Neo4j 向量索引集成

# Pip install necessary package
pip install -qU  neo4j
pip install -qU  langchain-openai langchain-neo4j
pip install -qU  tiktoken

import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")

OpenAI API Key: ········

from langchain_community.document_loaders import TextLoader
from langchain_core.documents import Document
from langchain_neo4j import Neo4jVector
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

loader = TextLoader("../../how_to/state_of_the_union.txt")

documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()

# Neo4jVector requires the Neo4j database credentials

url = "bolt://localhost:7687"
username = "neo4j"
password = "password"

# You can also use environment variables instead of directly passing named parameters
# os.environ["NEO4J_URI"] = "bolt://localhost:7687"
# os.environ["NEO4J_USERNAME"] = "neo4j"
# os.environ["NEO4J_PASSWORD"] = "pleaseletmein"

# The Neo4jVector Module will connect to Neo4j and create a vector index if needed.

db = Neo4jVector.from_documents(
    docs, OpenAIEmbeddings(), url=url, username=username, password=password
)

query = "What did the president say about Ketanji Brown Jackson"
docs_with_score = db.similarity_search_with_score(query, k=2)

for doc, score in docs_with_score:
    print("-" * 80)
    print("Score: ", score)
    print(doc.page_content)
    print("-" * 80)

--------------------------------------------------------------------------------
Score:  0.9076391458511353
Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you're at it, pass the Disclose Act so Americans can know who is funding our elections.

Tonight, I'd like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.

And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation's top legal minds, who will continue Justice Breyer's legacy of excellence.
--------------------------------------------------------------------------------
--------------------------------------------------------------------------------
Score:  0.8912242650985718
A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she's been nominated, she's received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.

And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.

We can do both. At our border, we've installed new technology like cutting-edge scanners to better detect drug smuggling.

We've set up joint patrols with Mexico and Guatemala to catch more human traffickers.

We're putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster.

We're securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.
--------------------------------------------------------------------------------

index_name = "vector"  # default index name

store = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name=index_name,
)

# First we create sample data in graph
store.query(
    "CREATE (p:Person {name: 'Tomaz', location:'Slovenia', hobby:'Bicycle', age: 33})"
)

[]

# Now we initialize from existing graph
existing_graph = Neo4jVector.from_existing_graph(
    embedding=OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name="person_index",
    node_label="Person",
    text_node_properties=["name", "location"],
    embedding_node_property="embedding",
)
result = existing_graph.similarity_search("Slovenia", k=1)

result[0]

Document(page_content='\nname: Tomaz\nlocation: Slovenia', metadata={'age': 33, 'hobby': 'Bicycle'})

# First we create sample data and index in graph
store.query(
    "MERGE (p:Person {name: 'Tomaz'}) "
    "MERGE (p1:Person {name:'Leann'}) "
    "MERGE (p1)-[:FRIEND {text:'example text', embedding:$embedding}]->(p2)",
    params={"embedding": OpenAIEmbeddings().embed_query("example text")},
)
# Create a vector index
relationship_index = "relationship_vector"
store.query(
    """
CREATE VECTOR INDEX $relationship_index
IF NOT EXISTS
FOR ()-[r:FRIEND]-() ON (r.embedding)
OPTIONS {indexConfig: {
 `vector.dimensions`: 1536,
 `vector.similarity_function`: 'cosine'
}}
""",
    params={"relationship_index": relationship_index},
)

[]

relationship_vector = Neo4jVector.from_existing_relationship_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name=relationship_index,
    text_node_property="text",
)
relationship_vector.similarity_search("Example")

[Document(page_content='example text')]

existing_graph.similarity_search(
    "Slovenia",
    filter={"hobby": "Bicycle", "name": "Tomaz"},
)

[Document(page_content='\nname: Tomaz\nlocation: Slovenia', metadata={'age': 33, 'hobby': 'Bicycle'})]

existing_graph.similarity_search(
    "Slovenia",
    filter={"hobby": {"$eq": "Bicycle"}, "age": {"$gt": 15}},
)

[Document(page_content='\nname: Tomaz\nlocation: Slovenia', metadata={'age': 33, 'hobby': 'Bicycle'})]

existing_graph.similarity_search(
    "Slovenia",
    filter={"$or": [{"hobby": {"$eq": "Bicycle"}}, {"age": {"$gt": 15}}]},
)

[Document(page_content='\nname: Tomaz\nlocation: Slovenia', metadata={'age': 33, 'hobby': 'Bicycle'})]

store.add_documents([Document(page_content="foo")])

['acbd18db4cc2f85cedef654fccc4a4d8']

docs_with_score = store.similarity_search_with_score("foo")

docs_with_score[0]

(Document(page_content='foo'), 0.9999997615814209)

read_query = (
  "CALL db.index.vector.queryNodes($index, $k, $embedding) "
  "YIELD node, score "
) + retrieval_query

retrieval_query = """
RETURN "Name:" + node.name AS text, score, {foo:"bar"} AS metadata
"""
retrieval_example = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name="person_index",
    retrieval_query=retrieval_query,
)
retrieval_example.similarity_search("Foo", k=1)

[Document(page_content='Name:Tomaz', metadata={'foo': 'bar'})]

retrieval_query = """
RETURN node {.name, .age, .hobby} AS text, score, {foo:"bar"} AS metadata
"""
retrieval_example = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name="person_index",
    retrieval_query=retrieval_query,
)
retrieval_example.similarity_search("Foo", k=1)

[Document(page_content='name: Tomaz\nage: 33\nhobby: Bicycle\n', metadata={'foo': 'bar'})]

retrieval_query = """
RETURN node {.*, embedding:Null, extra: $extra} AS text, score, {foo:"bar"} AS metadata
"""
retrieval_example = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name="person_index",
    retrieval_query=retrieval_query,
)
retrieval_example.similarity_search("Foo", k=1, params={"extra": "ParamInfo"})

[Document(page_content='location: Slovenia\nextra: ParamInfo\nname: Tomaz\nage: 33\nhobby: Bicycle\nembedding: None\n', metadata={'foo': 'bar'})]

# The Neo4jVector Module will connect to Neo4j and create a vector and keyword indices if needed.
hybrid_db = Neo4jVector.from_documents(
    docs,
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    search_type="hybrid",
)

index_name = "vector"  # default index name
keyword_index_name = "keyword"  # default keyword index name

store = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name=index_name,
    keyword_index_name=keyword_index_name,
    search_type="hybrid",
)

retriever = store.as_retriever()
retriever.invoke(query)[0]

Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you're at it, pass the Disclose Act so Americans can know who is funding our elections. \n\nTonight, I'd like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation's top legal minds, who will continue Justice Breyer's legacy of excellence.', metadata={'source': '../../how_to/state_of_the_union.txt'})

from langchain_classic.chains import RetrievalQAWithSourcesChain
from langchain_openai import ChatOpenAI

chain = RetrievalQAWithSourcesChain.from_chain_type(
    ChatOpenAI(temperature=0), chain_type="stuff", retriever=retriever
)

chain.invoke(
    {"question": "What did the president say about Justice Breyer"},
    return_only_outputs=True,
)

{'answer': 'The president honored Justice Stephen Breyer for his service to the country and mentioned his retirement from the United States Supreme Court.\n',
 'sources': '../../how_to/state_of_the_union.txt'}