my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: Azure OpenAI
#3	---
#4
#5	To use Azure OpenAI embedding models, set the `EMBEDDING_AZURE_OPENAI_API_KEY`, `EMBEDDING_AZURE_DEPLOYMENT`, `EMBEDDING_AZURE_ENDPOINT` and `EMBEDDING_AZURE_API_VERSION` environment variables. You can obtain the Azure OpenAI API key from the Azure.
#6
#7	### Usage
#8
#9	<CodeGroup>
#10	```python Python
#11	import os
#12	from mem0 import Memory
#13
#14	os.environ["EMBEDDING_AZURE_OPENAI_API_KEY"] = "your-api-key"
#15	os.environ["EMBEDDING_AZURE_DEPLOYMENT"] = "your-deployment-name"
#16	os.environ["EMBEDDING_AZURE_ENDPOINT"] = "your-api-base-url"
#17	os.environ["EMBEDDING_AZURE_API_VERSION"] = "version-to-use"
#18
#19	os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
#20
#21
#22	config = {
#23	"embedder": {
#24	"provider": "azure_openai",
#25	"config": {
#26	"model": "text-embedding-3-large",
#27	"azure_kwargs": {
#28	"api_version": "",
#29	"azure_deployment": "",
#30	"azure_endpoint": "",
#31	"api_key": "",
#32	"default_headers": {
#33	"CustomHeader": "your-custom-header",
#34	}
#35	}
#36	}
#37	}
#38	}
#39
#40	m = Memory.from_config(config)
#41	messages = [
#42	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#43	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#44	{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
#45	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#46	]
#47	m.add(messages, user_id="john")
#48	```
#49
#50	```typescript TypeScript
#51	import { Memory } from 'mem0ai/oss';
#52
#53	const config = {
#54	embedder: {
#55	provider: "azure_openai",
#56	config: {
#57	model: "text-embedding-3-large",
#58	modelProperties: {
#59	endpoint: "your-api-base-url",
#60	deployment: "your-deployment-name",
#61	apiVersion: "version-to-use",
#62	}
#63	}
#64	}
#65	}
#66
#67	const memory = new Memory(config);
#68
#69	const messages = [
#70	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#71	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#72	{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
#73	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#74	]
#75
#76	await memory.add(messages, { userId: "john" });
#77	```
#78	</CodeGroup>
#79
#80	As an alternative to using an API key, the Azure Identity credential chain can be used to authenticate with [Azure OpenAI role-based security](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/role-based-access-control).
#81
#82	<Note> If an API key is provided, it will be used for authentication over an Azure Identity </Note>
#83
#84	Below is a sample configuration for using Mem0 with Azure OpenAI and Azure Identity:
#85
#86	```python
#87	import os
#88	from mem0 import Memory
#89	# You can set the values directly in the config dictionary or use environment variables
#90
#91	os.environ["LLM_AZURE_DEPLOYMENT"] = "your-deployment-name"
#92	os.environ["LLM_AZURE_ENDPOINT"] = "your-api-base-url"
#93	os.environ["LLM_AZURE_API_VERSION"] = "version-to-use"
#94
#95	config = {
#96	"llm": {
#97	"provider": "azure_openai_structured",
#98	"config": {
#99	"model": "your-deployment-name",
#100	"temperature": 0.1,
#101	"max_tokens": 2000,
#102	"azure_kwargs": {
#103	"azure_deployment": "<your-deployment-name>",
#104	"api_version": "<version-to-use>",
#105	"azure_endpoint": "<your-api-base-url>",
#106	"default_headers": {
#107	"CustomHeader": "your-custom-header",
#108	}
#109	}
#110	}
#111	}
#112	}
#113	```
#114
#115	Refer to [Azure Identity troubleshooting tips](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/identity/azure-identity/TROUBLESHOOTING.md#troubleshoot-environmentcredential-authentication-issues) for setting up an Azure Identity credential.
#116
#117	### Config
#118
#119	Here are the parameters available for configuring Azure OpenAI embedder:
#120	<Tabs>
#121	<Tab title="Python">
#122	\| Parameter \| Description \| Default Value \|
#123	\| --- \| --- \| --- \|
#124	\| `model` \| The name of the embedding model to use \| `text-embedding-3-small` \|
#125	\| `embedding_dims` \| Dimensions of the embedding model \| `1536` \|
#126	\| `azure_kwargs` \| The Azure OpenAI configs \| `config_keys` \|
#127	</Tab>
#128	<Tab title="TypeScript">
#129	\| Parameter \| Description \| Default Value \|
#130	\| ----------------- \| --------------------------------------------- \| -------------------------- \|
#131	\| `model` \| The name of the embedding model to use \| `text-embedding-3-small` \|
#132	\| `embeddingDims` \| Dimensions of the embedding model \| `1536` \|
#133	\| `apiKey` \| Azure OpenAI API key \| `None` \|
#134	\| `modelProperties` \| Object containing endpoint and other settings \| `{ endpoint: "",...rest }`\|
#135	</Tab>
#136	</Tabs>
#137

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public