Spaces:
Sleeping
Sleeping
File size: 15,902 Bytes
4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 6e7c8ba 4939516 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 | """
ClauseGuard β FastAPI Backend v4.0
ββββββββββββββββββββββββββββββββββ
New in v4.0:
β’ /api/redline β clause redlining suggestions
β’ /api/chat β RAG chatbot (streaming)
β’ /api/ocr β OCR scanned PDF extraction
β’ Updated analysis to include redlining data
"""
import os
import re
import json
import time
import uuid
import tempfile
from contextlib import asynccontextmanager
from typing import Optional
from collections import defaultdict
from datetime import datetime
import httpx
import numpy as np
from fastapi import FastAPI, HTTPException, Depends, Body, Request, UploadFile, File as FastAPIFile
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import StreamingResponse
from pydantic import BaseModel, Field
from auth import get_current_user, require_auth
# ββ Import shared modules ββ
import sys
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
try:
from app import (
split_clauses, classify_cuad, extract_entities,
detect_contradictions, compute_risk_score, analyze_contract,
CUAD_LABELS, RISK_MAP, DESC_MAP, _model_status,
cuad_model, cuad_tokenizer
)
from obligations import extract_obligations
from compliance import check_compliance
from compare import compare_contracts
from redlining import generate_redlines
from chatbot import index_contract, chat_respond
from ocr_engine import parse_pdf_smart, get_ocr_status
_SHARED_MODULES = True
except ImportError as e:
_SHARED_MODULES = False
print(f"[API] WARNING: Could not import shared modules: {e}")
# βββ Config βββ
SUPABASE_URL = os.environ.get("SUPABASE_URL", "")
SUPABASE_SERVICE_KEY = os.environ.get("SUPABASE_SERVICE_ROLE_KEY", "")
HF_API_TOKEN = os.environ.get("HF_API_TOKEN", "")
SAULLM_ENDPOINT = os.environ.get("SAULLM_ENDPOINT", "")
MAX_TEXT_LENGTH = int(os.environ.get("MAX_TEXT_LENGTH", "100000"))
# βββ Rate Limiting βββ
_rate_limits = {}
RATE_LIMIT_REQUESTS = 30
RATE_LIMIT_WINDOW = 60
def _check_rate_limit(client_ip: str) -> bool:
now = time.time()
if client_ip in _rate_limits:
count, window_start = _rate_limits[client_ip]
if now - window_start > RATE_LIMIT_WINDOW:
_rate_limits[client_ip] = (1, now)
return True
if count >= RATE_LIMIT_REQUESTS:
return False
_rate_limits[client_ip] = (count + 1, window_start)
return True
_rate_limits[client_ip] = (1, now)
return True
# βββ Supabase helper βββ
async def supabase_insert(table: str, data: dict):
if not SUPABASE_URL or not SUPABASE_SERVICE_KEY:
return
try:
async with httpx.AsyncClient() as client:
await client.post(
f"{SUPABASE_URL}/rest/v1/{table}",
json=data,
headers={
"apikey": SUPABASE_SERVICE_KEY,
"Authorization": f"Bearer {SUPABASE_SERVICE_KEY}",
"Content-Type": "application/json",
"Prefer": "return=minimal",
},
timeout=10.0,
)
except Exception:
pass
async def supabase_query(table: str, params: dict, headers_extra: dict = {}):
if not SUPABASE_URL or not SUPABASE_SERVICE_KEY:
return []
try:
async with httpx.AsyncClient() as client:
resp = await client.get(
f"{SUPABASE_URL}/rest/v1/{table}",
params=params,
headers={
"apikey": SUPABASE_SERVICE_KEY,
"Authorization": f"Bearer {SUPABASE_SERVICE_KEY}",
**headers_extra,
},
timeout=10.0,
)
return resp.json() if resp.status_code == 200 else []
except Exception:
return []
# βββ In-memory RAG session store βββ
_rag_sessions: dict = {}
_RAG_SESSION_MAX = 100
# βββ Request/Response Models βββ
class AnalyzeRequest(BaseModel):
text: Optional[str] = Field(None, min_length=50)
clauses: Optional[list] = None
source_url: Optional[str] = None
class CompareRequest(BaseModel):
text_a: str = Field(..., min_length=50)
text_b: str = Field(..., min_length=50)
class ExplainRequest(BaseModel):
clause: str = Field(..., min_length=10, max_length=2000)
category: str
class ExplainResponse(BaseModel):
clause: str
category: str
explanation: str
legal_basis: str
recommendation: str
class ChatRequest(BaseModel):
message: str = Field(..., min_length=1, max_length=2000)
session_id: str
history: Optional[list[dict]] = None
class RedlineRequest(BaseModel):
session_id: Optional[str] = None
text: Optional[str] = None
use_llm: bool = True
# βββ App βββ
@asynccontextmanager
async def lifespan(app: FastAPI):
yield
app = FastAPI(title="ClauseGuard API", version="4.0.0", lifespan=lifespan)
ALLOWED_ORIGINS = [
"https://clauseguardweb.netlify.app",
"http://localhost:3000",
"http://localhost:3001",
]
app.add_middleware(
CORSMiddleware,
allow_origins=ALLOWED_ORIGINS,
allow_origin_regex=r"^chrome-extension://.*$",
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
@app.get("/health")
async def health():
model_status = "ml" if _SHARED_MODULES and cuad_model else "regex"
ocr_status = get_ocr_status() if _SHARED_MODULES else "unavailable"
return {
"status": "ok",
"model": model_status,
"version": "4.0.0",
"shared_modules": _SHARED_MODULES,
"ocr": ocr_status,
"features": ["analyze", "compare", "redline", "chat", "ocr"],
}
@app.post("/api/analyze")
async def analyze(req: AnalyzeRequest, request: Request, user: Optional[dict] = Depends(get_current_user)):
client_ip = request.client.host if request.client else "unknown"
if not _check_rate_limit(client_ip):
raise HTTPException(status_code=429, detail="Rate limit exceeded.")
text = req.text
if not text and req.clauses:
text = "\n\n".join(req.clauses) if isinstance(req.clauses, list) else str(req.clauses)
if not text or len(text.strip()) < 50:
raise HTTPException(status_code=400, detail="Text too short (minimum 50 characters)")
if len(text) > MAX_TEXT_LENGTH:
raise HTTPException(status_code=400, detail=f"Text too long (max {MAX_TEXT_LENGTH} chars)")
start = time.time()
clauses = split_clauses(text)
if not clauses:
raise HTTPException(status_code=400, detail="No clauses detected")
clause_results = []
for clause in clauses:
predictions = classify_cuad(clause)
if predictions:
for pred in predictions:
clause_results.append({
"text": clause,
"label": pred["label"],
"confidence": pred["confidence"],
"risk": pred["risk"],
"description": pred["description"],
"source": pred.get("source", "unknown"),
})
entities = extract_entities(text)
contradictions = detect_contradictions(clause_results, text)
risk, grade, sev_counts = compute_risk_score(clause_results, len(clauses))
obligations = extract_obligations(text)
compliance = check_compliance(text)
# v4.0: Redlining
analysis_for_redline = {"clauses": clause_results}
redlines = []
try:
redlines = generate_redlines(analysis_for_redline, use_llm=True)
except Exception as e:
print(f"[API] Redlining error: {e}")
latency = int((time.time() - start) * 1000)
results_for_db = []
for cr in clause_results:
results_for_db.append({
"text": cr["text"],
"categories": [{
"name": cr["label"],
"severity": cr["risk"],
"confidence": cr["confidence"],
"description": cr["description"],
}],
})
# v4.0: RAG indexing
session_id = None
try:
chunks, embeddings, _status = index_contract(text)
if chunks and embeddings is not None:
session_id = uuid.uuid4().hex[:12]
if len(_rag_sessions) >= _RAG_SESSION_MAX:
oldest = next(iter(_rag_sessions))
del _rag_sessions[oldest]
_rag_sessions[session_id] = {
"chunks": chunks,
"embeddings": embeddings,
"analysis": {
"risk": {"score": risk, "grade": grade, "breakdown": sev_counts},
"metadata": {"total_clauses": len(clauses), "flagged_clauses": len(clause_results)},
"clauses": clause_results[:30],
"entities": entities[:30],
"contradictions": contradictions,
},
}
except Exception as e:
print(f"[API] RAG indexing error: {e}")
if user:
await supabase_insert("analyses", {
"user_id": user["id"],
"source_url": req.source_url,
"total_clauses": len(clauses),
"flagged_count": len(set(cr["text"] for cr in clause_results)),
"risk_score": risk,
"grade": grade,
"clauses": results_for_db,
"entities": entities,
"contradictions": contradictions,
"obligations": obligations,
"compliance": compliance,
})
return {
"risk_score": risk,
"grade": grade,
"total_clauses": len(clauses),
"flagged_count": len(set(cr["text"] for cr in clause_results)),
"results": results_for_db,
"entities": entities,
"contradictions": contradictions,
"obligations": obligations,
"compliance": compliance,
"redlines": redlines,
"model": "ml" if cuad_model else "regex",
"latency_ms": latency,
"session_id": session_id,
}
@app.post("/api/compare")
async def compare(req: CompareRequest, request: Request):
client_ip = request.client.host if request.client else "unknown"
if not _check_rate_limit(client_ip):
raise HTTPException(status_code=429, detail="Rate limit exceeded.")
return compare_contracts(req.text_a, req.text_b)
@app.post("/api/redline")
async def redline(req: RedlineRequest, request: Request):
client_ip = request.client.host if request.client else "unknown"
if not _check_rate_limit(client_ip):
raise HTTPException(status_code=429, detail="Rate limit exceeded.")
if req.session_id and req.session_id in _rag_sessions:
analysis = _rag_sessions[req.session_id]["analysis"]
elif req.text:
result, error = analyze_contract(req.text)
if error:
raise HTTPException(status_code=400, detail=error)
analysis = result
else:
raise HTTPException(status_code=400, detail="Provide session_id or text")
redlines = generate_redlines(analysis, use_llm=req.use_llm)
return {"redlines": redlines, "count": len(redlines)}
@app.post("/api/chat")
async def chat(req: ChatRequest, request: Request):
client_ip = request.client.host if request.client else "unknown"
if not _check_rate_limit(client_ip):
raise HTTPException(status_code=429, detail="Rate limit exceeded.")
if req.session_id not in _rag_sessions:
raise HTTPException(status_code=404, detail="Session not found. Analyze a contract first.")
session = _rag_sessions[req.session_id]
response_text = ""
for partial in chat_respond(req.message, req.history or [],
session["chunks"], session["embeddings"], session["analysis"]):
response_text = partial
return {"response": response_text, "session_id": req.session_id}
@app.post("/api/chat/stream")
async def chat_stream(req: ChatRequest, request: Request):
client_ip = request.client.host if request.client else "unknown"
if not _check_rate_limit(client_ip):
raise HTTPException(status_code=429, detail="Rate limit exceeded.")
if req.session_id not in _rag_sessions:
raise HTTPException(status_code=404, detail="Session not found.")
session = _rag_sessions[req.session_id]
async def generate():
last = ""
for partial in chat_respond(
req.message, req.history or [],
session["chunks"], session["embeddings"], session["analysis"]
):
delta = partial[len(last):]
last = partial
if delta:
yield f"data: {json.dumps({'delta': delta})}\n\n"
yield "data: [DONE]\n\n"
return StreamingResponse(generate(), media_type="text/event-stream")
@app.post("/api/ocr")
async def ocr_endpoint(file: UploadFile = FastAPIFile(...)):
if not file.filename or not file.filename.lower().endswith(".pdf"):
raise HTTPException(status_code=400, detail="Only PDF files supported")
with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as tmp:
content = await file.read()
tmp.write(content)
tmp_path = tmp.name
try:
text, error, method = parse_pdf_smart(tmp_path)
if error:
raise HTTPException(status_code=400, detail=error)
return {"text": text, "method": method, "chars": len(text) if text else 0, "filename": file.filename}
finally:
os.unlink(tmp_path)
@app.post("/api/explain", response_model=ExplainResponse)
async def explain(req: ExplainRequest, user: dict = Depends(require_auth)):
desc = DESC_MAP.get(req.category, "Unknown category.")
legal = "Consult local consumer protection laws."
recommendation = "Review this clause carefully."
if SAULLM_ENDPOINT and HF_API_TOKEN:
try:
prompt = (
f"Analyze this contract clause and explain why it may be risky.\n\n"
f"Clause: \"{req.clause}\"\nCategory: {req.category}\n\n"
f"Provide: 1) Plain-English explanation 2) Legal basis 3) Recommendation"
)
async with httpx.AsyncClient(timeout=30.0) as client:
resp = await client.post(
SAULLM_ENDPOINT,
json={"inputs": prompt, "parameters": {"max_new_tokens": 300, "temperature": 0.3}},
headers={"Authorization": f"Bearer {HF_API_TOKEN}"},
)
if resp.status_code == 200:
output = resp.json()
generated = output[0]["generated_text"] if isinstance(output, list) else output.get("generated_text", "")
if generated and len(generated) > 50:
parts = generated.split("\n\n")
desc = parts[0] if len(parts) > 0 else desc
legal = parts[1] if len(parts) > 1 else legal
recommendation = parts[2] if len(parts) > 2 else recommendation
except Exception:
pass
return ExplainResponse(clause=req.clause, category=req.category,
explanation=desc, legal_basis=legal, recommendation=recommendation)
@app.get("/api/history")
async def history(user: dict = Depends(require_auth), limit: int = 20, offset: int = 0):
limit = min(limit, 100)
data = await supabase_query("analyses", {
"user_id": f"eq.{user['id']}", "select": "*",
"order": "created_at.desc", "limit": str(limit), "offset": str(offset),
})
return {"analyses": data, "limit": limit, "offset": offset}
if __name__ == "__main__":
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=8000)
|