> For the complete documentation index, see [llms.txt](https://docs.unitlab.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.unitlab.ai/api-sdk-cli/sdks/upsert-and-search-vectors.md).

# Upsert and search vectors

{% hint style="info" %}
**Outcome:** Upsert asset- or frame-level vectors in batches and run scoped nearest-neighbor search.
{% endhint %}

```python
space.upsert("ASSET_ID", [0.1, 0.2, 0.3], frame_index=12)

space.upsert_many([
    {"asset_id": "ASSET_A", "vector": [0.1, 0.2, 0.3]},
    {"asset_id": "ASSET_B", "frame_index": 4, "vector": [0.3, 0.2, 0.1]},
])

results = space.search(
    [0.1, 0.2, 0.3],
    limit=25,
    project_id="PROJECT_ID",
    level="frame",
)
```

Every vector must match the space dimension. `level` distinguishes compatible search granularity; `project_id` scopes results where supported. Preserve the model, preprocessing, normalization, and source version outside the raw vector so the index remains interpretable.

### Operating contract

| Concern           | Required behavior                                                                |
| ----------------- | -------------------------------------------------------------------------------- |
| Execution surface | Pinned `unitlab==3.0.0` application environment on Python 3.10+.                 |
| Identity          | Least-privilege API key supplied through approved configuration.                 |
| Target resolution | Stable resource IDs and an explicitly bounded target set.                        |
| Success evidence  | Typed return fields, server-side state, and downstream acceptance of the result. |

### Failure and recovery boundary

| Condition                                       | Response                                                                                                     |
| ----------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
| Authentication or authorization fails           | Stop, correct the service identity or access model, rotate exposed credentials, and rerun a read-only check. |
| Validation or entitlement rejects the operation | Correct the input or entitlement; do not retry an unchanged request.                                         |
| A request times out                             | Inspect remote state before repeating a mutation because the server may have accepted it.                    |
| Asynchronous processing exceeds its deadline    | Preserve the Batch Queue or release ID, continue bounded monitoring, and inspect item-level failures.        |
| Only part of a batch succeeds                   | Keep successful identifiers, isolate failed rows, and retry only the corrected subset.                       |

{% hint style="warning" %}
Pin and test the production SDK version. Use stable IDs, keep secrets out of logs and command history, and record the correlation ID, target IDs, counts, final state, and redacted error details for material state changes.
{% endhint %}