ezer-mishpati/legal-ai
1
0
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity
336 Commits 8 Branches 1 Tag
main
Commit Graph

3 Commits

Author SHA1 Message Date
Chaim
26c3fddf41 feat(retrieval): add voyage rerank-2 cross-encoder stage (feature flag)
All checks were successful
Build & Deploy / build-and-deploy (push) Successful in 1m29s
Details 
Stage B of voyage-upgrades-plan rewritten: instead of context-3 (which
4 POCs showed inconsistent improvement), add a cross-encoder rerank
layer on top of voyage-3. Default off (VOYAGE_RERANK_ENABLED=false).

POC validation (785-doc corpus, 12 queries, claude-haiku-4-5 judge):
- mean@3 +4.5% (4.306 → 4.500)
- practical-category queries +11.6% (3.78 → 4.22)
- latency +702ms per query
- no schema change, no re-embed, no double storage

Plumbing:
- config: VOYAGE_RERANK_ENABLED / _MODEL / _FETCH_K env vars
- embeddings.voyage_rerank() wraps voyageai client.rerank
- services/rerank.py: maybe_rerank() helper — fetches FETCH_K candidates
  via the bi-encoder then reranks to top-K. Fail-open if Voyage rerank is
  unavailable.
- tools/search.py: search_decisions, search_case_documents,
  find_similar_cases all wrapped
- services/precedent_library.search_library wrapped

Smoke-tested locally with flag on/off — produces expected behaviour and
latency profile. Ready for production rollout via Coolify env flip after
deploy.

POCs (kept under scripts/ for reference):
- voyage_context3_poc{_long}.py — context-3 evaluation (rejected)
- voyage_multimodal_poc.py — multimodal-3 (stage C, deferred)
- voyage_rerank_judge_poc.py — single-case rerank benchmark
- voyage_rerank_corpus_poc.py — full-corpus rerank validation

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-03 18:43:41 +00:00
Chaim
e068a611e7 Rewrite architecture.md — add Track Changes edit flow + 8 stages
All checks were successful
Build & Deploy / build-and-deploy (push) Successful in 6s
Details 
The old architecture.md was out of date (mentioned n8n which isn't used,
wrong embedding dimensions, missing multi-tenancy, no edit loop).

The rewrite documents the full process end-to-end:
  1. Document upload + OCR + embedding
  2. Analysis (proofreader, researcher)
  3. Outcome + direction decision (CEO + human)
  4. Deep analysis (pass 2)
  5. Drafting (writer writes 12 blocks)
  6. QA
  7. Initial DOCX export (with bookmarks for future revisions)
  8. Edit loop with Track Changes — the new architecture:
     a. User downloads + edits in Word + uploads עריכה-v{N}.docx
     b. Backend auto-retrofits bookmarks + registers as active_draft
     c. User asks CEO for specific change in Paperclip comment
     d. CEO stage G: calls writer in revision mode → builds revisions JSON
     e. docx_reviser applies <w:ins>/<w:del> preserving user's template
     f. User Accept/Reject from Word Review tab
     g. Repeat until marked final

Plus MCP tool reference, API endpoints, DB schema, multi-tenancy,
technology stack.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-16 19:10:11 +00:00
Chaim
d5ccf03e4c Add docs, scripts, skills, commands, and taskmaster config to repo 
Includes:
- docs/: architecture, block-schema, migration-plan, product-specification
- scripts/: bidi_table, decompose-decisions, extract-claims, seed-knowledge, etc.
- skill-legal-decision/: SKILL.md + references + block-schema
- skill-legal-assistant/: SKILL.md
- skill-legal-docx/: SKILL.md + references
- .claude/commands/: bidi-table skill
- .taskmaster/: task config + PRDs
- .gitignore: exclude legacy/, kiryat-yearim/, node_modules/, memory/

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-04 14:19:17 +00:00