my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	[Upstash Vector](https://upstash.com/docs/vector) is a serverless vector database with built-in embedding models.
#2
#3	### Usage with Upstash embeddings
#4
#5	You can enable the built-in embedding models by setting `enable_embeddings` to `True`. This allows you to use Upstash's embedding models for vectorization.
#6
#7	```python
#8	import os
#9	from mem0 import Memory
#10
#11	os.environ["UPSTASH_VECTOR_REST_URL"] = "..."
#12	os.environ["UPSTASH_VECTOR_REST_TOKEN"] = "..."
#13
#14	config = {
#15	"vector_store": {
#16	"provider": "upstash_vector",
#17	"enable_embeddings": True,
#18	}
#19	}
#20
#21	m = Memory.from_config(config)
#22	m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})
#23	```
#24
#25	<Note>
#26	Setting `enable_embeddings` to `True` will bypass any external embedding provider you have configured.
#27	</Note>
#28
#29	### Usage with external embedding providers
#30
#31	```python
#32	import os
#33	from mem0 import Memory
#34
#35	os.environ["OPENAI_API_KEY"] = "..."
#36	os.environ["UPSTASH_VECTOR_REST_URL"] = "..."
#37	os.environ["UPSTASH_VECTOR_REST_TOKEN"] = "..."
#38
#39	config = {
#40	"vector_store": {
#41	"provider": "upstash_vector",
#42	},
#43	"embedder": {
#44	"provider": "openai",
#45	"config": {
#46	"model": "text-embedding-3-large"
#47	},
#48	}
#49	}
#50
#51	m = Memory.from_config(config)
#52	m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})
#53	```
#54
#55	### Config
#56
#57	Here are the parameters available for configuring Upstash Vector:
#58
#59	\| Parameter \| Description \| Default Value \|
#60	\| ------------------- \| ---------------------------------- \| ------------- \|
#61	\| `url` \| URL for the Upstash Vector index \| `None` \|
#62	\| `token` \| Token for the Upstash Vector index \| `None` \|
#63	\| `client` \| An `upstash_vector.Index` instance \| `None` \|
#64	\| `collection_name` \| The default namespace used \| `""` \|
#65	\| `enable_embeddings` \| Whether to use Upstash embeddings \| `False` \|
#66
#67	<Note>
#68	When `url` and `token` are not provided, the `UPSTASH_VECTOR_REST_URL` and
#69	`UPSTASH_VECTOR_REST_TOKEN` environment variables are used.
#70	</Note>
#71

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public