What do knowledge graphs buy you before the first query?

The question is whether structure is worth precomputing

A vector index asks which chunks are close to a query in embedding space. A graph index also asks which entities recur, how they are connected, which groups form, and what evidence produced each connection.

That distinction matters for questions such as “What are the major positions across this archive?”, “Which organisations bridge otherwise separate programs?”, or “Where do accounts of the same event conflict?” No single paragraph is likely to answer them. Microsoft's original GraphRAG paper describes this as query-focused summarization over a whole corpus: a task where retrieving a handful of similar chunks is structurally insufficient.

The index converts prose into six inspectable layers

Standard GraphRAG uses a language model for extraction and summarization, then graph algorithms for community detection. The important point is not the rendered constellation. It is the sequence of intermediate tables that turns source passages into a hierarchy of evidence and interpretation.

1. 01

   Chunk the corpus

   Documents become overlapping text units with stable source links.

   The system can return from an answer to the exact passage that supplied it.

2. 02

   Extract entities

   A model identifies recurring people, organisations, places, events, and domain objects.

   Mentions that use different wording can be assembled around one entity.

3. 03

   Extract relationships

   The model describes how entity pairs are connected inside each text unit.

   Retrieval can follow a chain of evidence instead of relying only on semantic similarity.

4. 04

   Consolidate descriptions

   Repeated observations of an entity or relationship are summarized across the corpus.

   The index carries a corpus-level view while retaining links to its observations.

5. 05

   Detect communities

   Leiden clustering partitions the graph into densely connected groups at multiple levels.

   The corpus gains a navigable structure that did not exist in the source folder.

6. 06

   Write community reports

   A model summarizes the entities, relationships, and claims inside each community.

   Global questions can be answered over prepared maps of the corpus rather than a few nearest chunks.

The graph is inferred, not discovered as ground truth. Entity extraction, relationship descriptions, and community reports all remain model outputs that must be traceable to source text.

Precomputation creates different ways to ask

GraphRAG keeps ordinary vector retrieval as a baseline, then adds three graph-aware query strategies. Local search gathers an entity's graph neighbourhood and source text. Global search runs map-reduce over community reports. DRIFT uses community information to broaden the starting point of a local investigation and generate follow-up questions.

The intermediate artifacts are an observability system

A final answer hides where an indexing error entered the pipeline. An inspectable graph makes each transformation visible. If a community makes no sense, the operator can move backward: inspect its member entities, inspect their relationships, then open the text units that caused those edges.

This does not make the model correct. It makes errors diagnosable. The same principle applies to operations: workflow progress, provider errors, cache hits, artifact counts, and source provenance are part of the product because they distinguish a sparse corpus from a failed extraction job.

Local and cloud builds exchange time, cost, privacy, and model quality

Graph construction is dominated by repeated completion calls: extraction per text unit, consolidation across repeated entities, and report generation per community. Embeddings add another pass. A local Ollama build pays with workstation time and memory but keeps document content on the machine. A cloud build pays per token and sends text to the configured provider, but can run more requests concurrently and use a stronger model.

A graph can make model error look structural

The main risk is error propagation. A missed alias splits one actor into two nodes. A vague relationship produces a misleading edge. Those errors alter community detection; the altered community then shapes its report and every global query that reads it. More preprocessing therefore creates more query capability and more places to audit.

GraphRAG Workbench makes the index operable

The open-source workbench wraps Microsoft GraphRAG 3.1 in a local application. PDFs become source-linked text units; the graph populates as artifacts are produced; entities, relationships, communities, and terminal output remain inspectable. The Builder can run against local Ollama models or a configured cloud provider without editing environment files.

LOCAL / OLLAMA
private · no token bill · workstation time

CLOUD / OPENAI
faster · stronger extraction · provider cost

ONE CORPUS → SAME ARTIFACT MODEL → INSPECTABLE GRAPH