# Ollama

The `OllamaEmbeddings` class uses the `/api/embeddings` route of a locally hosted [Ollama](https://ollama.ai) server to generate embeddings for given texts.

# Setup

Follow [these instructions](https://github.com/jmorganca/ollama) to set up and run a local Ollama instance.

# Usage

Basic usage:

```typescript
import { OllamaEmbeddings } from "langchain/embeddings/ollama";

const embeddings = new OllamaEmbeddings({
  model: "llama2", // default value
  baseUrl: "http://localhost:11434", // default value
});
```

Ollama [model parameters](https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values) are also supported:

```typescript
import { OllamaEmbeddings } from "langchain/embeddings/ollama";

const embeddings = new OllamaEmbeddings({
  model: "llama2", // default value
  baseUrl: "http://localhost:11434", // default value
  requestOptions: {
    useMMap: true, // use_mmap 1
    numThreads: 6, // num_thread 6
    numGpu: 1, // num_gpu 1
  },
});
```

# Example usage:

```typescript
import { OllamaEmbeddings } from "langchain/embeddings/ollama";

const embeddings = new OllamaEmbeddings({
  model: "llama2", // default value
  baseUrl: "http://localhost:11434", // default value
  requestOptions: {
    useMMap: true,
    numThreads: 6,
    numGpu: 1,
  },
});

const documents = ["Hello World!", "Bye Bye"];

const documentEmbeddings = await embeddings.embedDocuments(documents);
```