my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	[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.
#2
#3	### Usage
#4
#5	<CodeGroup>
#6	```python Python
#7	import os
#8	from mem0 import Memory
#9
#10	os.environ["OPENAI_API_KEY"] = "sk-xx"
#11
#12	config = {
#13	"vector_store": {
#14	"provider": "pgvector",
#15	"config": {
#16	"user": "test",
#17	"password": "123",
#18	"host": "127.0.0.1",
#19	"port": "5432",
#20	}
#21	}
#22	}
#23
#24	m = Memory.from_config(config)
#25	messages = [
#26	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#27	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#28	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#29	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#30	]
#31	m.add(messages, user_id="alice", metadata={"category": "movies"})
#32	```
#33
#34	```typescript TypeScript
#35	import { Memory } from 'mem0ai/oss';
#36
#37	const config = {
#38	vectorStore: {
#39	provider: 'pgvector',
#40	config: {
#41	collectionName: 'memories',
#42	embeddingModelDims: 1536,
#43	user: 'test',
#44	password: '123',
#45	host: '127.0.0.1',
#46	port: 5432,
#47	dbname: 'vector_store', // Optional, defaults to 'postgres'
#48	diskann: false, // Optional, requires pgvectorscale extension
#49	hnsw: false, // Optional, for HNSW indexing
#50	},
#51	},
#52	};
#53
#54	const memory = new Memory(config);
#55	const messages = [
#56	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#57	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#58	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#59	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#60	]
#61	await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
#62	```
#63	</CodeGroup>
#64
#65	### Config
#66
#67	Here are the parameters available for configuring pgvector:
#68
#69	\| Parameter \| Description \| Default Value \|
#70	\| --- \| --- \| --- \|
#71	\| `dbname` \| The name of the database \| `postgres` \|
#72	\| `collection_name` \| The name of the collection \| `mem0` \|
#73	\| `embedding_model_dims` \| Dimensions of the embedding model \| `1536` \|
#74	\| `user` \| User name to connect to the database \| `None` \|
#75	\| `password` \| Password to connect to the database \| `None` \|
#76	\| `host` \| The host where the Postgres server is running \| `None` \|
#77	\| `port` \| The port where the Postgres server is running \| `None` \|
#78	\| `diskann` \| Whether to use diskann for vector similarity search (requires pgvectorscale) \| `True` \|
#79	\| `hnsw` \| Whether to use hnsw for vector similarity search \| `False` \|
#80	\| `sslmode` \| SSL mode for PostgreSQL connection (e.g., 'require', 'prefer', 'disable') \| `None` \|
#81	\| `connection_string` \| PostgreSQL connection string (overrides individual connection parameters) \| `None` \|
#82	\| `connection_pool` \| psycopg2 connection pool object (overrides connection string and individual parameters) \| `None` \|
#83
#84	Note: The connection parameters have the following priority:
#85	1. `connection_pool` (highest priority)
#86	2. `connection_string`
#87	3. Individual connection parameters (`user`, `password`, `host`, `port`, `sslmode`)

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public