my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: Baidu VectorDB (Mochow)
#3	---
#4
#5	[Baidu VectorDB](https://cloud.baidu.com/doc/VDB/index.html) is an enterprise-level distributed vector database service developed by Baidu Intelligent Cloud. It is powered by Baidu's proprietary "Mochow" vector database kernel, providing high performance, availability, and security for vector search.
#6
#7	### Usage
#8
#9	```python
#10	import os
#11	from mem0 import Memory
#12
#13	config = {
#14	"vector_store": {
#15	"provider": "baidu",
#16	"config": {
#17	"endpoint": "http://your-mochow-endpoint:8287",
#18	"account": "root",
#19	"api_key": "your-api-key",
#20	"database_name": "mem0",
#21	"table_name": "mem0_table",
#22	"embedding_model_dims": 1536,
#23	"metric_type": "COSINE"
#24	}
#25	}
#26	}
#27
#28	m = Memory.from_config(config)
#29	messages = [
#30	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#31	{"role": "assistant", "content": "How about a thriller movie? They can be quite engaging."},
#32	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#33	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#34	]
#35	m.add(messages, user_id="alice", metadata={"category": "movies"})
#36	```
#37
#38	### Config
#39
#40	Here are the parameters available for configuring Baidu VectorDB:
#41
#42	\| Parameter \| Description \| Default Value \|
#43	\| --- \| --- \| --- \|
#44	\| `endpoint` \| Endpoint URL for your Baidu VectorDB instance \| Required \|
#45	\| `account` \| Baidu VectorDB account name \| `root` \|
#46	\| `api_key` \| API key for accessing Baidu VectorDB \| Required \|
#47	\| `database_name` \| Name of the database \| `mem0` \|
#48	\| `table_name` \| Name of the table \| `mem0_table` \|
#49	\| `embedding_model_dims` \| Dimensions of the embedding model \| `1536` \|
#50	\| `metric_type` \| Distance metric for similarity search \| `L2` \|
#51
#52	### Distance Metrics
#53
#54	The following distance metrics are supported:
#55
#56	- `L2`: Euclidean distance (default)
#57	- `IP`: Inner product
#58	- `COSINE`: Cosine similarity
#59
#60	### Index Configuration
#61
#62	The vector index is automatically configured with the following HNSW parameters:
#63
#64	- `m`: 16 (number of connections per element)
#65	- `efconstruction`: 200 (size of the dynamic candidate list)
#66	- `auto_build`: true (automatically build index)
#67	- `auto_build_index_policy`: Incremental build with 10000 rows increment
#68

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public