my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	---
#2	title: Export Stored Memories
#3	description: "Retrieve, review, and migrate user memories with structured exports."
#4	---
#5
#6
#7	Mem0 is a dynamic memory store that gives you full control over your data. Along with storing memories, it gives you the ability to retrieve, export, and migrate your data whenever you need.
#8
#9	This cookbook shows you how to retrieve and export your data for inspection, migration, or compliance.
#10
#11	---
#12
#13	## Setup
#14
#15	```python
#16	from mem0 import MemoryClient
#17
#18	client = MemoryClient(api_key="your-api-key")
#19
#20	```
#21
#22	<Note>
#23	Your API key needs export permissions to download memory data. Check your project settings on the [dashboard](https://app.mem0.ai) if export operations fail with authentication errors.
#24	</Note>
#25
#26	Let's add some sample memories to work with:
#27
#28	```python
#29	# Dev's work history
#30	client.add(
#31	"Dev works at TechCorp as a senior engineer",
#32	user_id="dev",
#33	metadata={"type": "professional"}
#34	)
#35
#36	# Arjun's preferences
#37	client.add(
#38	"Arjun prefers morning meetings and async communication",
#39	user_id="arjun",
#40	metadata={"type": "preference"}
#41	)
#42
#43	# Carl's project notes
#44	client.add(
#45	"Carl is leading the API redesign project, targeting Q2 launch",
#46	user_id="carl",
#47	metadata={"type": "project"}
#48	)
#49
#50	```
#51
#52	---
#53
#54	## Getting All Memories
#55
#56	Use `get_all()` with filters to retrieve everything for a specific user:
#57
#58	```python
#59	dev_memories = client.get_all(
#60	filters={"user_id": "dev"},
#61	page_size=50
#62	)
#63
#64	print(f"Total memories: {dev_memories['count']}")
#65	print(f"First memory: {dev_memories['results'][0]['memory']}")
#66
#67	```
#68
#69	Output:
#70
#71	```
#72	Total memories: 1
#73	First memory: Dev works at TechCorp as a senior engineer
#74
#75	```
#76
#77	<Info>
#78	Expected output: `get_all()` retrieved Dev's complete memory record. This method returns everything matching your filters—no semantic search, no ranking, just raw retrieval. Perfect for exports and audits.
#79	</Info>
#80
#81	You can filter by metadata to get specific types:
#82
#83	```python
#84	carl_projects = client.get_all(
#85	filters={
#86	"AND": [
#87	{"user_id": "carl"},
#88	{"metadata": {"type": "project"}}
#89	]
#90	}
#91	)
#92
#93	for memory in carl_projects['results']:
#94	print(memory['memory'])
#95
#96	```
#97
#98	Output:
#99
#100	```
#101	Carl is leading the API redesign project, targeting Q2 launch
#102
#103	```
#104
#105	---
#106
#107	## Searching Memories
#108
#109	When you need semantic search instead of retrieving everything, use `search()`:
#110
#111	```python
#112	results = client.search(
#113	query="What does Dev do for work?",
#114	filters={"user_id": "dev"},
#115	top_k=5
#116	)
#117
#118	for result in results['results']:
#119	print(f"{result['memory']} (score: {result['score']:.2f})")
#120
#121	```
#122
#123	Output:
#124
#125	```
#126	Dev works at TechCorp as a senior engineer (score: 0.89)
#127
#128	```
#129
#130	Search works across all memory fields and ranks by relevance. Use it when you have a specific question, use `get_all()` when you need everything.
#131
#132	---
#133
#134	## Exporting to Structured Format
#135
#136	For migrations or compliance, you can export memories into a structured schema using Pydantic-style JSON schemas.
#137
#138	### Step 1: Define the schema
#139
#140	```python
#141	professional_profile_schema = {
#142	"properties": {
#143	"full_name": {
#144	"type": "string",
#145	"description": "The person's full name"
#146	},
#147	"current_role": {
#148	"type": "string",
#149	"description": "Current job title or role"
#150	},
#151	"company": {
#152	"type": "string",
#153	"description": "Current employer"
#154	}
#155	},
#156	"title": "ProfessionalProfile",
#157	"type": "object"
#158	}
#159
#160	```
#161
#162	### Step 2: Create export job
#163
#164	```python
#165	export_job = client.create_memory_export(
#166	schema=professional_profile_schema,
#167	filters={"user_id": "dev"}
#168	)
#169
#170	print(f"Export ID: {export_job['id']}")
#171	print(f"Status: {export_job['status']}")
#172
#173	```
#174
#175	Output:
#176
#177	```
#178	Export ID: exp_abc123
#179	Status: processing
#180
#181	```
#182
#183	<Info>
#184	Export initiated: Status is "processing". Large exports may take a few seconds. Poll with `get_memory_export()` until status changes to "completed" before downloading data.
#185	</Info>
#186
#187	### Step 3: Download the export
#188
#189	```python
#190	# Get by ID
#191	export_data = client.get_memory_export(
#192	memory_export_id=export_job['id']
#193	)
#194
#195	print(export_data['data'])
#196
#197	```
#198
#199	Output:
#200
#201	```json
#202	{
#203	"full_name": "Dev",
#204	"current_role": "senior engineer",
#205	"company": "TechCorp"
#206	}
#207
#208	```
#209
#210	You can also retrieve exports by filters:
#211
#212	```python
#213	# Get latest export matching filters
#214	export_by_filters = client.get_memory_export(
#215	filters={"user_id": "dev"}
#216	)
#217
#218	print(export_by_filters['data'])
#219
#220	```
#221
#222	---
#223
#224	## Adding Export Instructions
#225
#226	Guide how Mem0 resolves conflicts or formats the export:
#227
#228	```python
#229	export_with_instructions = client.create_memory_export(
#230	schema=professional_profile_schema,
#231	filters={"user_id": "arjun"},
#232	export_instructions="""
#233	1. Use the most recent information if there are conflicts
#234	2. Only include confirmed facts, not speculation
#235	3. Return null for missing fields rather than guessing
#236	"""
#237	)
#238
#239	```
#240
#241	<Tip>
#242	Always check export status before downloading. Call `get_memory_export()` in a loop with a short delay until `status == "completed"`. Attempting to download while still processing returns incomplete data.
#243	</Tip>
#244
#245	---
#246
#247	## Platform Export
#248
#249	You can also export memories directly from the Mem0 platform UI:
#250
#251	1. Navigate to Memory Exports in your project dashboard
#252	2. Click Create Export
#253	3. Select your filters and schema
#254	4. Download the completed export as JSON
#255
#256	This is useful for one-off exports or manual data reviews.
#257
#258	<Warning>
#259	Exported data expires after 7 days. Download and store exports locally if you need long-term archives. After expiration, you'll need to recreate the export job.
#260	</Warning>
#261
#262	---
#263
#264	## What You Built
#265
#266	A complete memory export system with multiple retrieval methods:
#267
#268	- Bulk retrieval (get_all) - Fetch all memories matching filters for comprehensive audits
#269	- Semantic search - Query-based lookups with relevance scoring
#270	- Structured exports - Pydantic-schema exports for migrations and compliance
#271	- Export instructions - Guide conflict resolution and data formatting
#272	- Platform UI exports - One-off manual downloads via dashboard
#273
#274	This covers data portability, GDPR compliance, system migrations, and manual reviews.
#275
#276	---
#277
#278	## Summary
#279
#280	Use `get_all()` for bulk retrieval, `search()` for specific questions, and `create_memory_export()` for structured data exports with custom schemas. Remember exports expire after 7 days—download them locally for long-term archives.
#281
#282	<CardGroup cols={2}>
#283	<Card title="Expire Short-Term Data" icon="timer" href="/cookbooks/essentials/memory-expiration-short-and-long-term">
#284	Keep exports lean by clearing session context before you archive it.
#285	</Card>
#286	<Card title="Control Memory Ingestion" icon="filter" href="/cookbooks/essentials/controlling-memory-ingestion">
#287	Ensure only verified insights make it into your export pipeline.
#288	</Card>
#289	</CardGroup>
#290

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public