POST
/
generate_user_memory
curl --request POST \
  --url https://api.usecortex.ai/generate_user_memory \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "query": "I had a productive meeting with the sales team about Q2 targets",
  "user_name": "John Doe"
}'
[
  {}
]

Automatically generates and saves echo memories based on a user query. This is the most sophisticated endpoint that combines query processin and memory generation for your end users.

​
Sample Request

curl --location 'https://api.usecortex.ai/generate_user_memory' \
  --header 'Authorization: Bearer {API_KEY}' \
  --header 'accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
    "query": "{USER_QUERY}",
    "user_name": "{USER_NAME}"
  }'

​
🔐 Headers

  • Authorization: Bearer token (Firebase token)
  • accept: application/json
  • Content-Type: application/json

​
🧾 Body Parameters

  • query (string, required): User query to generate memories from
  • user_name (string, required): Name of the user for personalization

​
📋 Functionality

  • Takes user query and user name from request
  • Rewrites the user query using OpenAI (without clarifications)
  • Generates multiple echo memories based on both original and rewritten queries
  • Automatically inserts all generated memories into the vector store
  • Returns the list of generated echo memories
  • Most sophisticated endpoint combining query processing, memory generation, and storage

​
📤 Response

Returns an array of generated echo memory objects that were created and stored.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Response

200 - application/json

Generated memories returned successfully

The response is of type object[].

POST
/
generate_user_memory
curl --request POST \
  --url https://api.usecortex.ai/generate_user_memory \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "query": "I had a productive meeting with the sales team about Q2 targets",
  "user_name": "John Doe"
}'
[
  {}
]

Automatically generates and saves echo memories based on a user query. This is the most sophisticated endpoint that combines query processin and memory generation for your end users.

​
Sample Request

curl --location 'https://api.usecortex.ai/generate_user_memory' \
  --header 'Authorization: Bearer {API_KEY}' \
  --header 'accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
    "query": "{USER_QUERY}",
    "user_name": "{USER_NAME}"
  }'

​
🔐 Headers

  • Authorization: Bearer token (Firebase token)
  • accept: application/json
  • Content-Type: application/json

​
🧾 Body Parameters

  • query (string, required): User query to generate memories from
  • user_name (string, required): Name of the user for personalization

​
📋 Functionality

  • Takes user query and user name from request
  • Rewrites the user query using OpenAI (without clarifications)
  • Generates multiple echo memories based on both original and rewritten queries
  • Automatically inserts all generated memories into the vector store
  • Returns the list of generated echo memories
  • Most sophisticated endpoint combining query processing, memory generation, and storage

​
📤 Response

Returns an array of generated echo memory objects that were created and stored.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Response

200 - application/json

Generated memories returned successfully

The response is of type object[].