使用 Neo4j 和 LangChain 集成非结构化知识图增强 QA

pip install langchain openai wikipedia tiktoken neo4j python-dotenv transformers
pip install -U sagemaker

import os
import re
from langchain.vectorstores.neo4j_vector import Neo4jVector
from langchain.document_loaders import WikipediaLoader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from dotenv import load_dotenv


load_dotenv()
os.environ["OPENAI_API_KEY"] = os.getenv('OPENAI_API_KEY')
os.environ["NEO4J_URI"] = os.getenv('NEO4J_URI')
os.environ["NEO4J_USERNAME"] = os.getenv('NEO4J_USERNAME')
os.environ["NEO4J_PASSWORD"] = os.getenv('NEO4J_PASSWORD')

tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")


def bert_len(text):
    tokens = tokenizer.encode(text)
    return len(tokens)


raw_documents = WikipediaLoader(query="Leonhard Euler").load()
text_splitter = RecursiveCharacterTextSplitter(
          chunk_size = 200,
          chunk_overlap  = 20,
          length_function = bert_len,
          separators=['\n\n', '\n', ' ', ''],
      )


documents = text_splitter.create_documents([raw_documents[0].page_content])

# Instantiate Neo4j vector from documents
neo4j_vector = Neo4jVector.from_documents(
    documents,
    OpenAIEmbeddings(),
    url=os.environ["NEO4J_URI"],
    username=os.environ["NEO4J_USERNAME"],
    password=os.environ["NEO4J_PASSWORD"]
)

query = "Who were the siblings of Leonhard Euler?"
vector_results = neo4j_vector.similarity_search(query, k=2)
for i, res in enumerate(vector_results):
    print(res.page_content)
    if i != len(vector_results)-1:
        print()
vector_result = vector_results[0].page_content

"""
You are a data scientist working for a company that is building a graph database. Your task is to extract information from data and convert it into a graph database.
Provide a set of Nodes in the form [ENTITY_ID, TYPE, PROPERTIES] and a set of relationships in the form [ENTITY_ID_1, RELATIONSHIP, ENTITY_ID_2, PROPERTIES].
It is important that the ENTITY_ID_1 and ENTITY_ID_2 exists as nodes with a matching ENTITY_ID. If you can't pair a relationship with a pair of nodes don't add it.
When you find a node or relationship you want to add try to create a generic TYPE for it that  describes the entity you can also think of it as a label.


Example:
Data: Alice lawyer and is 25 years old and Bob is her roommate since 2001. Bob works as a journalist. Alice owns a the webpage www.alice.com and Bob owns the webpage www.bob.com.
Nodes: ["alice", "Person", {"age": 25, "occupation": "lawyer", "name":"Alice"}], ["bob", "Person", {"occupation": "journalist", "name": "Bob"}], ["alice.com", "Webpage", {"url": "www.alice.com"}], ["bob.com", "Webpage", {"url": "www.bob.com"}]
Relationships: ["alice", "roommate", "bob", {"start": 2021}], ["alice", "owns", "alice.com", {}], ["bob", "owns", "bob.com", {}]
"""

from langchain.chat_models import ChatOpenAI
from langchain.chains import GraphCypherQAChain
from langchain.graphs import Neo4jGraph

graph = Neo4jGraph(
    url=os.environ["NEO4J_URI"], username=os.environ["NEO4J_USERNAME"], password=os.environ["NEO4J_PASSWORD"]
)


print(graph.schema)

Node properties are the following:
[{'labels': 'Person', 'properties': [{'property': 'name', 'type': 'STRING'}, 
{'property': 'nationality', 'type': 'STRING'}, 
{'property': 'death_date', 'type': 'STRING'}, 
{'property': 'birth_date', 'type': 'STRING'}]}, 
{'labels': 'Location', 'properties': [{'property': 'name', 'type': 'STRING'}]}, 
{'labels': 'Organization', 'properties': [{'property': 'name', 'type': 'STRING'}]}, 
{'labels': 'Publication', 'properties': [{'property': 'name', 'type': 'STRING'}]}]


Relationship properties are the following:
[]
The relationships are the following:
['(:Person)-[:worked_at]->(:Organization)', 
'(:Person)-[:influenced_by]->(:Person)', 
'(:Person)-[:born_in]->(:Location)', 
'(:Person)-[:lived_in]->(:Location)', 
'(:Person)-[:child_of]->(:Person)', 
'(:Person)-[:sibling_of]->(:Person)', 
'(:Person)-[:published]->(:Publication)']

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True
)


graph_result = chain.run("Who were the siblings of Leonhard Euler?")

'The siblings of Leonhard Euler were Maria Magdalena and Anna Maria.'

import json
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri


try:
    role = sagemaker.get_execution_role()
except ValueError:
    iam = boto3.client('iam')
    role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']
    
hub = {
    'HF_MODEL_ID':'mistralai/Mistral-7B-Instruct-v0.1',
    'SM_NUM_GPUS': json.dumps(1)
}


huggingface_model = HuggingFaceModel(
    image_uri=get_huggingface_llm_image_uri("huggingface",version="1.1.0"),
    env=hub,
    role=role, 
)

mistral7b_predictor = huggingface_model.deploy(
    initial_instance_count=1,
    instance_type="ml.g5.4xlarge",
    container_startup_health_check_timeout=300,
)


query = "Who were the siblings of Leonhard Euler?"
final_prompt = f"""You are a helpful question-answering agent. Your task is to analyze 
and synthesize information from two sources: the top result from a similarity search 
(unstructured information) and relevant data from a graph database (structured information). 
Given the user's query: {query}, provide a meaningful and efficient answer based 
on the insights derived from the following data:


Unstructured information: {vector_result}. 
Structured information: {graph_result}.
"""


response = mistral7b_predictor.predict({
    "inputs": final_prompt,
})


print(re.search(r"Answer: (.+)", response[0]['generated_text']).group(1))

The siblings of Leonhard Euler were Maria Magdalena and Anna Maria.