使用PebbloRetrievalQA的身份启用RAG

%pip install --upgrade --quiet langchain langchain_core langchain-community langchain-openai qdrant_client

from langchain_community.vectorstores.qdrant import Qdrant
from langchain_core.documents import Document
from langchain_openai.embeddings import OpenAIEmbeddings
from langchain_openai.llms import OpenAI

llm = OpenAI()
embeddings = OpenAIEmbeddings()
collection_name = "pebblo-identity-and-semantic-rag"

page_content = """
**ACME Corp Financial Report**

**Overview:**
ACME Corp, a leading player in the merger and acquisition industry, presents its financial report for the fiscal year ending December 31, 2020. 
Despite a challenging economic landscape, ACME Corp demonstrated robust performance and strategic growth.

**Financial Highlights:**
Revenue soared to $50 million, marking a 15% increase from the previous year, driven by successful deal closures and expansion into new markets. 
Net profit reached $12 million, showcasing a healthy margin of 24%.

**Key Metrics:**
Total assets surged to $80 million, reflecting a 20% growth, highlighting ACME Corp's strong financial position and asset base. 
Additionally, the company maintained a conservative debt-to-equity ratio of 0.5, ensuring sustainable financial stability.

**Future Outlook:**
ACME Corp remains optimistic about the future, with plans to capitalize on emerging opportunities in the global M&A landscape. 
The company is committed to delivering value to shareholders while maintaining ethical business practices.

**Bank Account Details:**
For inquiries or transactions, please refer to ACME Corp's US bank account:
Account Number: 123456789012
Bank Name: Fictitious Bank of America
"""

documents = [
    Document(
        **{
            "page_content": page_content,
            "metadata": {
                "pebblo_semantic_topics": ["financial-report"],
                "pebblo_semantic_entities": ["us-bank-account-number"],
                "authorized_identities": ["finance-team", "exec-leadership"],
                "page": 0,
                "source": "https://drive.google.com/file/d/xxxxxxxxxxxxx/view",
                "title": "ACME Corp Financial Report.pdf",
            },
        }
    )
]

vectordb = Qdrant.from_documents(
    documents,
    embeddings,
    location=":memory:",
    collection_name=collection_name,
)

print("Vectordb loaded.")

from langchain_community.chains import PebbloRetrievalQA
from langchain_community.chains.pebblo_retrieval.models import AuthContext, ChainInput

# Initialize PebbloRetrievalQA chain
qa_chain = PebbloRetrievalQA.from_chain_type(
    llm=llm,
    retriever=vectordb.as_retriever(),
    app_name="pebblo-identity-rag",
    description="Identity Enforcement app using PebbloRetrievalQA",
    owner="ACME Corp",
)


def ask(question: str, auth_context: dict):
    """
    Ask a question to the PebbloRetrievalQA chain
    """
    auth_context_obj = AuthContext(**auth_context) if auth_context else None
    chain_input_obj = ChainInput(query=question, auth_context=auth_context_obj)
    return qa_chain.invoke(chain_input_obj.dict())

auth = {
    "user_id": "finance-user@acme.org",
    "user_auth": [
        "finance-team",
    ],
}

question = "Share the financial performance of ACME Corp for the year 2020"
resp = ask(question, auth)
print(f"Question: {question}\n\nAnswer: {resp['result']}")

auth = {
    "user_id": "eng-user@acme.org",
    "user_auth": [
        "eng-support",
    ],
}

question = "Share the financial performance of ACME Corp for the year 2020"
resp = ask(question, auth)
print(f"Question: {question}\n\nAnswer: {resp['result']}")

from langchain_core.prompts import PromptTemplate

prompt_template = PromptTemplate.from_template(
    """
Answer the question using the provided context. 
If no context is provided, just say "I'm sorry, but that information is unavailable, or Access to it is restricted.".

Question: {question}
"""
)

question = "Share the financial performance of ACME Corp for the year 2020"
prompt = prompt_template.format(question=question)

auth = {
    "user_id": "finance-user@acme.org",
    "user_auth": [
        "finance-team",
    ],
}
resp = ask(prompt, auth)
print(f"Question: {question}\n\nAnswer: {resp['result']}")

auth = {
    "user_id": "eng-user@acme.org",
    "user_auth": [
        "eng-support",
    ],
}
resp = ask(prompt, auth)
print(f"Question: {question}\n\nAnswer: {resp['result']}")

from typing import List, Optional

from langchain_community.chains import PebbloRetrievalQA
from langchain_community.chains.pebblo_retrieval.models import (
    ChainInput,
    SemanticContext,
)

# Initialize PebbloRetrievalQA chain
qa_chain = PebbloRetrievalQA.from_chain_type(
    llm=llm,
    retriever=vectordb.as_retriever(),
    app_name="pebblo-semantic-rag",
    description="Semantic Enforcement app using PebbloRetrievalQA",
    owner="ACME Corp",
)


def ask(
    question: str,
    topics_to_deny: Optional[List[str]] = None,
    entities_to_deny: Optional[List[str]] = None,
):
    """
    Ask a question to the PebbloRetrievalQA chain
    """
    semantic_context = dict()
    if topics_to_deny:
        semantic_context["pebblo_semantic_topics"] = {"deny": topics_to_deny}
    if entities_to_deny:
        semantic_context["pebblo_semantic_entities"] = {"deny": entities_to_deny}

    semantic_context_obj = (
        SemanticContext(**semantic_context) if semantic_context else None
    )
    chain_input_obj = ChainInput(query=question, semantic_context=semantic_context_obj)
    return qa_chain.invoke(chain_input_obj.dict())

topic_to_deny = []
entities_to_deny = []
question = "Share the financial performance of ACME Corp for the year 2020"
resp = ask(question, topics_to_deny=topic_to_deny, entities_to_deny=entities_to_deny)
print(
    f"Topics to deny: {topic_to_deny}\nEntities to deny: {entities_to_deny}\n"
    f"Question: {question}\nAnswer: {resp['result']}"
)

topic_to_deny = ["financial-report"]
entities_to_deny = []
question = "Share the financial performance of ACME Corp for the year 2020"
resp = ask(question, topics_to_deny=topic_to_deny, entities_to_deny=entities_to_deny)
print(
    f"Topics to deny: {topic_to_deny}\nEntities to deny: {entities_to_deny}\n"
    f"Question: {question}\nAnswer: {resp['result']}"
)

topic_to_deny = []
entities_to_deny = ["us-bank-account-number"]
question = "Share the financial performance of ACME Corp for the year 2020"
resp = ask(question, topics_to_deny=topic_to_deny, entities_to_deny=entities_to_deny)
print(
    f"Topics to deny: {topic_to_deny}\nEntities to deny: {entities_to_deny}\n"
    f"Question: {question}\nAnswer: {resp['result']}"
)