# Python quickstart

This section contains information about different embedding models you can use with SurrealDB.

SurrealDB offers comprehensive support for vector embeddings, enabling powerful semantic search and machine learning capabilities across your data. Through integrations with leading embedding providers, you can easily store, index and query high-dimensional vectors alongside your regular data.

**LangChain**

More details and providers in [LangChain Embedding models](https://python.langchain.com/docs/integrations/text_embedding/) documentation.

**Ollama**

## Ollama

```python
from langchain_ollama import OllamaEmbeddings

vector_store = SurrealDBVectorStore(
    OllamaEmbeddings(model="all-minilm:22m"),
    conn
)
```

More [Ollama embedding models](https://ollama.com/search?c=embedding) in their documentation.

**OpenAI**

## OpenAI

Requires `OPENAI_API_KEY` environment variable.

```python
from langchain_openai import OpenAIEmbeddings

vector_store = SurrealDBVectorStore(
    OpenAIEmbeddings(model="text-embedding-3-large"),
    conn
)
```

**Mistral**

## Mistral

Requires `MISTRALAI_API_KEY` environment variable.

```python
from langchain_mistralai import MistralAIEmbeddings

vector_store = SurrealDBVectorStore(
    MistralAIEmbeddings(model="mistral-embed"),
    conn
)
```

**SentenceTransformer**

## SentenceTransformer

```python
from langchain_huggingface import HuggingFaceEmbeddings

vector_store = SurrealDBVectorStore(
    HuggingFaceEmbeddings(
        model_name="sentence-transformers/all-MiniLM-L6-v2"
    ),
    conn
)
```

More [SentenceTransformer models](https://www.sbert.net/docs/sentence_transformer/pretrained_models.html) in their documentation.

**AWS Bedrock**

## AWS Bedrock

```python
from langchain_aws import BedrockEmbeddings

vector_store = SurrealDBVectorStore(
    BedrockEmbeddings(model_id="amazon.titan-embed-text-v2:0"),
    conn
)
```

**Gemini**

## Gemini

Requires `GOOGLE_API_KEY` environment variable.

```python
from langchain_google_genai import GoogleGenerativeAIEmbeddings

vector_store = SurrealDBVectorStore(
    GoogleGenerativeAIEmbeddings(model="models/embedding-001"),
    conn
)
```

<br />

Then, to query the vector store using similarity search:

```python
doc1 = Document(
    page_content="SurrealDB is the ultimate multi-model database for AI applications",
    metadata={"key": "sdb"},
)
doc2 = Document(
    page_content="Surrealism is an artistic and cultural movement that emerged in the early 20th century",
    metadata={"key": "surrealism"},
)
vector_store.add_documents(documents=[doc1, doc2], ids=["1", "2"])

results = vector_store.similarity_search_with_score(query=q, k=2)
for doc, score in results:
    print(f"• [{score:.0%}]: {doc.page_content}")
top_match = results[0][0]
```

Find an example in [Minimal LangChain chatbot example with vector and graph](/blog/minimal-langchain-chatbot-example-with-vector-and-graph).

**Vanilla**

**Ollama**

## Ollama

```python
import ollama

embedding = ollama.embed(model="all-minilm:22m", input=text)
conn.create("documents", { "content": text, "embedding": embedding })
```

More [Ollama embedding models](https://ollama.com/search?c=embedding) in their documentation.

**OpenAI**

## OpenAI

```python
from openai import OpenAI
client = OpenAI()

text = "Your text string"
response = client.embeddings.create(
    input=text,
    model="text-embedding-3-small"
)

conn.create("documents", { "content": text, "embedding": response.data[0].embedding })
```

More info in [OpenAI embeddings](https://platform.openai.com/docs/guides/embeddings?lang=python) documentation.

**Sentence Transformers**

## Sentence Transformers

```python
from sentence_transformers import SentenceTransformer

st = SentenceTransformer("all-MiniLM-L6-v2")
embedding = st.encode(text).tolist()
conn.create("documents", { "content": text, "embedding": embedding })
```

More [SentenceTransformer models](https://www.sbert.net/docs/sentence_transformer/pretrained_models.html) in their documentation.

To query the vector store using similarity search:

```python
k = 5
query_embedding = st.encode("this is your query text")
res = conn.query(
    f"""
    SELECT
        *,
        vector::distance::knn() AS dist
    FROM documents
    WHERE embedding <|{k}|> $vector;
    """,
    {
        "vector": query_embedding.tolist(),
    },
)
```

This requires an index to be created beforehand. Refer to the [vector search cheat sheet](/docs/learn/data-models/vector-search/vector-indexes.md#vector-search-cheat-sheet).

<br />

Examples above assume you have a DB connection like this:

```python
conn = Surreal("localhost")
conn.signin({"username": "root", "password": "secret"})
conn.use("test_ns", "test_db")
```