JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(mem0-ts): support pgvector connection strings and ssl (#5789)

Browse Source
This commit is contained in:
Rod Boev
2026-06-25 02:27:37 -04:00
committed by GitHub
parent ac296f7534
commit 6bb1d328ad
5 changed files with 279 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/components/vectordbs/dbs/neon.mdx
+35 -37
View File
@@ -21,49 +21,47 @@ from mem0 import Memory
load_dotenv()
config = {
"vector_store": {
"provider": "pgvector",
"config": {
"connection_string": os.environ["DATABASE_URL"],
"collection_name": "memories",
"embedding_model_dims": 1536,
"hnsw": True,
},
},
"vector_store": {
"provider": "pgvector",
"config": {
"connection_string": os.environ["DATABASE_URL"],
"collection_name": "memories",
"embedding_model_dims": 1536,
"hnsw": True,
},
},
}
m = Memory.from_config(config)
messages = [
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."},
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."},
]
m.add(messages, user_id="alice", metadata={"category": "movies"})
results = m.search(
"What movies should I recommend?",
filters={"user_id": "alice"},
"What movies should I recommend?",
filters={"user_id": "alice"},
)
print(results)
```
````
```typescript TypeScript
import "dotenv/config";
import { Memory } from "mem0ai/oss";
const databaseUrl = new URL(process.env.DATABASE_URL!);
const m = new Memory({
vectorStore: {
provider: "pgvector",
config: {
user: decodeURIComponent(databaseUrl.username),
password: decodeURIComponent(databaseUrl.password),
host: databaseUrl.hostname,
port: Number(databaseUrl.port || 5432),
dbname: databaseUrl.pathname.slice(1) || "neondb",
connectionString: process.env.DATABASE_URL!,
ssl: {
rejectUnauthorized: false,
},
collectionName: "memories",
dimension: 1536,
embeddingModelDims: 1536,
@@ -89,7 +87,8 @@ const results = await m.search("What movies should I recommend?", {
});
console.log(results);
```
````
</CodeGroup>
## SQL Migration
@@ -116,20 +115,19 @@ DATABASE_URL=postgresql://user:password@ep-example.us-east-2.aws.neon.tech/neond
| `sslmode` | PostgreSQL SSL mode. Use `require` for Neon. | Driver default |
</Tab>
<Tab title="TypeScript">
The current Mem0 TypeScript `pgvector` adapter takes individual Postgres fields,
so parse `DATABASE_URL` before creating `Memory`.
Use the Neon `DATABASE_URL` directly with `connectionString`. Set `ssl` if your runtime needs an explicit TLS config object.
| Parameter | Description | Default |
| -------------------- | ---------------------------------------------- | -------------- |
| `connectionString` | Neon Postgres connection string. | Required |
| `ssl` | Optional TLS settings passed directly to `pg`. | Driver default |
| `collectionName` | Name for the vector collection. | `memories` |
| `dimension` | Vector dimension for Mem0 config. | Auto-detected |
| `embeddingModelDims` | Embedding model dimensions for table creation. | Required |
| `hnsw` | Enables HNSW indexing. | `false` |
**TLS note:** `ssl: true` is sufficient for most Neon connections since Neon uses valid certificates. Use `ssl: { rejectUnauthorized: false }` only when connecting through Neon's connection pooler on certain edge runtimes (e.g. Cloudflare Workers) that require it, or when your environment does not trust the Neon CA chain.
| Parameter | Description | Default |
| --- | --- | --- |
| `user` | Database user. | Required |
| `password` | Database password. | Required |
| `host` | Database host. | Required |
| `port` | Database port. | `5432` |
| `dbname` | Database name. | `vector_store` |
| `collectionName` | Name for the vector collection. | `memories` |
| `dimension` | Vector dimension for Mem0 config. | Auto-detected |
| `embeddingModelDims` | Embedding model dimensions for table creation. | Required |
| `hnsw` | Enables HNSW indexing. | `false` |
</Tab>
</Tabs>
docs/components/vectordbs/dbs/pgvector.mdx
+50 -45
View File
@@ -2,6 +2,7 @@
title: "pgvector"
description: "Use pgvector as a vector store in Mem0 for PostgreSQL-based vector similarity search with open-source simplicity."
---
[pgvector](https://github.com/pgvector/pgvector) is an open-source vector similarity search extension for Postgres. After connecting to Postgres, run `CREATE EXTENSION IF NOT EXISTS vector;` to create the vector extension.
### Usage
@@ -14,41 +15,38 @@ from mem0 import Memory
os.environ["OPENAI_API_KEY"] = "sk-xx"
config = {
"vector_store": {
"provider": "pgvector",
"config": {
"user": "test",
"password": "123",
"host": "127.0.0.1",
"port": "5432",
}
}
"vector_store": {
"provider": "pgvector",
"config": {
"user": "test",
"password": "123",
"host": "127.0.0.1",
"port": "5432",
},
}
}
m = Memory.from_config(config)
messages = [
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."},
]
m.add(messages, user_id="alice", metadata={"category": "movies"})
```
````
```typescript TypeScript
import { Memory } from 'mem0ai/oss';
import { Memory } from "mem0ai/oss";
const config = {
vectorStore: {
provider: 'pgvector',
provider: "pgvector",
config: {
collectionName: 'memories',
collectionName: "memories",
embeddingModelDims: 1536,
user: 'test',
password: '123',
host: '127.0.0.1',
port: 5432,
dbname: 'vector_store', // Optional; TypeScript OSS defaults to `vector_store` when omitted
connectionString: "postgresql://test:123@localhost:5432/vector_store",
diskann: false, // Optional, requires pgvectorscale extension
hnsw: false, // Optional, for HNSW indexing
},
@@ -57,37 +55,44 @@ const config = {
const memory = new Memory(config);
const messages = [
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
{ role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
{ role: "assistant", content: "How about thriller movies? They can be quite engaging." },
{ role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
{ role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." },
];
await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
```
````
</CodeGroup>
### Config
Here are the parameters available for configuring pgvector:
| Parameter | Description | Default Value |
| --- | --- | --- |
| `dbname` | The name of the database | `postgres` |
| `collection_name` | The name of the collection | `mem0` |
| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
| `user` | User name to connect to the database | `None` |
| `password` | Password to connect to the database | `None` |
| `host` | The host where the Postgres server is running | `None` |
| `port` | The port where the Postgres server is running | `None` |
| `diskann` | Whether to use diskann for vector similarity search (requires pgvectorscale) | `True` |
| `hnsw` | Whether to use hnsw for vector similarity search | `False` |
| `sslmode` | SSL mode for PostgreSQL connection (e.g., 'require', 'prefer', 'disable') | `None` |
| `connection_string` | PostgreSQL connection string (overrides individual connection parameters) | `None` |
| `connection_pool` | psycopg2 connection pool object (overrides connection string and individual parameters) | `None` |
| Parameter | SDK | Description | Default Value |
| -------------------- | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
| `connectionString` | TypeScript OSS | PostgreSQL connection string for direct connections. When set, Mem0 connects to the target database directly and skips the bootstrap `postgres` database flow. | `None` |
| `ssl` | TypeScript OSS | SSL option passed directly to `pg`, either `true` or an SSL config object, for both `connectionString` and split-field connections. | `None` |
| `dbname` | TypeScript OSS | Split-field database name. This is only used when `connectionString` is absent. | `vector_store` |
| `collectionName` | TypeScript OSS | Collection name. | `memories` |
| `embeddingModelDims` | TypeScript OSS | Dimensions of the embedding model. | Required |
| `user` | TypeScript OSS + Python | Database user for split-field connections. | `None` |
| `password` | TypeScript OSS + Python | Database password for split-field connections. | `None` |
| `host` | TypeScript OSS + Python | Database host for split-field connections. | `None` |
| `port` | TypeScript OSS + Python | Database port for split-field connections. | `None` |
| `diskann` | TypeScript OSS + Python | Whether to use DiskANN for vector similarity search, requires pgvectorscale. | `False` |
| `hnsw` | TypeScript OSS + Python | Whether to use HNSW for vector similarity search. | TypeScript OSS: `False`, Python: `True` |
| `connection_string` | Python only | PostgreSQL connection string, overrides individual connection parameters. | `None` |
| `sslmode` | Python only | SSL mode for PostgreSQL connections, such as `require`, `prefer`, or `disable`. | `None` |
| `connection_pool` | Python only | psycopg connection pool object, overrides connection string and individual connection parameters. | `None` |
**Note (TypeScript OSS):** If you omit `dbname`, the TypeScript client uses the database name `vector_store`. Python defaults to `postgres` for `dbname`, as in the table above.
**TypeScript OSS:** Use `connectionString` plus optional `ssl` for managed Postgres setups. If you omit `connectionString`, Mem0 falls back to split fields and uses `dbname`, `user`, `password`, `host`, `port`, and optional `ssl`.
**Python:** The Python SDK uses snake_case keys such as `connection_string`, `sslmode`, `collection_name`, and `embedding_model_dims`.
**Python connection priority**:
**Note**: The connection parameters have the following priority:
1. `connection_pool` (highest priority)
2. `connection_string`
3. Individual connection parameters (`user`, `password`, `host`, `port`, `sslmode`)
3. Individual connection parameters (`user`, `password`, `host`, `port`, `sslmode`)
mem0-ts/src/oss/src/vector_stores/pgvector.ts
+72 -33
View File
@@ -1,4 +1,4 @@
import type { Client as ClientType } from "pg";
import type { Client as ClientType, ClientConfig } from "pg";
import pkg from "pg";
const { Client, escapeIdentifier } = pkg;
import { VectorStore } from "./base";
@@ -157,41 +157,90 @@ export function buildFilterConditions(
interface PGVectorConfig extends VectorStoreConfig {
dbname?: string;
user: string;
password: string;
host: string;
port: number;
user?: string;
password?: string;
host?: string;
port?: number;
connectionString?: string;
ssl?: ClientConfig["ssl"];
embeddingModelDims: number;
diskann?: boolean;
hnsw?: boolean;
}
function getConnectionString(config: PGVectorConfig): string | undefined {
return config.connectionString?.trim() || undefined;
}
function validateConnectionConfig(config: PGVectorConfig): void {
if (getConnectionString(config)) {
return;
}
const missingFields = ["user", "password", "host", "port"].filter((field) => {
const v = config[field as keyof PGVectorConfig];
return v === undefined || v === null || v === "";
});
if (missingFields.length > 0) {
throw new Error(
`PGVector requires either connectionString or ${missingFields.join(", ")}`,
);
}
}
function buildClientConfig(
config: PGVectorConfig,
database?: string,
): ClientConfig {
const connectionString = getConnectionString(config);
if (connectionString) {
return {
connectionString,
...(config.ssl !== undefined ? { ssl: config.ssl } : {}),
};
}
return {
database,
user: config.user,
password: config.password,
host: config.host,
port: config.port,
...(config.ssl !== undefined ? { ssl: config.ssl } : {}),
};
}
export class PGVector implements VectorStore {
private client: ClientType;
private collectionName: string;
private useDiskann: boolean;
private useHnsw: boolean;
private readonly dbName: string;
private readonly useDirectConnection: boolean;
private config: PGVectorConfig;
private _initPromise?: Promise<void>;
constructor(config: PGVectorConfig) {
validateConnectionConfig(config);
this.collectionName = validateIdentifier(
config.collectionName || "memories",
"collectionName",
);
this.useDiskann = config.diskann || false;
this.useHnsw = config.hnsw || false;
this.dbName = validateIdentifier(config.dbname || "vector_store", "dbname");
this.useDirectConnection = !!getConnectionString(config);
this.dbName = this.useDirectConnection
? ""
: validateIdentifier(config.dbname || "vector_store", "dbname");
this.config = config;
this.client = new Client({
database: "postgres", // Initially connect to default postgres database
user: config.user,
password: config.password,
host: config.host,
port: config.port,
});
this.client = new Client(
buildClientConfig(
config,
this.useDirectConnection ? undefined : "postgres",
),
);
this.initialize().catch(console.error);
}
@@ -210,29 +259,20 @@ export class PGVector implements VectorStore {
try {
await this.client.connect();
// Check if database exists
const dbExists = await this.checkDatabaseExists(this.dbName);
if (!dbExists) {
await this.createDatabase(this.dbName);
if (!this.useDirectConnection) {
const dbExists = await this.checkDatabaseExists(this.dbName);
if (!dbExists) {
await this.createDatabase(this.dbName);
}
await this.client.end();
this.client = new Client(buildClientConfig(this.config, this.dbName));
await this.client.connect();
}
// Disconnect from postgres database
await this.client.end();
// Connect to the target database
this.client = new Client({
database: this.dbName,
user: this.config.user,
password: this.config.password,
host: this.config.host,
port: this.config.port,
});
await this.client.connect();
// Create vector extension
await this.client.query("CREATE EXTENSION IF NOT EXISTS vector");
// Create memory_migrations table
await this.client.query(`
CREATE TABLE IF NOT EXISTS memory_migrations (
id SERIAL PRIMARY KEY,
@@ -240,7 +280,6 @@ export class PGVector implements VectorStore {
)
`);
// Check if the collection exists
const collections = await this.listCols();
if (!collections.includes(this.collectionName)) {
await this.createCol(this.config.embeddingModelDims);
mem0-ts/src/oss/tests/pgvector.filters.test.ts
-2
View File
@@ -1,5 +1,3 @@
/// <reference types="jest" />
jest.mock("pg", () => {
const Client = jest.fn().mockImplementation(() => ({
connect: jest.fn().mockResolvedValue(undefined),
mem0-ts/src/oss/tests/pgvector.unit.test.ts
+122 -4
View File
@@ -1,5 +1,3 @@
/// <reference types="jest" />
const searchRows = [
{
id: "a",
@@ -23,9 +21,13 @@ const searchRows = [
},
];
const mockState = {
databaseExists: true,
};
function mockPgQuery(sql: string) {
if (sql.includes("SELECT 1 FROM pg_database")) {
return { rows: [{ "?column?": 1 }] };
return { rows: mockState.databaseExists ? [{ "?column?": 1 }] : [] };
}
if (sql.includes("FROM information_schema.tables")) {
@@ -69,13 +71,129 @@ jest.mock("pg", () => {
import { PGVector } from "../src/vector_stores/pgvector";
describe("PGVector - search()", () => {
function getClientQueries(client: { query: jest.Mock }) {
return client.query.mock.calls.map(([sql]) => sql as string);
}
describe("PGVector", () => {
beforeEach(() => {
const pg = require("pg");
mockState.databaseExists = true;
pg.__mock.Client.mockClear();
pg.__mock.clients.length = 0;
});
test("uses one direct client for connectionString mode and skips bootstrap database creation", async () => {
mockState.databaseExists = false;
const ssl = { rejectUnauthorized: false };
const store = new PGVector({
collectionName: "memories",
connectionString:
"postgresql://postgres:postgres@db.example.com:5432/neondb",
ssl,
embeddingModelDims: 3,
dimension: 3,
} as any);
await store.initialize();
const pg = require("pg");
expect(pg.__mock.Client).toHaveBeenCalledTimes(1);
expect(pg.__mock.Client).toHaveBeenCalledWith({
connectionString:
"postgresql://postgres:postgres@db.example.com:5432/neondb",
ssl,
});
const directClient = pg.__mock.clients[0];
const queries = getClientQueries(directClient);
expect(queries).not.toEqual(
expect.arrayContaining([
expect.stringContaining("SELECT 1 FROM pg_database"),
]),
);
expect(queries).not.toEqual(
expect.arrayContaining([expect.stringContaining("CREATE DATABASE")]),
);
expect(queries).toEqual(
expect.arrayContaining([
"CREATE EXTENSION IF NOT EXISTS vector",
expect.stringContaining("FROM information_schema.tables"),
]),
);
});
test("keeps the split-field bootstrap flow when connectionString is absent", async () => {
mockState.databaseExists = false;
const ssl = { rejectUnauthorized: false };
const store = new PGVector({
collectionName: "memories",
user: "postgres",
password: "postgres",
host: "localhost",
port: 5432,
dbname: "vector_store",
ssl,
embeddingModelDims: 3,
dimension: 3,
} as any);
await store.initialize();
const pg = require("pg");
expect(pg.__mock.Client).toHaveBeenCalledTimes(2);
expect(pg.__mock.Client).toHaveBeenNthCalledWith(1, {
database: "postgres",
user: "postgres",
password: "postgres",
host: "localhost",
port: 5432,
ssl,
});
expect(pg.__mock.Client).toHaveBeenNthCalledWith(2, {
database: "vector_store",
user: "postgres",
password: "postgres",
host: "localhost",
port: 5432,
ssl,
});
const bootstrapClient = pg.__mock.clients[0];
const activeClient = pg.__mock.clients[1];
const bootstrapQueries = getClientQueries(bootstrapClient);
expect(bootstrapQueries).toEqual(
expect.arrayContaining([
"SELECT 1 FROM pg_database WHERE datname = $1",
'CREATE DATABASE "vector_store"',
]),
);
expect(bootstrapClient.end).toHaveBeenCalledTimes(1);
expect(getClientQueries(activeClient)).toEqual(
expect.arrayContaining([
"CREATE EXTENSION IF NOT EXISTS vector",
expect.stringContaining("FROM information_schema.tables"),
]),
);
});
test("throws when connectionString is absent and split-field params are missing", () => {
expect(
() =>
new PGVector({
collectionName: "memories",
embeddingModelDims: 3,
dimension: 3,
} as any),
).toThrow(
"PGVector requires either connectionString or user, password, host, port",
);
});
test("returns similarity score (1 - distance) clamped to [0, 1]", async () => {
const store = new PGVector({
collectionName: "memories",