mirror of
https://github.com/langchain-ai/langchain.git
synced 2026-10-15 14:19:23 +03:00
38 lines
1011 B
Plaintext
38 lines
1011 B
Plaintext
# DocArray
|
|
|
|
> [DocArray](https://docarray.jina.ai/) is a library for nested, unstructured, multimodal data in transit,
|
|
> including text, image, audio, video, 3D mesh, etc. It allows deep-learning engineers to efficiently process,
|
|
> embed, search, recommend, store, and transfer multimodal data with a Pythonic API.
|
|
|
|
|
|
## Installation and Setup
|
|
|
|
We need to install `docarray` python package.
|
|
|
|
```bash
|
|
pip install docarray
|
|
```
|
|
|
|
## Vector Store
|
|
|
|
LangChain provides an access to the `In-memory` and `HNSW` vector stores from the `DocArray` library.
|
|
|
|
See a [usage example](/docs/integrations/vectorstores/docarray_hnsw).
|
|
|
|
```python
|
|
from langchain_community.vectorstores import DocArrayHnswSearch
|
|
```
|
|
See a [usage example](/docs/integrations/vectorstores/docarray_in_memory).
|
|
|
|
```python
|
|
from langchain_community.vectorstores DocArrayInMemorySearch
|
|
```
|
|
|
|
## Retriever
|
|
|
|
See a [usage example](/docs/integrations/retrievers/docarray_retriever).
|
|
|
|
```python
|
|
from langchain_community.retrievers import DocArrayRetriever
|
|
```
|