Skip to main content

​
When to use this

You need SearchType.TRIPLET_COMPLETION to return results. This search type matches queries against text representations of graph triplets (source → relationship → target). The create_triplet_embeddings pipeline creates these embeddings. Before you start:
  • Complete Quickstart to understand basic operations
  • Ensure you have LLM Providers configured
  • Have an existing knowledge graph (add → cognify completed)

​
Code in Action

import asyncio
import cognee
from cognee import SearchType
from cognee.memify_pipelines.create_triplet_embeddings import create_triplet_embeddings
from cognee.modules.users.methods import get_default_user

async def main():
    await cognee.add(
        ["GraphRAG combines vector search with graph traversal for better context."],
        dataset_name="triplet_demo",
    )
    await cognee.cognify(datasets=["triplet_demo"])

    user = await get_default_user()
    await create_triplet_embeddings(user=user, dataset="triplet_demo")

    results = await cognee.search(
        query_type=SearchType.TRIPLET_COMPLETION,
        query_text="How does GraphRAG work?",
    )
    for result in results:
        print(result)

asyncio.run(main())

​
What Just Happened

  1. Add + Cognify — builds a knowledge graph with entities and relationships from your text.
  2. get_default_user() — retrieves the authenticated user. This pipeline requires a User object with write access to the dataset.
  3. create_triplet_embeddings(user, dataset) — iterates over all graph triplets, converts each to a text representation, and indexes them in the vector DB.
  4. Search with TRIPLET_COMPLETION — queries the new Triplet_text collection by semantic similarity.

​
What Changed in Your Graph

  • The Triplet_text collection is populated in the vector DB. Each entry is a text representation of a graph triplet (source → relationship → target).
  • SearchType.TRIPLET_COMPLETION queries now return results by matching your query against these triplet embeddings.
  • user (User, required) — authenticated user with write access. Obtain via await get_default_user().
  • dataset (str, default: "main_dataset") — the dataset whose graph triplets to index.
  • run_in_background (bool, default: False) — run asynchronously and return immediately.
  • triplets_batch_size (int, default: 100) — how many triplets to index per batch. Lower values use less memory; higher values are faster.
Two tasks run in sequence:
  1. get_triplet_datapoints — iterates over graph triplets and yields Triplet objects with embeddable text.
  2. index_data_points — indexes each triplet in the vector DB under the Triplet_text collection.
  • Empty results from TRIPLET_COMPLETION — ensure the graph has been built (cognify completed) and that create_triplet_embeddings finished without errors.
  • Error: no graph data found — run cognee.add() and cognee.cognify() before calling this pipeline.
  • LLM errors — verify that your LLM provider is configured. See LLM Providers.
  • Permission errors — the user must have write access to the target dataset. See Permissions.

Memify Concept

Understand how memify pipelines work

Memify Quickstart

Run the default coding-rules pipeline

Search

Query the enriched graph with specialized search types