Skip to main content
PUT
/
api
/
v2
/
config
/
memory
/
semantic
Update Semantic Memory Config
curl --request PUT \
  --url http://localhost:8080/api/v2/config/memory/semantic \
  --header 'Content-Type: application/json' \
  --data '
{
  "enabled": true,
  "database": "<string>",
  "storage_backend": "<string>",
  "feature_store": "<string>",
  "vector_collection": "<string>",
  "vector_dimensions": 1,
  "llm_model": "<string>",
  "embedding_model": "<string>",
  "ingestion_trigger_messages": 1,
  "ingestion_trigger_age_seconds": 1
}
'
{
  "success": true,
  "message": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://docs.memmachine.ai/llms.txt

Use this file to discover all available pages before exploring further.

Body

application/json

Partial update for semantic memory configuration.

​
enabled
boolean | null
Whether semantic memory is enabled. When set to true, the required
fields (database, llm_model, embedding_model) must also be configured.
Set to false to disable semantic memory entirely.
​
database
string | null
The ID of the database to use for semantic memory storage.
Must reference a database configured in the resources section. Used by
legacy semantic storage backends.
​
storage_backend
string | null
The storage backend used for semantic memory.
​
feature_store
string | null
The ID of the relational database resource used to store semantic feature
data when the semantic storage backend is `vector_store`.
​
vector_collection
string | null
The ID of the vector store resource used to store semantic feature
embeddings when the semantic storage backend is `vector_store`.
​
vector_dimensions
integer | null
The vector dimensions used for semantic memory embeddings. If omitted for
vector store storage, the configured embedder dimensions are used.
Required range: x > 0
​
llm_model
string | null
The ID of the language model to use for semantic memory extraction.
Must reference a language model configured in the resources section.
​
embedding_model
string | null
The ID of the embedder to use for semantic memory vector search.
Must reference an embedder configured in the resources section.
​
ingestion_trigger_messages
integer | null
The number of uningested messages that triggers an ingestion cycle.
Required range: x > 0
​
ingestion_trigger_age_seconds
integer | null
The maximum age (in seconds) of uningested messages before
triggering an ingestion cycle.
Required range: x > 0

Response

Successful Response

Response model for memory configuration update.

​
success
boolean
required
Whether the operation succeeded.
​
message
string
required
Status message describing the result of the operation.