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

# Relationships

> Relationship data model representing edges in the knowledge graph

## Overview

The `Relationship` class represents an edge in the knowledge graph, connecting two entities. Relationships are extracted from documents and describe how entities are related to each other. Each relationship has a source entity, target entity, and optional weight indicating the strength of the connection.

Relationships inherit from the `Identified` base class, which provides `id` and `short_id` fields.

## Schema

### Core fields

<ResponseField name="id" type="string" required>
  Unique identifier for the relationship.
</ResponseField>

<ResponseField name="short_id" type="string | null">
  Human-readable ID used to refer to this relationship in prompts or texts displayed to users.
</ResponseField>

<ResponseField name="source" type="string" required>
  The source entity name. This is the entity from which the relationship originates.
</ResponseField>

<ResponseField name="target" type="string" required>
  The target entity name. This is the entity to which the relationship points.
</ResponseField>

<ResponseField name="weight" type="float" default={1.0}>
  The edge weight indicating the strength or importance of the relationship. Higher values indicate stronger connections.
</ResponseField>

<ResponseField name="description" type="string | null">
  A textual description of the relationship explaining the nature of the connection between source and target entities.
</ResponseField>

### Embeddings

<ResponseField name="description_embedding" type="float[]">
  The semantic embedding vector for the relationship description. Used for similarity search and semantic queries.
</ResponseField>

### Relationships

<ResponseField name="text_unit_ids" type="string[]">
  List of text unit IDs in which the relationship appears. Links the relationship back to its source text chunks.
</ResponseField>

### Metadata

<ResponseField name="rank" type="integer" default={1}>
  Rank of the relationship, used for sorting and prioritization. Higher rank indicates more important relationship. This can be based on centrality or other metrics.
</ResponseField>

<ResponseField name="attributes" type="object">
  Additional attributes associated with the relationship. These attributes are included in search prompts and can contain custom metadata.
</ResponseField>

## Example

```json theme={null}
{
  "id": "r1234567-89ab-cdef-0123-456789abcdef",
  "short_id": "0",
  "source": "Microsoft Corporation",
  "target": "Satya Nadella",
  "weight": 0.95,
  "description": "Satya Nadella is the CEO of Microsoft Corporation",
  "description_embedding": [0.123, -0.456, 0.789, ...],
  "text_unit_ids": ["t1", "t2"],
  "rank": 5,
  "attributes": {
    "relationship_type": "leadership",
    "start_date": "2014"
  }
}
```

## Creating from dictionary

The `Relationship` class provides a `from_dict()` class method to create instances from dictionary data:

```python theme={null}
relationship = Relationship.from_dict({
    "id": "r1234567-89ab-cdef-0123-456789abcdef",
    "source": "Microsoft Corporation",
    "target": "Satya Nadella",
    "weight": 0.95,
    "description": "Satya Nadella is the CEO of Microsoft Corporation",
    "rank": 5,
    "text_unit_ids": ["t1", "t2"],
    "attributes": {"relationship_type": "leadership"}
})
```

<Expandable title="Custom key mapping">
  The `from_dict()` method accepts custom key names for flexible data import:

  * `id_key`: Key for the relationship ID (default: "id")
  * `short_id_key`: Key for the human-readable ID (default: "human\_readable\_id")
  * `source_key`: Key for the source entity (default: "source")
  * `target_key`: Key for the target entity (default: "target")
  * `description_key`: Key for the description (default: "description")
  * `rank_key`: Key for the rank value (default: "rank")
  * `weight_key`: Key for the edge weight (default: "weight")
  * `text_unit_ids_key`: Key for text unit IDs (default: "text\_unit\_ids")
  * `attributes_key`: Key for additional attributes (default: "attributes")
</Expandable>

## Use cases

Relationships are used throughout GraphRAG for:

* **Graph traversal**: Following connections between entities during search
* **Community detection**: Identifying clusters of related entities
* **Importance ranking**: Using edge weights to prioritize relevant information
* **Context retrieval**: Accessing source text through text\_unit\_ids