my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	---
#2	title: Keywords AI
#3	---
#4
#5	Build AI applications with persistent memory and comprehensive LLM observability by integrating Mem0 with Keywords AI.
#6
#7	## Overview
#8
#9	Mem0 is a self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users. Keywords AI provides complete LLM observability.
#10
#11	Combining Mem0 with Keywords AI allows you to:
#12	1. Add persistent memory to your AI applications
#13	2. Track interactions across sessions
#14	3. Monitor memory usage and retrieval with Keywords AI observability
#15	4. Optimize token usage and reduce costs
#16
#17	<Note>
#18	You can get your Mem0 API key, user_id, and org_id from the [Mem0 dashboard](https://app.mem0.ai/). These are required for proper integration.
#19	</Note>
#20
#21	## Setup and Configuration
#22
#23	Install the necessary libraries:
#24
#25	```bash
#26	pip install mem0 keywordsai-sdk
#27	```
#28
#29	Set up your environment variables:
#30
#31	```python
#32	import os
#33
#34	# Set your API keys
#35	os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
#36	os.environ["KEYWORDSAI_API_KEY"] = "your-keywords-api-key"
#37	os.environ["KEYWORDSAI_BASE_URL"] = "https://api.keywordsai.co/api/"
#38	```
#39
#40	## Basic Integration Example
#41
#42	Here's a simple example of using Mem0 with Keywords AI:
#43
#44	```python
#45	from mem0 import Memory
#46	import os
#47
#48	# Configuration
#49	api_key = os.getenv("MEM0_API_KEY")
#50	keywordsai_api_key = os.getenv("KEYWORDSAI_API_KEY")
#51	base_url = os.getenv("KEYWORDSAI_BASE_URL") # "https://api.keywordsai.co/api/"
#52
#53	# Set up Mem0 with Keywords AI as the LLM provider
#54	config = {
#55	"llm": {
#56	"provider": "openai",
#57	"config": {
#58	"model": "gpt-4.1-nano-2025-04-14",
#59	"temperature": 0.0,
#60	"api_key": keywordsai_api_key,
#61	"openai_base_url": base_url,
#62	},
#63	}
#64	}
#65
#66	# Initialize Memory
#67	memory = Memory.from_config(config_dict=config)
#68
#69	# Add a memory
#70	result = memory.add(
#71	"I like to take long walks on weekends.",
#72	user_id="alice",
#73	metadata={"category": "hobbies"},
#74	)
#75
#76	print(result)
#77	```
#78
#79	## Advanced Integration with OpenAI SDK
#80
#81	For more advanced use cases, you can integrate Keywords AI with Mem0 through the OpenAI SDK:
#82
#83	```python
#84	from openai import OpenAI
#85	import os
#86	import json
#87
#88	# Initialize client
#89	client = OpenAI(
#90	api_key=os.environ.get("KEYWORDSAI_API_KEY"),
#91	base_url=os.environ.get("KEYWORDSAI_BASE_URL"),
#92	)
#93
#94	# Sample conversation messages
#95	messages = [
#96	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#97	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#98	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#99	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#100	]
#101
#102	# Add memory and generate a response
#103	response = client.chat.completions.create(
#104	model="openai/gpt-4.1-nano",
#105	messages=messages,
#106	extra_body={
#107	"mem0_params": {
#108	"user_id": "test_user",
#109	"org_id": "org_1",
#110	"api_key": os.environ.get("MEM0_API_KEY"),
#111	"add_memories": {
#112	"messages": messages,
#113	},
#114	}
#115	},
#116	)
#117
#118	print(json.dumps(response.model_dump(), indent=4))
#119	```
#120
#121	For detailed information on this integration, refer to the official [Keywords AI Mem0 integration documentation](https://docs.keywordsai.co/integration/development-frameworks/mem0).
#122
#123	## Key Features
#124
#125	1. Memory Integration: Store and retrieve relevant information from past interactions
#126	2. LLM Observability: Track memory usage and retrieval patterns with Keywords AI
#127	3. Session Persistence: Maintain context across multiple user sessions
#128	4. Cost Optimization: Reduce token usage through efficient memory retrieval
#129
#130	## Conclusion
#131
#132	Integrating Mem0 with Keywords AI provides a powerful combination for building AI applications with persistent memory and comprehensive observability. This integration enables more personalized user experiences while providing insights into your application's memory usage.
#133
#134	<CardGroup cols={2}>
#135	<Card title="OpenAI Agents SDK" icon="cube" href="/integrations/openai-agents-sdk">
#136	Build monitored agents with OpenAI SDK
#137	</Card>
#138	<Card title="AgentOps Integration" icon="chart-line" href="/integrations/agentops">
#139	Monitor agent performance with AgentOps
#140	</Card>
#141	</CardGroup>
#142
#143

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public