my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	---
#2	title: Groq
#3	---
#4
#5	[Groq](https://groq.com/) is the creator of the world's first Language Processing Unit (LPU), providing exceptional speed performance for AI workloads running on their LPU Inference Engine.
#6
#7	In order to use LLMs from Groq, go to their [platform](https://console.groq.com/keys) and get the API key. Set the API key as `GROQ_API_KEY` environment variable to use the model as given below in the example.
#8
#9	## Usage
#10
#11	<CodeGroup>
#12	```python Python
#13	import os
#14	from mem0 import Memory
#15
#16	os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model
#17	os.environ["GROQ_API_KEY"] = "your-api-key"
#18
#19	config = {
#20	"llm": {
#21	"provider": "groq",
#22	"config": {
#23	"model": "mixtral-8x7b-32768",
#24	"temperature": 0.1,
#25	"max_tokens": 2000,
#26	}
#27	}
#28	}
#29
#30	m = Memory.from_config(config)
#31	messages = [
#32	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#33	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#34	{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
#35	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#36	]
#37	m.add(messages, user_id="alice", metadata={"category": "movies"})
#38	```
#39
#40	```typescript TypeScript
#41	import { Memory } from 'mem0ai/oss';
#42
#43	const config = {
#44	llm: {
#45	provider: 'groq',
#46	config: {
#47	apiKey: process.env.GROQ_API_KEY \|\| '',
#48	model: 'mixtral-8x7b-32768',
#49	temperature: 0.1,
#50	maxTokens: 1000,
#51	},
#52	},
#53	};
#54
#55	const memory = new Memory(config);
#56	const messages = [
#57	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#58	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#59	{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
#60	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#61	]
#62	await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
#63	```
#64	</CodeGroup>
#65
#66	## Config
#67
#68	All available parameters for the `groq` config are present in [Master List of All Params in Config](../config).

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public