klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Doc: MemoryExport update (#2132)

Browse Source
This commit is contained in:
Dev Khant
2025-01-10 00:00:18 +05:30
committed by GitHub
parent a6b9721ede
commit 9c4acdcba7
3 changed files with 146 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
docs/platform/quickstart.mdx
View File

@@ -1630,177 +1630,6 @@ curl -X DELETE "https://api.mem0.ai/v1/memories/batch/" \
```
</CodeGroup>
### 4.11 Create Memory Export
Submit a job to create a structured export of memories using a customizable Pydantic schema. This process may take some time to complete, especially if you’re exporting a large number of memories. You can tailor the export by applying various filters (e.g., `user_id`, `agent_id`, `run_id`, or `session_id`) and by modifying the Pydantic schema to ensure the final data matches your exact needs.
For example, if you want to extract professional profile information from memories, you can define a schema and export the memories in that structured format:
<CodeGroup>
```python Python
response = client.create_memory_export(schema=json_schema, user_id="user123")
print(response)
```
```bash cURL
curl -X POST "https://api.mem0.ai/v1/memories/export/" \
-H "Authorization: Token your-api-key" \
-H "Content-Type: application/json" \
-d '{
"schema":{json_schema},
"user_id": "user123"
}'
```
```json json_schema
{
"$defs": {
"EducationLevel": {
"enum": ["high_school", "bachelors", "masters"],
"title": "EducationLevel",
"type": "string"
},
"EmploymentStatus": {
"enum": ["full_time", "part_time", "student"],
"title": "EmploymentStatus",
"type": "string"
}
},
"example": {
"current_role": "Senior Software Engineer",
"education_level": "masters",
"employment_status": "full_time",
"full_name": "John Doe",
"skills": ["Python", "AWS", "Machine Learning"],
"years_experience": 8
},
"properties": {
"full_name": {
"anyOf": [
{
"maxLength": 100,
"minLength": 2,
"type": "string"
},
{
"type": "null"
}
],
"default": None,
"description": "The professional's full name",
"title": "Full Name"
},
"current_role": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": None,
"description": "Current job title or role",
"title": "Current Role"
},
"years_experience": {
"anyOf": [
{
"maximum": 70,
"minimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"default": None,
"description": "Years of professional experience",
"title": "Years Experience"
},
"employment_status": {
"anyOf": [
{
"$ref": "#/$defs/EmploymentStatus"
},
{
"type": "null"
}
],
"default": None,
"description": "Current employment status"
},
"education_level": {
"anyOf": [
{
"$ref": "#/$defs/EducationLevel"
},
{
"type": "null"
}
],
"default": None,
"description": "Highest level of education completed"
},
"skills": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": None,
"description": "Professional skills and competencies",
"title": "Skills"
}
},
"title": "ProfessionalProfile",
"type": "object"
}
```
```json Output
{
"message": "Memory export request received. The export will be ready in a few seconds.",
"id": "550e8400-e29b-41d4-a716-446655440000"
}
```
</CodeGroup>
### 4.12 Get Memory Export
Retrieve the structured export of memories after you have submitted a export job using the previous endpoint. It return the latest memory export.
<CodeGroup>
```python Python
response = client.get_memory_export(user_id="user123")
print(response)
```
```bash cURL
curl -X GET "https://api.mem0.ai/v1/memories/export/?user_id=user123" \
-H "Authorization: Token your-api-key"
```
```json Output
{
"full_name": "John Doe",
"current_role": "Senior Software Engineer",
"years_experience": 8,
"employment_status": "full_time",
"education_level": "masters",
"skills": ["Python", "AWS", "Machine Learning"]
}
```
</CodeGroup>
If you have any questions, please feel free to reach out to us using one of the following methods:
<Snippet file="get-help.mdx" />