> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cognee.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Triplet Embeddings
> Index graph triplets as embeddings to enable TRIPLET_COMPLETION search
## 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](/getting-started/quickstart) to understand basic operations
* Ensure you have [LLM Providers](/setup-configuration/llm-providers) configured
* Have an existing knowledge graph (add → cognify completed)
## Code in Action
```python theme={null}
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](/setup-configuration/llm-providers).
* **Permission errors** — the user must have write access to the target dataset. See [Permissions](/core-concepts/multi-user-mode/permissions-system/datasets).
Understand how memify pipelines work
Run the default coding-rules pipeline
Query the enriched graph with specialized search types