my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: Google AI
#3	---
#4
#5	To use the Gemini model, set the `GOOGLE_API_KEY` environment variable. You can obtain the Google/Gemini API key from [Google AI Studio](https://aistudio.google.com/app/apikey).
#6
#7	> Note: As of the latest release, Mem0 uses the new `google.genai` SDK instead of the deprecated `google.generativeai`. All message formatting and model interaction now use the updated `types` module from `google.genai`.
#8
#9	> Note: Some Gemini models are being deprecated and will retire soon. It is recommended to migrate to the latest stable models like `"gemini-2.0-flash-001"` or `"gemini-2.0-flash-lite-001"` to ensure ongoing support and improvements.
#10
#11	## Usage
#12
#13	<CodeGroup>
#14	```python Python
#15	import os
#16	from mem0 import Memory
#17
#18	os.environ["OPENAI_API_KEY"] = "your-openai-api-key" # Used for embedding model
#19	os.environ["GOOGLE_API_KEY"] = "your-gemini-api-key"
#20
#21	config = {
#22	"llm": {
#23	"provider": "gemini",
#24	"config": {
#25	"model": "gemini-2.0-flash-001",
#26	"temperature": 0.2,
#27	"max_tokens": 2000,
#28	"top_p": 1.0
#29	}
#30	}
#31	}
#32
#33	m = Memory.from_config(config)
#34
#35	messages = [
#36	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#37	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#38	{"role": "user", "content": "I’m not a big fan of thrillers, but I love sci-fi movies."},
#39	{"role": "assistant", "content": "Got it! I'll avoid thrillers and suggest sci-fi movies instead."}
#40	]
#41
#42	m.add(messages, user_id="alice", metadata={"category": "movies"})
#43
#44	```
#45	```typescript TypeScript
#46	import { Memory } from "mem0ai/oss";
#47
#48	const config = {
#49	llm: {
#50	// You can also use "google" as provider ( for backward compatibility )
#51	provider: "gemini",
#52	config: {
#53	model: "gemini-2.0-flash-001",
#54	temperature: 0.1
#55	}
#56	}
#57	}
#58
#59	const memory = new Memory(config);
#60
#61	const messages = [
#62	{ role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
#63	{ role: "assistant", content: "How about thriller movies? They can be quite engaging." },
#64	{ role: "user", content: "I’m not a big fan of thrillers, but I love sci-fi movies." },
#65	{ role: "assistant", content: "Got it! I'll avoid thrillers and suggest sci-fi movies instead." }
#66	]
#67
#68	await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
#69	```
#70	</CodeGroup>
#71
#72	## Config
#73
#74	All available parameters for the `Gemini` config are present in [Master List of All Params in Config](../config).

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public