> ## Documentation Index
> Fetch the complete documentation index at: https://nvd-54.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Diffbot 集成

> 使用 LangChain Python 集成 Diffbot。

> [Diffbot](https://docs.diffbot.com/docs/getting-started-with-diffbot) is a suite of ML-based products that make it easy to structure web data.
>
> Diffbot's [Natural Language Processing API](https://www.diffbot.com/products/natural-language/) allows for the extraction of entities, relationships, and semantic meaning from unstructured text data.
> [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/v0.3/docs/docs/integrations/graphs/diffbot.ipynb)

## 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](https://www.diffbot.com/products/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.

## 概述

LangChain provides tools to interact with Graph Databases:

1. `Construct knowledge graphs from text` using graph transformer and store integrations
2. `Query a graph database` using chains for query creation and execution
3. `Interact with a graph database` using agents for robust and flexible querying

## 设置

First, get required packages and set environment variables:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install -qU  langchain langchain-experimental langchain-openai langchain-neo4j 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](https://app.diffbot.com/get-started/).

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_experimental.graph_transformers.diffbot import DiffbotGraphTransformer

diffbot_api_key = "DIFFBOT_KEY"
diffbot_nlp = DiffbotGraphTransformer(diffbot_api_key=diffbot_api_key)
```

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.
请注意 text chunking is avoided due to Diffbot's [character limit per API request](https://docs.diffbot.com/reference/introduction-to-natural-language-api).

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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

你需要一个正在运行的 Neo4j instance. One option is to create a [free Neo4j database instance in their Aura cloud service](https://neo4j.com/cloud/platform/aura-graph-database/). 你也可以使用以下方式在本地运行数据库： [Neo4j Desktop application](https://neo4j.com/download/), or running a docker container. 你可以通过执行以下脚本运行本地 docker 容器：

```
docker run \
    --name neo4j \
    -p 7474:7474 -p 7687:7687 \
    -d \
    -e NEO4J_AUTH=neo4j/password \
    -e NEO4J_PLUGINS=\[\"apoc\"\]  \
    neo4j:latest
```

如果使用 docker 容器，你需要等待几秒钟让数据库启动。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_neo4j import Neo4jGraph

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

graph = Neo4jGraph(url=url, username=username, password=password)
```

The `GraphDocuments` can be loaded into a knowledge graph using the `add_graph_documents` method.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
graph.add_graph_documents(graph_documents)
```

## 刷新图 Schema 信息

If the schema of database changes, you can refresh the schema information needed to generate Cypher statements

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
graph.refresh_schema()
```

## 查询图

我们现在可以使用 graph cypher QA chain 来查询图. It is advisable to use **gpt-4** to construct Cypher queries to get the best experience.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_neo4j 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,
    allow_dangerous_requests=True,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain.run("Which university did Warren Buffett attend?")
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (p:Person {name: "Warren Buffett"})-[:EDUCATED_AT]->(o:Organization)
RETURN o.name
Full Context:
[{'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'}]

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
'Warren Buffett attended the University of Nebraska.'
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain.run("Who is or was working at Berkshire Hathaway?")
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (p:Person)-[r:EMPLOYEE_OR_MEMBER_OF]->(o:Organization) WHERE o.name = 'Berkshire Hathaway' RETURN p.name
Full Context:
[{'p.name': 'Charlie Munger'}, {'p.name': 'Oliver Chace'}, {'p.name': 'Howard Buffett'}, {'p.name': 'Howard'}, {'p.name': 'Susan Buffett'}, {'p.name': 'Warren Buffett'}]

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
'Charlie Munger, Oliver Chace, Howard Buffett, Susan Buffett, and Warren Buffett are or were working at Berkshire Hathaway.'
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
```

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/graphs/diffbot.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>