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

# embed-english-light-v3.0

> Cohere's embed-english-light-v3.0 makes 384-dimension English text embeddings. Generate vectors with Cohere's API, then upsert them to a Pinecone index.

[Back to all models](https://docs.pinecone.io/models/overview.md)

![Cohere](https://cdn.sanity.io/images/vr8gru94/production/33b1cb253308f74fc83248746b7370a89b3c2c05-250x250.svg)

# embed-english-light-v3.0

Cohere

Bring your own vectors

Specifications

<dl />

## When to use it

Ideal for easy to use text embeddings where short queries are expected to return medium-length passages of text (1-2 paragraphs). Performance is close to full size Cohere-embed-english-v3.0 model while outputting lower-dimensional embeddings for vector storage savings.

## Quickstart

### Installation

```python theme={null}
!pip install -qU cohere==4.34 pinecone
```

### Create index

```python theme={null}
from pinecone import Pinecone, ServerlessSpec

pc = Pinecone(api_key="API_KEY")

# Create Index
index_name = "cohere-embed-english-light-v3"

if not pc.has_index(index_name):
    pc.create_index(
        name=index_name,
        dimension=384,
        metric="cosine",
        spec=ServerlessSpec(
            cloud='aws',
            region='us-east-1'
        )
    )

index = pc.Index(index_name)
```

### Embed & upsert

```python theme={null}
# Embed data
data = [
    {"id": "vec1", "text": "Apple is a popular fruit known for its sweetness and crisp texture."},
    {"id": "vec2", "text": "The tech company Apple is known for its innovative products like the iPhone."},
    {"id": "vec3", "text": "Many people enjoy eating apples as a healthy snack."},
    {"id": "vec4", "text": "Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces."},
    {"id": "vec5", "text": "An apple a day keeps the doctor away, as the saying goes."},
]

import cohere

co = cohere.Client("COHERE_API_KEY")


def embed(docs: list[str], input_type: str) -> list[list[float]]:
    doc_embeds = co.embed(
            docs,
        input_type=input_type,
        model="embed-english-light-v3.0"
    )
    return doc_embeds.embeddings

# when encoding documents / passages
embeddings = embed([d["text"] for d in data] , input_type="search_document")


vectors = []
for d, e in zip(data, embeddings):
    vectors.append({
        "id": d['id'],
        "values": e,
        "metadata": {'text': d['text']}
    })

index.upsert(
    vectors=vectors,
    namespace="ns1"
)
```

### Query

```python theme={null}
query = "Tell me about the tech company known as Apple"

# when encoding a query
x = embed([query], input_type="search_query")

results = index.query(
    namespace="ns1",
    vector=x[0],
    top_k=3,
    include_values=False,
    include_metadata=True
)

print(results)
```

## Good to know

You must set `input_type="search_document"` when you embed passages or documents, and `input_type="search_query"` when you embed queries. For an example, see the [Cohere retrieval notebook](https://github.com/pinecone-io/examples/blob/master/learn/search/semantic-search/2311-embedding-examples/retrieval-perf-cohere.ipynb).
