00

.claude

Add email notifications: agents send mail when human action needed

2026-04-07 17:07:43 +00:00

.taskmaster

Reorganize: skills/ directory + move memory to docs/

2026-04-04 14:27:07 +00:00

docs

Reorganize: skills/ directory + move memory to docs/

2026-04-04 14:27:07 +00:00

mcp-server

Switch embedding model from voyage-3-large to voyage-law-2

2026-04-08 19:05:58 +00:00

scripts

Add email notifications: agents send mail when human action needed

2026-04-07 17:07:43 +00:00

skills

Reorganize: skills/ directory + move memory to docs/

2026-04-04 14:27:07 +00:00

web

Add sync-to-DB and delete-from-DB actions for skills

2026-04-08 17:52:00 +00:00

.dockerignore

Initial commit: MCP server + web upload interface

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

.gitignore

Reorganize: skills/ directory + move memory to docs/

2026-04-04 14:27:07 +00:00

CLAUDE.md

Reorganize: skills/ directory + move memory to docs/

2026-04-04 14:27:07 +00:00

Dockerfile

Set git default branch to main in Docker image

2026-04-04 13:36:10 +00:00

Description

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

32 MiB

Languages

Python 59.1%

TypeScript 37.4%

JavaScript 1.7%

Shell 1.2%

CSS 0.5%

Other 0.1%