> ## 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

> `v0.17.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

<Tabs>
  <Tab title="Embedded">
    Install `cyborgdb-core` with the `langchain` extra:

    ```bash theme={null}
    pip install cyborgdb-core[langchain]
    ```
  </Tab>

  <Tab title="Python SDK">
    Install the `cyborgdb` package with the `langchain` extra:

    ```bash theme={null}
    pip install cyborgdb[langchain]
    ```
  </Tab>

  <Tab title="JS/TS">
    Install the `cyborgdb` npm package:

    ```bash theme={null}
    npm install cyborgdb
    ```
  </Tab>
</Tabs>

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

## Import

<Tabs>
  <Tab title="Embedded">
    ```python theme={null}
    from cyborgdb_core.integrations.langchain import CyborgVectorStore
    ```
  </Tab>

  <Tab title="Python SDK">
    ```python theme={null}
    from cyborgdb.integrations.langchain import CyborgVectorStore
    ```
  </Tab>

  <Tab title="JS/TS">
    ```typescript theme={null}
    import { CyborgVectorStore } from 'cyborgdb';
    ```
  </Tab>
</Tabs>

## Key Features

* Full VectorStore API compatibility (`add_texts`, `similarity_search`, etc.)
* Async operations support
* Configurable distance metrics (`cosine`, `euclidean`, `squared_euclidean`)
* Document ID tracking and management
* Max marginal relevance search
* Factory methods (`from_texts`, `from_documents`) for quick setup

## 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()` / `.list_ids()` / `.delete()`
* `.as_retriever()` for use in LangChain chains
* Async variants (`.aadd_texts()`, `.asimilarity_search()`, etc.)
* Reversible document ID tracking
* Configurable distance metric (`cosine`, `euclidean`, `squared_euclidean`)

### `DBConfig` (Embedded only)

Configuration object for defining the location of index data. v0.17 supports `memory`, `rocksdb`, `threadsafememory`, and `s3`. Used only with the Embedded library (`cyborgdb-core`).

## Quick Start

<Tabs>
  <Tab title="Embedded">
    ```python theme={null}
    from cyborgdb_core.integrations.langchain import CyborgVectorStore
    from cyborgdb_core import DBConfig
    from langchain_openai import OpenAIEmbeddings

    store = CyborgVectorStore.from_texts(
        texts=["hello world", "goodbye world"],
        embedding=OpenAIEmbeddings(),
        index_key=CyborgVectorStore.generate_key(save=True),
        api_key="your-api-key",
        index_location=DBConfig("memory"),
        config_location=DBConfig("memory"),
        index_type="ivfsq",
        metric="cosine"
    )

    docs = store.similarity_search("hello")
    ```
  </Tab>

  <Tab title="Python SDK">
    ```python theme={null}
    from cyborgdb.integrations.langchain import CyborgVectorStore

    store = CyborgVectorStore.from_texts(
        texts=["hello world", "goodbye world"],
        embedding="all-MiniLM-L6-v2",
        index_key=CyborgVectorStore.generate_key(save=True),
        api_key="your-api-key",
        base_url="http://localhost:8000",
        index_type="ivfflat",
        metric="cosine"
    )

    docs = store.similarity_search("hello")
    ```
  </Tab>

  <Tab title="JS/TS">
    ```typescript theme={null}
    import { CyborgVectorStore } from 'cyborgdb';
    import { OpenAIEmbeddings } from '@langchain/openai';

    const store = await CyborgVectorStore.fromTexts(
        ["hello world", "goodbye world"],
        [{ source: "greeting" }, { source: "farewell" }],
        new OpenAIEmbeddings(),
        {
            baseUrl: "http://localhost:8000",
            apiKey: "your-api-key",
            indexName: "my_documents",
            indexKey: CyborgVectorStore.generateKey(),
            indexType: "ivfflat",
            metric: "cosine"
        }
    );

    const docs = await store.similaritySearch("hello");
    ```

    <Note>`fromExistingIndex()` is available as a JS/TS-only convenience factory method for connecting to an already-created index without re-adding documents.</Note>
  </Tab>
</Tabs>