API Reference

Body

application/json

user_id

string

required

User ID

query

string

required

Chat query message

readable_cube_ids

string[]

List of cube IDs user can read for multi-cube chat

writable_cube_ids

string[]

List of cube IDs user can write for multi-cube chat

history

object[]

Chat history

mode

string

Enumeration for search modes.

Enum:"fast""fine""mixture"

system_prompt

string

Base system prompt to use for chat

top_k

number

default: 10

Number of results to return

session_id

string

Session ID for soft-filtering memories

include_preference

boolean

default: true

Whether to handle preference memory

pref_top_k

number

default: 6

Number of preference results to return

model_name_or_path

string

Model name to use for chat

max_tokens

number

Max tokens to generate

temperature

number

Temperature for sampling

top_p

number

Top-p (nucleus) sampling parameter

add_message_on_answer

boolean

default: true

Add dialogs to memory after chat

filter

object

Filter for the memory

internet_search

boolean

default: false

Whether to use internet search

threshold

number

default: 0.5

Threshold for filtering references

moscube

boolean

default: false

(Deprecated) Whether to use legacy MemOSCube pipeline.

mem_cube_id

string

(Deprecated) Single cube ID to use for chat. Prefer `readable_cube_ids` / `writable_cube_ids` for multi-cube chat.

Response

text/event-stream

Successful Response