my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: Configurations
#3	---
#4
#5
#6	Config in mem0 is a dictionary that specifies the settings for your embedding models. It allows you to customize the behavior and connection details of your chosen embedder.
#7
#8	## How to define configurations?
#9
#10	The config is defined as an object (or dictionary) with two main keys:
#11	- `embedder`: Specifies the embedder provider and its configuration
#12	- `provider`: The name of the embedder (e.g., "openai", "ollama")
#13	- `config`: A nested object or dictionary containing provider-specific settings
#14
#15
#16	## How to use configurations?
#17
#18	Here's a general example of how to use the config with mem0:
#19
#20	<CodeGroup>
#21	```python Python
#22	import os
#23	from mem0 import Memory
#24
#25	os.environ["OPENAI_API_KEY"] = "sk-xx"
#26
#27	config = {
#28	"embedder": {
#29	"provider": "your_chosen_provider",
#30	"config": {
#31	# Provider-specific settings go here
#32	}
#33	}
#34	}
#35
#36	m = Memory.from_config(config)
#37	m.add("Your text here", user_id="user", metadata={"category": "example"})
#38	```
#39
#40	```typescript TypeScript
#41	import { Memory } from 'mem0ai/oss';
#42
#43	const config = {
#44	embedder: {
#45	provider: 'openai',
#46	config: {
#47	apiKey: process.env.OPENAI_API_KEY \|\| '',
#48	model: 'text-embedding-3-small',
#49	// Provider-specific settings go here
#50	},
#51	},
#52	};
#53
#54	const memory = new Memory(config);
#55	await memory.add("Your text here", { userId: "user", metadata: { category: "example" } });
#56	```
#57	</CodeGroup>
#58
#59	## Why is Config Needed?
#60
#61	Config is essential for:
#62	1. Specifying which embedding model to use.
#63	2. Providing necessary connection details (e.g., model, api_key, embedding_dims).
#64	3. Ensuring proper initialization and connection to your chosen embedder.
#65
#66	## Master List of All Params in Config
#67
#68	Here's a comprehensive list of all parameters that can be used across different embedders:
#69
#70	<Tabs>
#71	<Tab title="Python">
#72	\| Parameter \| Description \| Provider \|
#73	\|-----------\|-------------\|----------\|
#74	\| `model` \| Embedding model to use \| All \|
#75	\| `api_key` \| API key of the provider \| All \|
#76	\| `embedding_dims` \| Dimensions of the embedding model \| All \|
#77	\| `http_client_proxies` \| Allow proxy server settings \| All \|
#78	\| `ollama_base_url` \| Base URL for the Ollama embedding model \| Ollama \|
#79	\| `model_kwargs` \| Key-Value arguments for the Huggingface embedding model \| Huggingface \|
#80	\| `azure_kwargs` \| Key-Value arguments for the AzureOpenAI embedding model \| Azure OpenAI \|
#81	\| `openai_base_url` \| Base URL for OpenAI API \| OpenAI \|
#82	\| `vertex_credentials_json` \| Path to the Google Cloud credentials JSON file for VertexAI \| VertexAI \|
#83	\| `memory_add_embedding_type` \| The type of embedding to use for the add memory action \| VertexAI \|
#84	\| `memory_update_embedding_type` \| The type of embedding to use for the update memory action \| VertexAI \|
#85	\| `memory_search_embedding_type` \| The type of embedding to use for the search memory action \| VertexAI \|
#86	\| `lmstudio_base_url` \| Base URL for LM Studio API \| LM Studio \|
#87	</Tab>
#88	<Tab title="TypeScript">
#89	\| Parameter \| Description \| Provider \|
#90	\|-----------\|-------------\|----------\|
#91	\| `model` \| Embedding model to use \| All \|
#92	\| `apiKey` \| API key of the provider \| All \|
#93	\| `embeddingDims` \| Dimensions of the embedding model \| All \|
#94	</Tab>
#95	</Tabs>
#96
#97	## Supported Embedding Models
#98
#99	For detailed information on configuring specific embedders, please visit the [Embedding Models](./models) section. There you'll find information for each supported embedder with provider-specific usage examples and configuration details.
#100

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public