Создание корпоративного AI-ассистента на Colab с RAG и политиками безопасности

!pip -q install faiss-cpu transformers==4.44.2 accelerate sentence-transformers==3.0.1

from typing import List, Dict, Tuple
import re, textwrap, numpy as np, torch
from sentence_transformers import SentenceTransformer
import faiss
from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM


GEN_MODEL = "google/flan-t5-base"
EMB_MODEL = "sentence-transformers/all-MiniLM-L6-v2"


gen_tok = AutoTokenizer.from_pretrained(GEN_MODEL)
gen_model = AutoModelForSeq2SeqLM.from_pretrained(GEN_MODEL, device_map="auto")
generate = pipeline("text2text-generation", model=gen_model, tokenizer=gen_tok)


emb_device = "cuda" if torch.cuda.is_available() else "cpu"
emb_model = SentenceTransformer(EMB_MODEL, device=emb_device)

DOCS = [
 {"id":"policy_sec_001","title":"Data Security Policy",
  "text":"All customer data must be encrypted at rest (AES-256) and in transit (TLS 1.2+). Access is role-based (RBAC). Secrets are stored in a managed vault. Backups run nightly with 35-day retention. PII includes name, email, phone, address, PAN/Aadhaar."},
 {"id":"policy_ai_002","title":"Responsible AI Guidelines",
  "text":"Use internal models for confidential data. Retrieval sources must be logged. No customer decisioning without human-in-the-loop. Redact PII in prompts and outputs. All model prompts and outputs are stored for audit for 180 days."},
 {"id":"runbook_inc_003","title":"Incident Response Runbook",
  "text":"If a suspected breach occurs, page on-call SecOps. Rotate keys, isolate affected services, perform forensic capture, notify DPO within regulatory SLA. Communicate via the incident room only."},
 {"id":"sop_sales_004","title":"Sales SOP - Enterprise Deals",
  "text":"For RFPs, use the approved security questionnaire responses. Claims must match policy_sec_001. Custom clauses need Legal sign-off. Keep records in CRM with deal room links."}
]


def chunk(text:str, chunk_size=600, overlap=80):
   w = text.split()
   if len(w) <= chunk_size: return [text]
   out=[]; i=0
   while i < len(w):
       j=min(i+chunk_size, len(w)); out.append(" ".join(w[i:j]))
       if j==len(w): break
       i = j - overlap
   return out


CORPUS=[]
for d in DOCS:
   for i,c in enumerate(chunk(d["text"])):
       CORPUS.append({"doc_id":d["id"],"title":d["title"],"chunk_id":i,"text":c})

def build_index(chunks:List[Dict]) -> Tuple[faiss.IndexFlatIP, np.ndarray]:
   vecs = emb_model.encode([c["text"] for c in chunks], normalize_embeddings=True, convert_to_numpy=True)
   index = faiss.IndexFlatIP(vecs.shape[1]); index.add(vecs); return index, vecs


INDEX, VECS = build_index(CORPUS)

PII_PATTERNS = [
   (re.compile(r"\b\d{10}\b"), "<REDACTED_PHONE>"),
   (re.compile(r"\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b", re.I), "<REDACTED_EMAIL>"),
   (re.compile(r"\b\d{12}\b"), "<REDACTED_ID12>"),
   (re.compile(r"\b[A-Z]{5}\d{4}[A-Z]\b"), "<REDACTED_PAN>")
]
def redact(t:str)->str:
   for p,r in PII_PATTERNS: t = p.sub(r, t)
   return t


POLICY_DISALLOWED = [
   re.compile(r"\b(share|exfiltrate)\b.*\b(raw|all)\b.*\bdata\b", re.I),
   re.compile(r"\bdisable\b.*\bencryption\b", re.I),
]
def policy_check(q:str):
   for r in POLICY_DISALLOWED:
       if r.search(q): return False, "Request violates security policy (data exfiltration/encryption tampering)."
   return True, ""

def retrieve(query:str, k=4)->List[Dict]:
   qv = emb_model.encode([query], normalize_embeddings=True, convert_to_numpy=True)
   scores, idxs = INDEX.search(qv, k)
   return [{**CORPUS[i], "score": float(s)} for s,i in zip(scores[0], idxs[0])]


SYSTEM = ("You are an enterprise AI assistant.\n"
         "- Answer strictly from the provided CONTEXT.\n"
         "- If missing info, say what is unknown and suggest the correct policy/runbook.\n"
         "- Keep it concise and cite titles + doc_ids inline like [Title (doc_id:chunk)].")
def build_prompt(user_q:str, ctx_blocks:List[Dict])->str:
   ctx = "\n\n".join(f"[{i+1}] {b['title']} (doc:{b['doc_id']}:{b['chunk_id']})\n{b['text']}" for i,b in enumerate(ctx_blocks))
   uq = redact(user_q)
   return f"SYSTEM:\n{SYSTEM}\n\nCONTEXT:\n{ctx}\n\nUSER QUESTION:\n{uq}\n\nINSTRUCTIONS:\n- Cite sources inline.\n- Keep to 5-8 sentences.\n- Preserve redactions."


def answer(user_q:str, k=4, max_new_tokens=220)->Dict:
   ok,msg = policy_check(user_q)
   if not ok: return {"answer": f" {msg}", "ctx":[]}
   ctx = retrieve(user_q, k=k); prompt = build_prompt(user_q, ctx)
   out = generate(prompt, max_new_tokens=max_new_tokens, do_sample=False)[0]["generated_text"].strip()
   return {"answer": out, "ctx": ctx}

def eval_query(user_q:str, ctx:List[Dict])->Dict:
   terms = [w.lower() for w in re.findall(r"[a-zA-Z]{4,}", user_q)]
   ctx_text = " ".join(c["text"].lower() for c in ctx)
   hits = sum(t in ctx_text for t in terms)
   return {"terms": len(terms), "hits": hits, "hit_rate": round(hits/max(1,len(terms)), 2)}


QUERIES = [
   "What encryption and backup rules do we follow for customer data?",
   "Can we auto-answer RFP security questionnaires? What should we cite?",
   "If there is a suspected breach, what are the first three steps?",
   "Is it allowed to share all raw customer data externally for testing?"
]
for q in QUERIES:
   res = answer(q, k=3)
   print("\n" + "="*100); print("Q:", q); print("\nA:", res["answer"])
   if res["ctx"]:
       ev = eval_query(q, res["ctx"]); print("\nRetrieved Context (top 3):")
       for r in res["ctx"]: print(f"- {r['title']} [{r['doc_id']}:{r['chunk_id']}] score={r['score']:.3f}")
       print("Eval:", ev)