my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	---
#2	title: Configurations
#3	---
#4
#5	## How to define configurations?
#6
#7	The `config` is defined as an object with two main keys:
#8	- `vector_store`: Specifies the vector database provider and its configuration
#9	- `provider`: The name of the vector database (e.g., "chroma", "pgvector", "qdrant", "milvus", "upstash_vector", "azure_ai_search", "vertex_ai_vector_search", "valkey")
#10	- `config`: A nested dictionary containing provider-specific settings
#11
#12
#13	## How to Use Config
#14
#15	Here's a general example of how to use the config with mem0:
#16
#17	<CodeGroup>
#18	```python Python
#19	import os
#20	from mem0 import Memory
#21
#22	os.environ["OPENAI_API_KEY"] = "sk-xx"
#23
#24	config = {
#25	"vector_store": {
#26	"provider": "your_chosen_provider",
#27	"config": {
#28	# Provider-specific settings go here
#29	}
#30	}
#31	}
#32
#33	m = Memory.from_config(config)
#34	m.add("Your text here", user_id="user", metadata={"category": "example"})
#35	```
#36
#37	```typescript TypeScript
#38	// Example for in-memory vector database (Only supported in TypeScript)
#39	import { Memory } from 'mem0ai/oss';
#40
#41	const configMemory = {
#42	vector_store: {
#43	provider: 'memory',
#44	config: {
#45	collectionName: 'memories',
#46	dimension: 1536,
#47	},
#48	},
#49	};
#50
#51	const memory = new Memory(configMemory);
#52	await memory.add("Your text here", { userId: "user", metadata: { category: "example" } });
#53	```
#54	</CodeGroup>
#55
#56	<Note>
#57	The in-memory vector database is only supported in the TypeScript implementation.
#58	</Note>
#59
#60	## Why is Config Needed?
#61
#62	Config is essential for:
#63	1. Specifying which vector database to use.
#64	2. Providing necessary connection details (e.g., host, port, credentials).
#65	3. Customizing database-specific settings (e.g., collection name, path).
#66	4. Ensuring proper initialization and connection to your chosen vector store.
#67
#68	## Master List of All Params in Config
#69
#70	Here's a comprehensive list of all parameters that can be used across different vector databases:
#71
#72	<Tabs>
#73	<Tab title="Python">
#74	\| Parameter \| Description \|
#75	\|-----------\|-------------\|
#76	\| `collection_name` \| Name of the collection \|
#77	\| `embedding_model_dims` \| Dimensions of the embedding model \|
#78	\| `client` \| Custom client for the database \|
#79	\| `path` \| Path for the database \|
#80	\| `host` \| Host where the server is running \|
#81	\| `port` \| Port where the server is running \|
#82	\| `user` \| Username for database connection \|
#83	\| `password` \| Password for database connection \|
#84	\| `dbname` \| Name of the database \|
#85	\| `url` \| Full URL for the server \|
#86	\| `api_key` \| API key for the server \|
#87	\| `on_disk` \| Enable persistent storage \|
#88	\| `endpoint_id` \| Endpoint ID (vertex_ai_vector_search) \|
#89	\| `index_id` \| Index ID (vertex_ai_vector_search) \|
#90	\| `deployment_index_id` \| Deployment index ID (vertex_ai_vector_search) \|
#91	\| `project_id` \| Project ID (vertex_ai_vector_search) \|
#92	\| `project_number` \| Project number (vertex_ai_vector_search) \|
#93	\| `vector_search_api_endpoint` \| Vector search API endpoint (vertex_ai_vector_search) \|
#94	\| `connection_string` \| PostgreSQL connection string (for Supabase/PGVector) \|
#95	\| `index_method` \| Vector index method (for Supabase) \|
#96	\| `index_measure` \| Distance measure for similarity search (for Supabase) \|
#97	</Tab>
#98	<Tab title="TypeScript">
#99	\| Parameter \| Description \|
#100	\|-----------\|-------------\|
#101	\| `collectionName` \| Name of the collection \|
#102	\| `embeddingModelDims` \| Dimensions of the embedding model \|
#103	\| `dimension` \| Dimensions of the embedding model (for memory provider) \|
#104	\| `host` \| Host where the server is running \|
#105	\| `port` \| Port where the server is running \|
#106	\| `url` \| URL for the server \|
#107	\| `apiKey` \| API key for the server \|
#108	\| `path` \| Path for the database \|
#109	\| `onDisk` \| Enable persistent storage \|
#110	\| `redisUrl` \| URL for the Redis server \|
#111	\| `username` \| Username for database connection \|
#112	\| `password` \| Password for database connection \|
#113	</Tab>
#114	</Tabs>
#115
#116	## Customizing Config
#117
#118	Each vector database has its own specific configuration requirements. To customize the config for your chosen vector store:
#119
#120	1. Identify the vector database you want to use from [supported vector databases](./dbs).
#121	2. Refer to the `Config` section in the respective vector database's documentation.
#122	3. Include only the relevant parameters for your chosen database in the `config` dictionary.
#123
#124	## Supported Vector Databases
#125
#126	For detailed information on configuring specific vector databases, please visit the [Supported Vector Databases](./dbs) section. There you'll find individual pages for each supported vector store with provider-specific usage examples and configuration details.
#127

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public