Diffbot
Diffbot is a suite of ML-based products that make it easy to structure web data.
Diffbot's Natural Language Processing API allows for the extraction of entities, relationships, and semantic meaning from unstructured text data.
Use case
Text data often contain rich relationships and insights used for various analytics, recommendation engines, or knowledge management applications.
By coupling Diffbot's NLP API
with Neo4j
, a graph database, you can create powerful, dynamic graph structures based on the information extracted from text. These graph structures are fully queryable and can be integrated into various applications.
This combination allows for use cases such as:
- Building knowledge graphs (like Diffbot's Knowledge Graph) from textual documents, websites, or social media feeds.
- Generating recommendations based on semantic relationships in the data.
- Creating advanced search features that understand the relationships between entities.
- Building analytics dashboards that allow users to explore the hidden relationships in data.
Overview
LangChain provides tools to interact with Graph Databases:
Construct knowledge graphs from text
using graph transformer and store integrationsQuery a graph database
using chains for query creation and executionInteract with a graph database
using agents for robust and flexible querying
Setting up
First, get required packages and set environment variables:
%pip install --upgrade --quiet langchain langchain-experimental langchain-openai neo4j wikipedia
Diffbot NLP API
Diffbot's NLP API
is a tool for extracting entities, relationships, and semantic context from unstructured text data.
This extracted information can be used to construct a knowledge graph.
To use the API, you'll need to obtain a free API token from Diffbot.
from langchain_experimental.graph_transformers.diffbot import DiffbotGraphTransformer
diffbot_api_token = "DIFFBOT_API_TOKEN"
diffbot_nlp = DiffbotGraphTransformer(diffbot_api_token=diffbot_api_token)
This code fetches Wikipedia articles about "Warren Buffett" and then uses DiffbotGraphTransformer
to extract entities and relationships.
The DiffbotGraphTransformer
outputs a structured data GraphDocument
, which can be used to populate a graph database.
Note that text chunking is avoided due to Diffbot's character limit per API request.
from langchain_community.document_loaders import WikipediaLoader
query = "Warren Buffett"
raw_documents = WikipediaLoader(query=query).load()
graph_documents = diffbot_nlp.convert_to_graph_documents(raw_documents)
Loading the data into a knowledge graph
You will need to have a running Neo4j instance. One option is to create a free Neo4j database instance in their Aura cloud service. You can also run the database locally using the Neo4j Desktop application, or running a docker container. You can run a local docker container by running the executing the following script:
docker run \
--name neo4j \
-p 7474:7474 -p 7687:7687 \
-d \
-e NEO4J_AUTH=neo4j/pleaseletmein \
-e NEO4J_PLUGINS=\[\"apoc\"\] \
neo4j:latest
If you are using the docker container, you need to wait a couple of second for the database to start.
from langchain_community.graphs import Neo4jGraph
url = "bolt://localhost:7687"
username = "neo4j"
password = "pleaseletmein"
graph = Neo4jGraph(url=url, username=username, password=password)
The GraphDocuments
can be loaded into a knowledge graph using the add_graph_documents
method.
graph.add_graph_documents(graph_documents)
Refresh graph schema information
If the schema of database changes, you can refresh the schema information needed to generate Cypher statements
graph.refresh_schema()
Querying the graph
We can now use the graph cypher QA chain to ask question of the graph. It is advisable to use gpt-4 to construct Cypher queries to get the best experience.
from langchain.chains import GraphCypherQAChain
from langchain_openai import ChatOpenAI
chain = GraphCypherQAChain.from_llm(
cypher_llm=ChatOpenAI(temperature=0, model_name="gpt-4"),
qa_llm=ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo"),
graph=graph,
verbose=True,
)
chain.run("Which university did Warren Buffett attend?")
[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (p:Person {name: "Warren Buffett"})-[:EDUCATED_AT]->(o:Organization)
RETURN o.name[0m
Full Context:
[32;1m[1;3m[{'o.name': 'New York Institute of Finance'}, {'o.name': 'Alice Deal Junior High School'}, {'o.name': 'Woodrow Wilson High School'}, {'o.name': 'University of Nebraska'}][0m
[1m> Finished chain.[0m
'Warren Buffett attended the University of Nebraska.'
chain.run("Who is or was working at Berkshire Hathaway?")
[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (p:Person)-[r:EMPLOYEE_OR_MEMBER_OF]->(o:Organization) WHERE o.name = 'Berkshire Hathaway' RETURN p.name[0m
Full Context:
[32;1m[1;3m[{'p.name': 'Charlie Munger'}, {'p.name': 'Oliver Chace'}, {'p.name': 'Howard Buffett'}, {'p.name': 'Howard'}, {'p.name': 'Susan Buffett'}, {'p.name': 'Warren Buffett'}][0m
[1m> Finished chain.[0m
'Charlie Munger, Oliver Chace, Howard Buffett, Susan Buffett, and Warren Buffett are or were working at Berkshire Hathaway.'