ezer-mishpati/legal-ai
1
0
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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>
This commit is contained in:
Chaim
2026-04-08 19:05:58 +00:00
parent d8e888ad6a
commit bc72a83a71
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
mcp-server/src/legal_mcp/config.py
View File

@@ -44,7 +44,7 @@ REDIS_URL = os.environ.get("REDIS_URL", "redis://127.0.0.1:6380/0")
# Voyage AI
VOYAGE_API_KEY = os.environ.get("VOYAGE_API_KEY", "")
VOYAGE_MODEL = "voyage-3-large"
VOYAGE_MODEL = os.environ.get("VOYAGE_MODEL", "voyage-law-2")
VOYAGE_DIMENSIONS = 1024
# Anthropic (for Claude Vision OCR)