langchain/docs/extras/integrations/providers/pg_embedding.mdx
Leonid Ganeline e1f4f9ac3e
docs: integrations/providers (#9631)
Added missed pages for `integrations/providers` from `vectorstores`.
Updated several `vectorstores` notebooks.
2023-08-22 20:28:11 -07:00

25 lines
560 B
Plaintext

# Postgres Embedding
> [pg_embedding](https://github.com/neondatabase/pg_embedding) is an open-source package for
> vector similarity search using `Postgres` and the `Hierarchical Navigable Small Worlds`
> algorithm for approximate nearest neighbor search.
## Installation and Setup
We need to install several python packages.
```bash
pip install openai
pip install psycopg2-binary
pip install tiktoken
```
## Vector Store
See a [usage example](/docs/integrations/vectorstores/pgembedding).
```python
from langchain.vectorstores import PGEmbedding
```