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

# CyborgDB - LangChain Integration

> `v0.11.x`

CyborgDB provides a seamless integration with [LangChain](https://www.langchain.com/), enabling developers to leverage encrypted vector search for large language models (LLMs) and RAG pipelines. This integration is implemented via the `CyborgVectorStore` class, which conforms to the `VectorStore` interface from `langchain-core`.

## Installation (Python Client SDK)

To use the LangChain integration with the CyborgDB Python Client SDK, you need to install the `cyborgdb` package with the `langchain` extra:

```bash theme={null}
pip install cyborgdb[langchain]
```

This will install the necessary dependencies for the LangChain integration.

## Installation (Embedded Library)

To install CyborgDB with LangChain support, you must install either `cyborgdb-core` or `cyborgdb-lite` with the `langchain` extra. You can do this using pip:

```bash theme={null}
# For cyborgdb-core
pip install cyborgdb-core[langchain]

# For cyborgdb-lite
pip install cyborgdb-lite[langchain]
```

<Tip>To learn more about the differences between `cyborgdb`, `cyborgdb-core`, and `cyborgdb-lite`, refer to the [Deployment Models Guide](../../intro/deployment-models).</Tip>

## Usage

To use CyborgDB with LangChain, you can import the `CyborgVectorStore` class from the `cyborgdb_core.integrations.langchain` or `cyborgdb_lite.integrations.langchain` module, depending on which version you are using.

```python theme={null}
from cyborgdb.integrations.langchain import CyborgVectorStore
# or
from cyborgdb_core.integrations.langchain import CyborgVectorStore
# or
from cyborgdb_lite.integrations.langchain import CyborgVectorStore
```

## Key Classes

### `CyborgVectorStore`

Implements the LangChain-compatible vector store interface. Supports:

* `.add_texts()` / `.add_documents()`
* `.similarity_search()` / `.similarity_search_with_score()`
* `.max_marginal_relevance_search()`
* `.get_document()` and `.delete()`
* Async variants (`.aadd_texts()`, `.asimilarity_search()`, etc.)
* Reversible document ID tracking
* Configurable distance metric (`cosine`, `euclidean`, `squared_euclidean`)

### `DBConfig`

Configuration object for defining the location of index data (`memory`, `redis`, `postgres`, etc.).

## Usage Example

```python theme={null}
from cyborgdb_core.integrations.langchain import CyborgVectorStore
from cyborgdb_core import DBConfig

store = CyborgVectorStore.from_texts(
    texts=["hello world", "goodbye world"],
    embedding="all-MiniLM-L6-v2",  # sentence-transformer name
    index_key=CyborgVectorStore.generate_key(),
    api_key="your-api-key",
    index_location=DBConfig("memory"),
    config_location=DBConfig("memory"),
    index_type="ivfflat",
    metric="cosine"
)

docs = store.similarity_search("hello")
```