> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-opensw-1783454697-4d4e2b4.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# PGVectorStore integration
> Integrate with the PGVectorStore using LangChain JavaScript.
**Compatibility**: Only available on Node.js.
To enable vector search in generic PostgreSQL databases, LangChain.js supports using the [`pgvector`](https://github.com/pgvector/pgvector) Postgres extension.
This guide provides a quick overview for getting started with PGVector [vector stores](/oss/javascript/integrations/vectorstores). For detailed documentation of all `PGVectorStore` features and configurations head to the [API reference](https://reference.langchain.com/javascript/langchain-pgvector/PGVectorStore).
## PGVectorStore vs PGVector: Which one to use?
LangChain has two Postgres vector store integrations. Here's how to choose the right one:
| Feature | PGVector (Legacy) | PGVectorStore (Modern) |
| ------------- | ------------------------ | ---------------------------------------------------------- |
| Package | `langchain-community` | `langchain-postgres` (Python) / `@langchain/pgvector` (JS) |
| Maintenance | Community-maintained | Official Partner Package |
| Connection | Simple connection string | `PGEngine` (better connection pooling) |
| Search Types | Standard Vector Search | Hybrid Search (Vector + BM25) |
| Async Support | Limited | Full Native Async |
| Schema | Fixed table structure | Customizable columns and schemas |
**Use `PGVectorStore` (Modern—recommended) when:**
* Starting any new project
* You need Hybrid Search (vector + keyword combined)
* You want better performance via connection pooling
* You are building async applications (e.g., FastAPI, async Node.js)
**Use `PGVector` (Legacy) only when:**
* Maintaining an existing codebase that already uses it
* Following an older tutorial that has not been updated yet
For all new projects, we recommend using `PGVectorStore` from `langchain-postgres` (Python) or `@langchain/community` (JavaScript).
***
## Overview
### Integration details
| Class | Package | [PY support](https://python.langchain.com/docs/integrations/vectorstores/pgvector/) | Downloads | Version |
| :--------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------- | :---------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------: |
| [`PGVectorStore`](https://reference.langchain.com/javascript/langchain-pgvector/PGVectorStore) | [`@langchain/pgvector`](https://www.npmjs.com/package/@langchain/pgvector) | âś… |  |  |
## Setup
To use PGVector vector stores, set up a Postgres instance with the [`pgvector`](https://github.com/pgvector/pgvector) extension enabled, then install `@langchain/pgvector`, the [`pg`](https://www.npmjs.com/package/pg) driver, and `@langchain/core`.
This guide uses [OpenAI embeddings](/oss/javascript/integrations/embeddings/openai) as an example. You can use [other supported embeddings models](/oss/javascript/integrations/embeddings) instead.
```bash npm theme={null}
npm install @langchain/pgvector @langchain/openai @langchain/core pg
```
```bash yarn theme={null}
yarn add @langchain/pgvector @langchain/openai @langchain/core pg
```
```bash pnpm theme={null}
pnpm add @langchain/pgvector @langchain/openai @langchain/core pg
```
### Setting up an instance
There are many ways to connect to Postgres depending on how you've set up your instance. Here's one example of a local setup using a prebuilt Docker image provided by the `pgvector` team.
Create a file with the below content named docker-compose.yml:
```yaml theme={null}
# Run this command to start the database:
# docker compose up
services:
db:
hostname: 127.0.0.1
image: pgvector/pgvector:pg16
ports:
- 5432:5432
restart: always
environment:
- POSTGRES_DB=api
- POSTGRES_USER=myuser
- POSTGRES_PASSWORD=ChangeMe
```
And then in the same directory, run `docker compose up` to start the container.
You can find more information on how to setup pgvector in the [official repository](https://github.com/pgvector/pgvector/).
### Credentials
To connect to your Postgres instance, you'll need corresponding credentials. For a full list of supported options, see the [`node-postgres` docs](https://node-postgres.com/apis/client).
If you are using OpenAI embeddings for this guide, you'll need to set your OpenAI key as well:
```typescript theme={null}
process.env.OPENAI_API_KEY = "YOUR_API_KEY";
```
If you want to get automated tracing of your model calls you can also set your [LangSmith](/langsmith/observability) API key by uncommenting below:
```typescript theme={null}
// process.env.LANGSMITH_TRACING="true"
// process.env.LANGSMITH_API_KEY="your-api-key"
```
## Instantiation
To instantiate the vector store, call the `.initialize()` static method. This will automatically check for the presence of a table, given by `tableName` in the passed `config`. If it is not there, it will create it with the required columns.
**Security**: User-generated data such as usernames should not be used as input for table and column names.
**This may lead to SQL Injection!**
```typescript theme={null}
import { PGVectorStore } from "@langchain/pgvector";
import type { DistanceStrategy } from "@langchain/pgvector";
import { OpenAIEmbeddings } from "@langchain/openai";
import type { PoolConfig } from "pg";
const embeddings = new OpenAIEmbeddings({
model: "text-embedding-3-small",
});
// Sample config
const config = {
postgresConnectionOptions: {
type: "postgres",
host: "127.0.0.1",
port: 5433,
user: "myuser",
password: "ChangeMe",
database: "api",
} as PoolConfig,
tableName: "testlangchainjs",
columns: {
idColumnName: "id",
vectorColumnName: "vector",
contentColumnName: "content",
metadataColumnName: "metadata",
},
// supported distance strategies: cosine (default), innerProduct, or euclidean
distanceStrategy: "cosine" as DistanceStrategy,
};
const vectorStore = await PGVectorStore.initialize(
embeddings,
config
);
```
## Manage vector store
### Add items to vector store
```typescript theme={null}
import type { Document } from "@langchain/core/documents";
const document1: Document = {
pageContent: "The powerhouse of the cell is the mitochondria",
metadata: { source: "https://example.com" }
};
const document2: Document = {
pageContent: "Buildings are made out of brick",
metadata: { source: "https://example.com" }
};
const document3: Document = {
pageContent: "Mitochondria are made out of lipids",
metadata: { source: "https://example.com" }
};
const document4: Document = {
pageContent: "The 2024 Olympics are in Paris",
metadata: { source: "https://example.com" }
}
const documents = [document1, document2, document3, document4];
const ids = [crypto.randomUUID(), crypto.randomUUID(), crypto.randomUUID(), crypto.randomUUID()]
await vectorStore.addDocuments(documents, { ids: ids });
```
### Delete items from vector store
```typescript theme={null}
const id4 = ids[ids.length - 1];
await vectorStore.delete({ ids: [id4] });
```
## Query vector store
Once your vector store has been created and the relevant documents have been added you will most likely wish to query it during the running of your chain or agent.
### Query directly
Performing a simple similarity search can be done as follows:
```typescript theme={null}
const filter = { source: "https://example.com" };
const similaritySearchResults = await vectorStore.similaritySearch("biology", 2, filter);
for (const doc of similaritySearchResults) {
console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}
```
```text theme={null}
* The powerhouse of the cell is the mitochondria [{"source":"https://example.com"}]
* Mitochondria are made out of lipids [{"source":"https://example.com"}]
```
The above filter syntax supports exact match, but the following are also supported:
#### Using the `in` operator
```json theme={null}
{
"field": {
"in": ["value1", "value2"],
}
}
```
#### Using the `notIn` operator
```json theme={null}
{
"field": {
"notIn": ["value1", "value2"],
}
}
```
#### Using the `arrayContains` operator
```json theme={null}
{
"field": {
"arrayContains": ["value1", "value2"],
}
}
```
If you want to execute a similarity search and receive the corresponding scores you can run:
```typescript theme={null}
const similaritySearchWithScoreResults = await vectorStore.similaritySearchWithScore("biology", 2, filter)
for (const [doc, score] of similaritySearchWithScoreResults) {
console.log(`* [SIM=${score.toFixed(3)}] ${doc.pageContent} [${JSON.stringify(doc.metadata)}]`);
}
```
```text theme={null}
* [SIM=0.835] The powerhouse of the cell is the mitochondria [{"source":"https://example.com"}]
* [SIM=0.852] Mitochondria are made out of lipids [{"source":"https://example.com"}]
```
### Query by turning into retriever
You can also transform the vector store into a [retriever](/oss/javascript/langchain/retrieval) for easier usage in your chains.
```typescript theme={null}
const retriever = vectorStore.asRetriever({
// Optional filter
filter: filter,
k: 2,
});
await retriever.invoke("biology");
```
```javascript theme={null}
[
Document {
pageContent: 'The powerhouse of the cell is the mitochondria',
metadata: { source: 'https://example.com' },
id: undefined
},
Document {
pageContent: 'Mitochondria are made out of lipids',
metadata: { source: 'https://example.com' },
id: undefined
}
]
```
### Usage for retrieval-augmented generation
For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
* [Build a RAG app with LangChain](/oss/javascript/langchain/rag).
* [Agentic RAG](/oss/javascript/langgraph/agentic-rag)
* [Retrieval docs](/oss/javascript/langchain/retrieval)
## Advanced: reusing connections
You can reuse connections by creating a pool, then creating new `PGVectorStore` instances directly via the constructor.
Note that you should call `.initialize()` to set up your database at least once to set up your tables properly before using the constructor.
```typescript theme={null}
import { OpenAIEmbeddings } from "@langchain/openai";
import { PGVectorStore } from "@langchain/pgvector";
import pg from "pg";
const reusablePool = new pg.Pool({
host: "127.0.0.1",
port: 5433,
user: "myuser",
password: "ChangeMe",
database: "api",
});
const originalConfig = {
pool: reusablePool,
tableName: "testlangchainjs",
collectionName: "sample",
collectionTableName: "collections",
columns: {
idColumnName: "id",
vectorColumnName: "vector",
contentColumnName: "content",
metadataColumnName: "metadata",
},
};
// Set up the DB.
// Can skip this step if you've already initialized the DB.
// await PGVectorStore.initialize(new OpenAIEmbeddings(), originalConfig);
const pgvectorStore = new PGVectorStore(new OpenAIEmbeddings(), originalConfig);
await pgvectorStore.addDocuments([
{ pageContent: "what's this", metadata: { a: 2 } },
{ pageContent: "Cat drinks milk", metadata: { a: 1 } },
]);
const results = await pgvectorStore.similaritySearch("water", 1);
console.log(results);
/*
[ Document { pageContent: 'Cat drinks milk', metadata: { a: 1 } } ]
*/
const pgvectorStore2 = new PGVectorStore(new OpenAIEmbeddings(), {
pool: reusablePool,
tableName: "testlangchainjs",
collectionTableName: "collections",
collectionName: "some_other_collection",
columns: {
idColumnName: "id",
vectorColumnName: "vector",
contentColumnName: "content",
metadataColumnName: "metadata",
},
});
const results2 = await pgvectorStore2.similaritySearch("water", 1);
console.log(results2);
/*
[]
*/
await reusablePool.end();
```
## Create HNSW index
By default, the extension performs a sequential scan search, with 100% recall. You might consider creating an HNSW index for approximate nearest neighbor (ANN) search to speed up `similaritySearchVectorWithScore` execution time. To create the HNSW index on your vector column, use the `createHnswIndex()` method.
The method parameters include:
* `dimensions`: Defines the number of dimensions in your vector data type, up to 2000. For example, use 1536 for OpenAI's text-embedding-ada-002 and Amazon's amazon.titan-embed-text-v1 models.
* `m?`: The max number of connections per layer (16 by default). Index build time improves with smaller values, while higher values can speed up search queries.
* `efConstruction?`: The size of the dynamic candidate list for constructing the graph (64 by default). A higher value can potentially improve the index quality at the cost of index build time.
* `distanceFunction?`: The distance function name you want to use, is automatically selected based on the distanceStrategy.
For more info, see the [Pgvector GitHub repo](https://github.com/pgvector/pgvector?tab=readme-ov-file#hnsw) and the [HNSW paper from Malkov Yu A. and Yashunin D. A.. 2020. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs](https://arxiv.org/pdf/1603.09320)
```typescript theme={null}
import { OpenAIEmbeddings } from "@langchain/openai";
import { PGVectorStore } from "@langchain/pgvector";
import type { DistanceStrategy } from "@langchain/pgvector";
import type { PoolConfig } from "pg";
const hnswConfig = {
postgresConnectionOptions: {
type: "postgres",
host: "127.0.0.1",
port: 5433,
user: "myuser",
password: "ChangeMe",
database: "api",
} as PoolConfig,
tableName: "testlangchainjs",
columns: {
idColumnName: "id",
vectorColumnName: "vector",
contentColumnName: "content",
metadataColumnName: "metadata",
},
// supported distance strategies: cosine (default), innerProduct, or euclidean
distanceStrategy: "cosine" as DistanceStrategy,
};
const hnswPgVectorStore = await PGVectorStore.initialize(
new OpenAIEmbeddings(),
hnswConfig
);
// create the index
await hnswPgVectorStore.createHnswIndex({
dimensions: 1536,
efConstruction: 64,
m: 16,
});
await hnswPgVectorStore.addDocuments([
{ pageContent: "what's this", metadata: { a: 2, b: ["tag1", "tag2"] } },
{ pageContent: "Cat drinks milk", metadata: { a: 1, b: ["tag2"] } },
]);
const model = new OpenAIEmbeddings();
const query = await model.embedQuery("water");
const hnswResults = await hnswPgVectorStore.similaritySearchVectorWithScore(query, 1);
console.log(hnswResults);
await hnswPgVectorStore.end();
```
## Closing connections
Make sure you close the connection when you are finished to avoid excessive resource consumption:
```typescript theme={null}
await vectorStore.end();
```
***
## API reference
For detailed documentation of all `PGVectorStore` features and configurations head to the [API reference](https://reference.langchain.com/javascript/langchain-pgvector/PGVectorStore).
***
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/javascript/integrations/vectorstores/pgvector.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).