Chaim
6f515dc2cb
Ezer Mishpati - AI legal decision drafting system with: - MCP server (FastMCP) with document processing pipeline - Web upload interface (FastAPI) for file upload and classification - pgvector-based semantic search - Hebrew legal document chunking and embedding
343 lines
11 KiB
Python
343 lines
11 KiB
Python
"""Ezer Mishpati — Web upload interface for legal documents."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import json
|
|
import logging
|
|
import re
|
|
import shutil
|
|
import subprocess
|
|
import sys
|
|
import time
|
|
from contextlib import asynccontextmanager
|
|
from pathlib import Path
|
|
from uuid import UUID, uuid4
|
|
|
|
# Allow importing legal_mcp from the MCP server source
|
|
sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "mcp-server" / "src"))
|
|
|
|
from fastapi import FastAPI, File, HTTPException, UploadFile
|
|
from fastapi.responses import FileResponse, StreamingResponse
|
|
from fastapi.staticfiles import StaticFiles
|
|
from pydantic import BaseModel
|
|
|
|
from legal_mcp import config
|
|
from legal_mcp.services import chunker, db, embeddings, extractor, processor
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
UPLOAD_DIR = config.DATA_DIR / "uploads"
|
|
ALLOWED_EXTENSIONS = {".pdf", ".docx", ".rtf", ".txt"}
|
|
MAX_FILE_SIZE = 50 * 1024 * 1024 # 50MB
|
|
|
|
# In-memory progress tracking
|
|
_progress: dict[str, dict] = {}
|
|
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
UPLOAD_DIR.mkdir(parents=True, exist_ok=True)
|
|
await db.init_schema()
|
|
yield
|
|
await db.close_pool()
|
|
|
|
|
|
app = FastAPI(title="Ezer Mishpati — Upload", lifespan=lifespan)
|
|
|
|
STATIC_DIR = Path(__file__).parent / "static"
|
|
|
|
|
|
# ── API Endpoints ──────────────────────────────────────────────────
|
|
|
|
|
|
@app.get("/")
|
|
async def index():
|
|
return FileResponse(STATIC_DIR / "index.html")
|
|
|
|
|
|
@app.post("/api/upload")
|
|
async def upload_file(file: UploadFile = File(...)):
|
|
"""Upload a file to the temporary uploads directory."""
|
|
if not file.filename:
|
|
raise HTTPException(400, "No filename provided")
|
|
|
|
# Validate extension
|
|
ext = Path(file.filename).suffix.lower()
|
|
if ext not in ALLOWED_EXTENSIONS:
|
|
raise HTTPException(400, f"Unsupported file type: {ext}. Allowed: {', '.join(ALLOWED_EXTENSIONS)}")
|
|
|
|
# Sanitize filename
|
|
safe_name = re.sub(r"[^\w\u0590-\u05FF\s.\-()]", "", Path(file.filename).stem)
|
|
if not safe_name:
|
|
safe_name = "document"
|
|
timestamp = int(time.time())
|
|
filename = f"{timestamp}_{safe_name}{ext}"
|
|
|
|
# Read and validate size
|
|
content = await file.read()
|
|
if len(content) > MAX_FILE_SIZE:
|
|
raise HTTPException(400, f"File too large. Max: {MAX_FILE_SIZE // (1024*1024)}MB")
|
|
|
|
dest = UPLOAD_DIR / filename
|
|
dest.write_bytes(content)
|
|
|
|
return {
|
|
"filename": filename,
|
|
"original_name": file.filename,
|
|
"size": len(content),
|
|
}
|
|
|
|
|
|
@app.get("/api/uploads")
|
|
async def list_uploads():
|
|
"""List files in the uploads (pending) directory."""
|
|
if not UPLOAD_DIR.exists():
|
|
return []
|
|
files = []
|
|
for f in sorted(UPLOAD_DIR.iterdir(), key=lambda p: p.stat().st_mtime, reverse=True):
|
|
if f.is_file() and f.suffix.lower() in ALLOWED_EXTENSIONS:
|
|
stat = f.stat()
|
|
files.append({
|
|
"filename": f.name,
|
|
"size": stat.st_size,
|
|
"uploaded_at": stat.st_mtime,
|
|
})
|
|
return files
|
|
|
|
|
|
@app.delete("/api/uploads/{filename}")
|
|
async def delete_upload(filename: str):
|
|
"""Remove a file from the uploads directory."""
|
|
path = UPLOAD_DIR / filename
|
|
if not path.exists() or not path.parent.samefile(UPLOAD_DIR):
|
|
raise HTTPException(404, "File not found")
|
|
path.unlink()
|
|
return {"deleted": filename}
|
|
|
|
|
|
class ClassifyRequest(BaseModel):
|
|
filename: str
|
|
category: str # "training" or "case"
|
|
# For case documents
|
|
case_number: str = ""
|
|
doc_type: str = "appeal"
|
|
title: str = ""
|
|
# For training documents
|
|
decision_number: str = ""
|
|
decision_date: str = ""
|
|
subject_categories: list[str] = []
|
|
|
|
|
|
@app.post("/api/classify")
|
|
async def classify_file(req: ClassifyRequest):
|
|
"""Classify a pending file and start processing."""
|
|
source = UPLOAD_DIR / req.filename
|
|
if not source.exists() or not source.parent.samefile(UPLOAD_DIR):
|
|
raise HTTPException(404, "File not found in uploads")
|
|
|
|
if req.category not in ("training", "case"):
|
|
raise HTTPException(400, "Category must be 'training' or 'case'")
|
|
|
|
if req.category == "case" and not req.case_number:
|
|
raise HTTPException(400, "case_number required for case documents")
|
|
|
|
task_id = str(uuid4())
|
|
_progress[task_id] = {"status": "queued", "filename": req.filename}
|
|
|
|
asyncio.create_task(_process_file(task_id, source, req))
|
|
|
|
return {"task_id": task_id}
|
|
|
|
|
|
@app.get("/api/progress/{task_id}")
|
|
async def progress_stream(task_id: str):
|
|
"""SSE stream of processing progress."""
|
|
if task_id not in _progress:
|
|
raise HTTPException(404, "Task not found")
|
|
|
|
async def event_stream():
|
|
while True:
|
|
data = _progress.get(task_id, {})
|
|
yield f"data: {json.dumps(data, ensure_ascii=False)}\n\n"
|
|
if data.get("status") in ("completed", "failed"):
|
|
break
|
|
await asyncio.sleep(1)
|
|
# Clean up after a delay
|
|
await asyncio.sleep(30)
|
|
_progress.pop(task_id, None)
|
|
|
|
return StreamingResponse(event_stream(), media_type="text/event-stream")
|
|
|
|
|
|
@app.get("/api/cases")
|
|
async def list_cases():
|
|
"""List existing cases for the dropdown."""
|
|
cases = await db.list_cases()
|
|
return [
|
|
{
|
|
"case_number": c["case_number"],
|
|
"title": c["title"],
|
|
"status": c["status"],
|
|
}
|
|
for c in cases
|
|
]
|
|
|
|
|
|
# ── Background Processing ─────────────────────────────────────────
|
|
|
|
|
|
async def _process_file(task_id: str, source: Path, req: ClassifyRequest):
|
|
"""Process a classified file in the background."""
|
|
try:
|
|
if req.category == "case":
|
|
await _process_case_document(task_id, source, req)
|
|
else:
|
|
await _process_training_document(task_id, source, req)
|
|
except Exception as e:
|
|
logger.exception("Processing failed for %s", req.filename)
|
|
_progress[task_id] = {"status": "failed", "error": str(e), "filename": req.filename}
|
|
|
|
|
|
async def _process_case_document(task_id: str, source: Path, req: ClassifyRequest):
|
|
"""Process a case document (mirrors documents.document_upload logic)."""
|
|
_progress[task_id] = {"status": "validating", "filename": req.filename}
|
|
|
|
case = await db.get_case_by_number(req.case_number)
|
|
if not case:
|
|
_progress[task_id] = {"status": "failed", "error": f"Case {req.case_number} not found"}
|
|
return
|
|
|
|
case_id = UUID(case["id"])
|
|
title = req.title or source.stem.split("_", 1)[-1] # Remove timestamp prefix
|
|
|
|
# Copy to case directory
|
|
_progress[task_id] = {"status": "copying", "filename": req.filename}
|
|
case_dir = config.CASES_DIR / req.case_number / "documents"
|
|
case_dir.mkdir(parents=True, exist_ok=True)
|
|
# Use original name without timestamp prefix
|
|
original_name = re.sub(r"^\d+_", "", source.name)
|
|
dest = case_dir / original_name
|
|
shutil.copy2(str(source), str(dest))
|
|
|
|
# Create document record
|
|
_progress[task_id] = {"status": "registering", "filename": req.filename}
|
|
doc = await db.create_document(
|
|
case_id=case_id,
|
|
doc_type=req.doc_type,
|
|
title=title,
|
|
file_path=str(dest),
|
|
)
|
|
|
|
# Process (extract → chunk → embed → store)
|
|
_progress[task_id] = {"status": "processing", "filename": req.filename, "step": "extracting"}
|
|
result = await processor.process_document(UUID(doc["id"]), case_id)
|
|
|
|
# Git commit
|
|
repo_dir = config.CASES_DIR / req.case_number
|
|
if repo_dir.exists():
|
|
subprocess.run(["git", "add", "."], cwd=repo_dir, capture_output=True)
|
|
doc_type_hebrew = {
|
|
"appeal": "כתב ערר", "response": "תשובה", "decision": "החלטה",
|
|
"reference": "מסמך עזר", "exhibit": "נספח",
|
|
}.get(req.doc_type, req.doc_type)
|
|
subprocess.run(
|
|
["git", "commit", "-m", f"הוספת {doc_type_hebrew}: {title}"],
|
|
cwd=repo_dir, capture_output=True,
|
|
env={"GIT_AUTHOR_NAME": "Ezer Mishpati", "GIT_AUTHOR_EMAIL": "legal@local",
|
|
"GIT_COMMITTER_NAME": "Ezer Mishpati", "GIT_COMMITTER_EMAIL": "legal@local",
|
|
"PATH": "/usr/bin:/bin"},
|
|
)
|
|
|
|
# Remove from uploads
|
|
source.unlink(missing_ok=True)
|
|
|
|
_progress[task_id] = {
|
|
"status": "completed",
|
|
"filename": req.filename,
|
|
"result": result,
|
|
"case_number": req.case_number,
|
|
"doc_type": req.doc_type,
|
|
}
|
|
|
|
|
|
async def _process_training_document(task_id: str, source: Path, req: ClassifyRequest):
|
|
"""Process a training document (mirrors documents.document_upload_training logic)."""
|
|
from datetime import date as date_type
|
|
|
|
title = req.title or source.stem.split("_", 1)[-1]
|
|
|
|
# Copy to training directory
|
|
_progress[task_id] = {"status": "copying", "filename": req.filename}
|
|
config.TRAINING_DIR.mkdir(parents=True, exist_ok=True)
|
|
original_name = re.sub(r"^\d+_", "", source.name)
|
|
dest = config.TRAINING_DIR / original_name
|
|
shutil.copy2(str(source), str(dest))
|
|
|
|
# Extract text
|
|
_progress[task_id] = {"status": "processing", "filename": req.filename, "step": "extracting"}
|
|
text, page_count = await extractor.extract_text(str(dest))
|
|
|
|
# Parse date
|
|
d_date = None
|
|
if req.decision_date:
|
|
d_date = date_type.fromisoformat(req.decision_date)
|
|
|
|
# Add to style corpus
|
|
_progress[task_id] = {"status": "processing", "filename": req.filename, "step": "corpus"}
|
|
corpus_id = await db.add_to_style_corpus(
|
|
document_id=None,
|
|
decision_number=req.decision_number,
|
|
decision_date=d_date,
|
|
subject_categories=req.subject_categories,
|
|
full_text=text,
|
|
)
|
|
|
|
# Chunk and embed
|
|
_progress[task_id] = {"status": "processing", "filename": req.filename, "step": "chunking"}
|
|
chunks = chunker.chunk_document(text)
|
|
|
|
chunk_count = 0
|
|
if chunks:
|
|
doc = await db.create_document(
|
|
case_id=None,
|
|
doc_type="decision",
|
|
title=f"[קורפוס] {title}",
|
|
file_path=str(dest),
|
|
page_count=page_count,
|
|
)
|
|
doc_id = UUID(doc["id"])
|
|
await db.update_document(doc_id, extracted_text=text, extraction_status="completed")
|
|
|
|
_progress[task_id] = {"status": "processing", "filename": req.filename, "step": "embedding"}
|
|
texts = [c.content for c in chunks]
|
|
embs = await embeddings.embed_texts(texts, input_type="document")
|
|
|
|
chunk_dicts = [
|
|
{
|
|
"content": c.content,
|
|
"section_type": c.section_type,
|
|
"embedding": emb,
|
|
"page_number": c.page_number,
|
|
"chunk_index": c.chunk_index,
|
|
}
|
|
for c, emb in zip(chunks, embs)
|
|
]
|
|
await db.store_chunks(doc_id, None, chunk_dicts)
|
|
chunk_count = len(chunks)
|
|
|
|
# Remove from uploads
|
|
source.unlink(missing_ok=True)
|
|
|
|
_progress[task_id] = {
|
|
"status": "completed",
|
|
"filename": req.filename,
|
|
"result": {
|
|
"corpus_id": str(corpus_id),
|
|
"title": title,
|
|
"pages": page_count,
|
|
"text_length": len(text),
|
|
"chunks": chunk_count,
|
|
},
|
|
}
|