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

# Vectors

> Create embeddings with the Pawa AI Python SDK.

`client.vectors.create(...)` maps to [`POST /vectors/embedding`](/api-reference/endpoint/vectors/embeddings).

## Create embeddings

```python theme={null}
from pawa_ai import PawaAI

client = PawaAI()

response = client.vectors.create(
    model="pawa-embeddings-v1-20241001",
    sentences=["Embed this sentence.", "And this one too."],
    lang="multi",
)

print(response.success)
print(len(response.embeddings))
print(len(response.embeddings[0]))  # vector dimensions
```

You can also pass `input=` instead of `sentences=`:

```python theme={null}
response = client.vectors.create(
    model="pawa-embeddings-v1-20241001",
    input=["Habari", "Karibu"],
    lang="sw",
)
```

### Raw JSON

```python theme={null}
payload = client.vectors.create(
    sentences=["hello"],
    raw=True,
)
print(payload)
```

`client.vectors.embeddings(...)` is an alias for `create`.