Elasticsearch と LlamaIndex を使用して RAG の機密情報と PII 情報を保護する

python3 -m venv .venv

source .venv/bin/activate
pip install llama-index 
pip install llama-index-embeddings-openai
pip install llama-index-vector-stores-elasticsearch
pip install sentence-transformers
pip install python-dotenv
pip install openai

OPENAI_API_KEY="REPLACEME"
ELASTIC_CLOUD_ID="REPLACEME"
ELASTIC_API_KEY="REPLACEME"

{
"conversation_id": 103,
"customer_name": "Sophia Jones",
"agent_name": "Emily Wilson",
"policy_number": "JKL0123",
"conversation": "Customer: Hi, I'm Sophia Jones. My Date of Birth is November 15th, 1985, Address is 303 Cedar St, Miami, FL 33101, and my Policy Number is JKL0123.\nAgent: Hello, Sophia. How may I assist you today?\nCustomer: Hello, Emily. I have a question about my policy.\nCustomer: There's been a break-in at my home, and some valuable items are missing. Are they covered?\nAgent: Let me check your policy for coverage related to theft.\nAgent: Yes, theft of personal belongings is covered under your policy.\nCustomer: That's a relief. I'll need to file a claim for the stolen items.\nAgent: We'll assist you with the claim process, Sophia. Is there anything else I can help you with?\nCustomer: No, that's all for now. Thank you for your assistance, Emily.\nAgent: You're welcome, Sophia. Please feel free to reach out if you have any further questions or concerns.\nCustomer: I will. Have a great day!\nAgent: You too, Sophia. Take care.",
"summary": "A customer inquires about coverage for stolen items after a break-in at home, and the agent confirms that theft of personal belongings is covered under the policy. The agent offers assistance with the claim process, resulting in the customer expressing relief and gratitude."
}

# index.py
# pip install sentence-transformers
# pip install llama-index-embeddings-openai
# pip install llama-index-embeddings-huggingface

import json
import os
from dotenv import load_dotenv
from llama_index.core import Document
from llama_index.core import Settings
from llama_index.core.ingestion import IngestionPipeline
from llama_index.core.node_parser import SentenceSplitter
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.vector_stores.elasticsearch import ElasticsearchStore


def get_documents_from_file(file):
   """Reads a json file and returns list of Documents"""

   with open(file=file, mode='rt') as f:
       conversations_dict = json.loads(f.read())

   # Build Document objects using fields of interest.
   documents = [Document(text=item['conversation'],
                         metadata={"conversation_id": item['conversation_id']})
                for
                item in conversations_dict]
   return documents

# Load .env file contents into env
load_dotenv('.env')
Settings.embed_model = HuggingFaceEmbedding(
   model_name="BAAI/bge-small-en-v1.5"
)

def main():
   # ElasticsearchStore is a VectorStore that
   # takes care of Elasticsearch Index and Data management.
   es_vector_store = ElasticsearchStore(index_name="convo_index",
                                        vector_field='conversation_vector',
                                        text_field='conversation',
                                        es_cloud_id=os.getenv("ELASTIC_CLOUD_ID"),
                                        es_api_key=os.getenv("ELASTIC_API_KEY"))

   # LlamaIndex Pipeline configured to take care of chunking, embedding
   # and storing the embeddings in the vector store.
   llamaindex_pipeline = IngestionPipeline(
       transformations=[
           SentenceSplitter(chunk_size=350, chunk_overlap=50),
           Settings.embed_model
       ],
       vector_store=es_vector_store
   )

   # Load data from a json file into a list of LlamaIndex Documents
   documents = get_documents_from_file(file="conversations.json")
   llamaindex_pipeline.run(documents=documents)
   print(".....Indexing Data Completed.....\n")

if __name__ == "__main__":
   main()

# query.py
from llama_index.core import VectorStoreIndex, QueryBundle, Settings
from llama_index.llms.openai import OpenAI
from index import es_vector_store

# Public LLM where we send user query and Related Documents
llm = OpenAI()

index = VectorStoreIndex.from_vector_store(es_vector_store)

# This query_engine, for a given user query retrieves top 10 similar documents from
# Elasticsearch vector database and sends the documents along with the user query to the LLM.
# Note that documents are sent as-is. So any PII/Sensitive data is sent to the LLM.
query_engine = index.as_query_engine(llm, similarity_top_k=10)

query="Give me summary of water related claims that customers raised."
bundle = QueryBundle(query, embedding=Settings.embed_model.get_query_embedding(query))
result = query_engine.query(bundle)
print(result)

# query_masking_nlp.py

# pip install spacy
# python3 - m spacy download en_core_web_sm
import re
from typing import List, Optional

import spacy
from llama_index.core import VectorStoreIndex, QueryBundle, Settings
from llama_index.core.postprocessor.types import BaseNodePostprocessor
from llama_index.core.schema import NodeWithScore
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.openai import OpenAI
from index import es_vector_store

# Load the spaCy model
nlp = spacy.load("en_core_web_sm")

# Compile regex patterns for performance
phone_pattern = re.compile(r'\b\d{3}[-.]?\d{3}[-.]?\d{4}\b')
email_pattern = re.compile(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b')
date_pattern = re.compile(r'\b(\d{1,2}[-/]\d{1,2}[-/]\d{2,4}|\d{2,4}[-/]\d{1,2}[-/]\d{1,2})\b')
dob_pattern = re.compile(
r"(January|February|March|April|May|June|July|August|September|October|November|December)\s(\d{1,2})(st|nd|rd|th),\s(\d{4})")
address_pattern = re.compile(r'\d+\s+[\w\s]+\,\s+[A-Za-z]+\,\s+[A-Z]{2}\s+\d{5}(-\d{4})?')
zip_code_pattern =  re.compile(r'\b\d{5}(?:-\d{4})?\b')
policy_number_pattern = re.compile(r"[A-Z]{3}\d{4}\.$")  # 3 characters followed by 4 digits, in our case e.g XYZ9876

Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")

# match = re.match(policy_number_pattern, "XYZ9876")
# print(match)


def mask_pii(text):
   """
   Masks Personally Identifiable Information (PII) in the given
   text using pre-defined regex patterns and spaCy's named entity recognition.
   Args:
       text (str): The input text containing potential PII.
   Returns:
       str: The text with PII masked.
   """

   # Process the text with spaCy for NER
   doc = nlp(text)

   # Mask entities identified by spaCy NER (e.g First/Last Names etc)
   for ent in doc.ents:
       if ent.label_ in ["PERSON", "ORG", "GPE"]:
           text = text.replace(ent.text, '[MASKED]')

   # Apply regex patterns after NER to avoid overlapping issues
   text = phone_pattern.sub('[PHONE MASKED]', text)
   text = email_pattern.sub('[EMAIL MASKED]', text)
   text = date_pattern.sub('[DATE MASKED]', text)
   text = address_pattern.sub('[ADDRESS MASKED]', text)
   text = dob_pattern.sub('[DOB MASKED]', text)
   text = zip_code_pattern.sub('[ZIP MASKED]', text)
   text = policy_number_pattern.sub('[POLICY MASKED]', text)

   return text


class CustomPostProcessor(BaseNodePostprocessor):
   """
   Custom Postprocessor which masks Personally Identifiable Information (PII).
   PostProcessor is called on the Documents before they are sent to the LLM.
   """
   def _postprocess_nodes(
           self, nodes: List[NodeWithScore], query_bundle: Optional[QueryBundle]
   ) -> List[NodeWithScore]:
       # Masks PII
       for n in nodes:
          n.node.set_content(mask_pii(n.text))
       return nodes

   
# Use Public LLM to send user query and Related Documents
llm = OpenAI()
index = VectorStoreIndex.from_vector_store(es_vector_store)

# This query_engine, for a given user query retrieves top 10 similar documents from
# Elasticsearch vector database and sends the documents along with the user query to the LLM.
# Note that documents are masked based on custom logic defined in CustomPostProcessor._postprocess_nodes.
query_engine = index.as_query_engine(llm, similarity_top_k=10, node_postprocessors=[CustomPostProcessor()])



query = "Give me summary of water related claims that customers raised."
bundle = QueryBundle(query, embedding=Settings.embed_model.get_query_embedding(query))
response = query_engine.query(bundle)
print(response)

from llama_index.core import VectorStoreIndex, QueryBundle, Settings
from llama_index.core.postprocessor import NERPIINodePostprocessor
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.openai import OpenAI
from index import es_vector_store

Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")

# Use Public LLM to send user query and Related Documents
llm = OpenAI()

ner_processor = NERPIINodePostprocessor()
index = VectorStoreIndex.from_vector_store(es_vector_store)

# This query_engine, for a given user query retrieves top 10 similar documents from
# Elasticsearch vector database and sends the documents along with the user query to the LLM.
# Note that documents masked using the NERPIINodePostprocessor so that PII/Sensitive data is not sent to the LLM.
query_engine = index.as_query_engine(llm, similarity_top_k=10, node_postprocessors=[ner_processor])

query = "Give me summary of fire related claims that customers raised."
bundle = QueryBundle(query, embedding=Settings.embed_model.get_query_embedding(query))
response = query_engine.query(bundle)
print(response)

ollama run mistral

# pip install llama-index-llms-ollama
from llama_index.core import VectorStoreIndex, QueryBundle, Settings
from llama_index.core.postprocessor import PIINodePostprocessor
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.ollama import Ollama
from llama_index.llms.openai import OpenAI
from index import es_vector_store

Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")

# Use Public LLM to send user query and Related Documents and Local LLM to mask
public_llm = OpenAI()
local_llm = Ollama(model="mistral")

pii_processor = PIINodePostprocessor(llm=local_llm)
index = VectorStoreIndex.from_vector_store(es_vector_store)

# This query_engine, for a given user query retrieves top 10 similar documents from
# Elasticsearch vector database and sends the documents along with the user query to the public LLM.
# Note that documents are masked using the local llm via PIINodePostprocessor
# so that PII/Sensitive data is not sent to the public LLM.
query_engine = index.as_query_engine(public_llm, similarity_top_k=10, node_postprocessors=[pii_processor])


query = "Give me summary of fire related claims that customers raised."
bundle = QueryBundle(query, embedding=Settings.embed_model.get_query_embedding(query))
result = query_engine.query(bundle)
print(result)