my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: Direct Import
#3	description: 'Bypass the memory deduction phase and directly store pre-defined memories for efficient retrieval'
#4	---
#5
#6	## How to Use Direct Import
#7
#8	The Direct Import feature allows users to skip the memory deduction phase and directly input pre-defined memories into the system for storage and retrieval. To enable this feature, set the `infer` parameter to `False` in the `add` method.
#9
#10
#11	<CodeGroup>
#12
#13
#14	```python Python
#15	messages = [
#16	{"role": "user", "content": "Alice loves playing badminton"},
#17	{"role": "assistant", "content": "That's great! Alice is a fitness freak"},
#18	{"role": "user", "content": "Alice mostly cooks at home because of her gym plan"},
#19	]
#20
#21
#22	client.add(messages, user_id="alice", infer=False)
#23	```
#24
#25	```markdown Output
#26	[]
#27	```
#28	</CodeGroup>
#29
#30	You can see that the output of the add call is an empty list.
#31
#32	<Note>Only messages with the role "user" will be used for storage. Messages with roles such as "assistant" or "system" will be ignored during the storage process.</Note>
#33
#34	<Warning>
#35	Direct import skips the inference pipeline, so it also skips duplicate detection. If you later send the same fact with `infer=True`, Mem0 will store a second copy. Pick one mode per memory source unless you truly want both versions.
#36	</Warning>
#37
#38	## How to Retrieve Memories
#39
#40	You can retrieve memories using the `search` method.
#41
#42	<CodeGroup>
#43
#44	```python Python
#45	client.search("What is Alice's favorite sport?", user_id="alice")
#46	```
#47
#48	```json Output
#49	{
#50	"results": [
#51	{
#52	"id": "19d6d7aa-2454-4e58-96fc-e74d9e9f8dd1",
#53	"memory": "Alice loves playing badminton",
#54	"user_id": "pc123",
#55	"metadata": null,
#56	"categories": null,
#57	"created_at": "2024-10-15T21:52:11.474901-07:00",
#58	"updated_at": "2024-10-15T21:52:11.474912-07:00"
#59	}
#60	]
#61	}
#62	```
#63
#64	</CodeGroup>
#65
#66	## How to Retrieve All Memories
#67
#68	You can retrieve all memories using the `get_all` method.
#69
#70	<Callout type="warning" title="Filters Required">
#71	`get_all()` now requires filters to be specified.
#72	</Callout>
#73
#74	<CodeGroup>
#75
#76	```python Python
#77	client.get_all(filters={"AND": [{"user_id": "alice"}]})
#78	```
#79
#80	```json Output
#81	{
#82	"results": [
#83	{
#84	"id": "19d6d7aa-2454-4e58-96fc-e74d9e9f8dd1",
#85	"memory": "Alice loves playing badminton",
#86	"user_id": "pc123",
#87	"metadata": null,
#88	"categories": null,
#89	"created_at": "2024-10-15T21:52:11.474901-07:00",
#90	"updated_at": "2024-10-15T21:52:11.474912-07:00"
#91	},
#92	{
#93	"id": "8557f05d-7b3c-47e5-b409-9886f9e314fc",
#94	"memory": "Alice mostly cooks at home because of her gym plan",
#95	"user_id": "pc123",
#96	"metadata": null,
#97	"categories": null,
#98	"created_at": "2024-10-15T21:52:11.474929-07:00",
#99	"updated_at": "2024-10-15T21:52:11.474932-07:00"
#100	}
#101	]
#102	}
#103	```
#104
#105	</CodeGroup>
#106
#107	If you have any questions, please feel free to reach out to us using one of the following methods:
#108
#109	<Snippet file="get-help.mdx" />
#110

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public