> For the complete documentation index, see [llms.txt](https://docs.graphlit.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.graphlit.dev/api-guides/use-cases/specifications/specification-create-embedding.md).

# Create Embedding Model

## User Intent

"I want to configure which embedding model to use for vector (semantic) search"

## Operation

* **SDK Methods**: `createSpecification()`, `updateProject()`
* **GraphQL**: `createSpecification`, `updateProject`

## TypeScript

```typescript
import { Graphlit } from 'graphlit-client';
import { ModelServiceTypes, OpenAiModels, SpecificationTypes } from 'graphlit-client/dist/generated/graphql-types';

const graphlit = new Graphlit();

// 1) Create a text-embedding specification
const spec = await graphlit.createSpecification({
  name: 'OpenAI Embedding 3 Large',
  type: SpecificationTypes.TextEmbedding,
  serviceType: ModelServiceTypes.OpenAi,
  openAI: {
    model: OpenAiModels.Embedding_3Large,
    chunkTokenLimit: 512,
  },
});

// 2) Set it as the project default text embedding strategy
await graphlit.updateProject({
  embeddings: {
    textSpecification: { id: spec.createSpecification.id },
  },
});
```

## Python

```python
from graphlit import Graphlit
from graphlit_api.enums import ModelServiceTypes, OpenAiModels, SpecificationTypes
from graphlit_api.input_types import (
    EmbeddingsStrategyInput,
    EntityReferenceInput,
    OpenAiModelPropertiesInput,
    ProjectUpdateInput,
    SpecificationInput,
)

graphlit = Graphlit()

spec = await graphlit.client.create_specification(
    SpecificationInput(
        name="OpenAI Embedding 3 Large",
        type=SpecificationTypes.TEXT_EMBEDDING,
        service_type=ModelServiceTypes.OPEN_AI,
        open_ai=OpenAiModelPropertiesInput(
            model=OpenAiModels.EMBEDDING_3_LARGE,
            chunk_token_limit=512,
        ),
    )
)

await graphlit.client.update_project(
    ProjectUpdateInput(
        embeddings=EmbeddingsStrategyInput(
            text_specification=EntityReferenceInput(id=spec.create_specification.id)
        )
    )
)
```

## C\#

```csharp
using GraphlitClient;
using System.Net.Http;
using StrawberryShake;

using var httpClient = new HttpClient();
var client = new Graphlit(httpClient);

var spec = await client.Client.CreateSpecification.ExecuteAsync(new SpecificationInput(
    name: "OpenAI Embedding 3 Large",
    type: SpecificationTypes.TextEmbedding,
    serviceType: ModelServiceTypes.OpenAi,
    openAi: new OpenAiModelPropertiesInput(
        model: OpenAiModels.Embedding_3Large,
        chunkTokenLimit: 512
    )
));

await client.Client.UpdateProject.ExecuteAsync(new ProjectUpdateInput(
    embeddings: new EmbeddingsStrategyInput(
        textSpecification: new EntityReferenceInput(spec.Data!.CreateSpecification!.Id)
    )
));
```