LlamaIndex Integration

Build compliant RAG pipelines without exposing PII.

Install

pip install llama-index-ambientmeta

Quick Start

from llama_index.core import VectorStoreIndex, Settings
from llama_index.llms.openai import OpenAI
from llama_index_ambientmeta import PrivacyLLM

# Wrap your LLM with privacy protection
Settings.llm = PrivacyLLM(
    llm=OpenAI(),
    ambientmeta_api_key="am_live_xxx"
)

# Build your index as normal
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()

# Queries are automatically sanitized
response = query_engine.query("What's in John Smith's contract?")
# LLM never sees real names

How It Works

1. Your query is sanitized before processing
2. RAG retrieval happens with sanitized text
3. The LLM generates a response with placeholders
4. Response is rehydrated with original entities

With Chat Engine

chat_engine = index.as_chat_engine()

# Multi-turn conversations stay private
response = chat_engine.chat("Tell me about employee EMP-123456")
response = chat_engine.chat("What's their email?")

Configuration

Settings.llm = PrivacyLLM(
    llm=OpenAI(model="gpt-4"),
    ambientmeta_api_key="am_live_xxx",
    entities=["PERSON", "EMAIL", "SSN"],  # Optional
    custom_patterns=True
)

With Any LLM

Works with any LlamaIndex-supported LLM:

from llama_index.llms.anthropic import Anthropic

Settings.llm = PrivacyLLM(
    llm=Anthropic(model="claude-sonnet-4-20250514"),
    ambientmeta_api_key="am_live_xxx"
)