Developer Portal
Alchemyst Docs
HomeSDKsAPI ReferenceContext Plugin
Context

Update memory context data

POST
/api/v1/context/memory/update

This endpoint updates memory context data.

Authorization

bearerAuth
AuthorizationBearer <token>

In: header

Request Body

application/json

sessionId*string

The ID of the memory to update

contents*array<>

Array of updated content objects

Response Body

application/json

application/json

application/json

application/json

application/json

application/json

application/json

curl -X POST "https://example.com/api/v1/context/memory/update" \  -H "Content-Type: application/json" \  -d '{    "sessionId": "support-thread-TCK-1234",    "contents": [      {        "content": "Customer asked about pricing for the Scale plan.",        "metadata": {          "messageId": "msg-1"        },        "role": "user",        "id": "msg-1",        "createdAt": "2025-01-10T12:34:56.000Z"      },      {        "content": "Updated answer about the Scale plan pricing after discounts.",        "metadata": {          "messageId": "msg-2"        },        "role": "assistant",        "id": "msg-2",        "createdAt": "2025-01-10T12:36:00.000Z"      }    ]  }'
{  "success": true,  "memory_id": "string",  "updated_entries": 0}

Search for context data in the context processor POST

This endpoint sends a search request to the context processor to retrieve relevant context data based on the provided query.

Search context and generate an LLM-powered answer POST

This endpoint performs a context search using the context processor, joins all matching context chunks into a single string, then sends that joined context along with the user's query to an LLM to produce a natural-language answer grounded in the retrieved context. By default the response only includes the generated `answer`. Pass `?context=true` to also receive the joined context string that was used to ground the answer.