Platform APIs
- Client libraries
- GETList memory stores
- POSTCreate memory store
- GETRetrieve memory store
- DELDelete memory store
- PATCHUpdate memory store
- GETList all memories
- POSTCreate a new memory
- GETRetrieve a specific memory
- DELDelete a specific memory
- PATCHUpdate a specific memory
- GETList all documents for a memory
- POSTCreate a new memory document
- GETRetrieve a specific memory document
- DELDelete a specific memory document
- PATCHUpdate a specific memory document
- GET
Gateway APIs
curl --request POST \
--url https://api.orq.ai/v2/memory-stores \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"key": "<string>",
"embedding_config": {
"model": "<string>"
},
"description": "<string>",
"path": "Default",
"ttl": 123
}
'{
"_id": "<string>",
"key": "<string>",
"description": "<string>",
"created": "<string>",
"updated": "<string>",
"embedding_config": {
"model": "<string>"
},
"created_by_id": "<string>",
"updated_by_id": "<string>",
"ttl": 123
}Create memory store
curl --request POST \
--url https://api.orq.ai/v2/memory-stores \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"key": "<string>",
"embedding_config": {
"model": "<string>"
},
"description": "<string>",
"path": "Default",
"ttl": 123
}
'{
"_id": "<string>",
"key": "<string>",
"description": "<string>",
"created": "<string>",
"updated": "<string>",
"embedding_config": {
"model": "<string>"
},
"created_by_id": "<string>",
"updated_by_id": "<string>",
"ttl": 123
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
The unique key of the memory store. The key is unique and inmmutable and cannot be repeated within the same workspace.
Show child attributes
Show child attributes
The embeddings model to use for the knowledge base in the format "provider/model" for public models or "workspaceKey@provider/model" for private workspace models. This model will be used to embed the chunks when they are added to the knowledge base. Refer to the (Supported models)[/docs/proxy/supported-models] to browse available models.
The description of the memory store. Be as precise as possible to help the AI to understand the purpose of the memory store.
Entity storage path in the format: project/folder/subfolder/...
The first element identifies the project, followed by nested folders (auto-created as needed).
With project-based API keys, the first element is treated as a folder name, as the project is predetermined by the API key.
"Default"
The default time to live of every memory document created within the memory store. Useful to control if the documents in the memory should be store for short or long term.
Response
Memory store successfully created with the specified configuration.
The unique identifier of the memory store
The unique key of the memory store. The key is unique and inmmutable and cannot be repeated within the same workspace.
The description of the memory store. Be as precise as possible to help the AI to understand the purpose of the memory store.
The creation date of the memory store
The last update date of the memory store
Show child attributes
Show child attributes
The embeddings model to use for the knowledge base in the format "provider/model" for public models or "workspaceKey@provider/model" for private workspace models. This model will be used to embed the chunks when they are added to the knowledge base. Refer to the (Supported models)[/docs/proxy/supported-models] to browse available models.
The user ID of the creator
The user ID of the last updater
The default time to live of every memory document created within the memory store. Useful to control if the documents in the memory should be store for short or long term.
Was this page helpful?