| question |
str |
User question |
|
| allowed_relationship_types |
[AllowedRelationshipType] |
Filter relationships and search results based on allowed relationship type combinations. When specified, only relationships matching the allowed types are returned (e.g. for view-only users). |
[optional] |
| include_hidden |
bool |
If true, includes hidden objects in search and visualization building. If false (default), excludes objects where isHidden=true. |
[optional] if omitted the server will use the default value of False |
| limit_create |
int |
Maximum number of created results. |
[optional] if omitted the server will use the default value of 3 |
| limit_create_context |
int |
Maximum number of relevant objects included into context for LLM (for each object type). |
[optional] if omitted the server will use the default value of 10 |
| limit_search |
int |
Maximum number of search results. |
[optional] if omitted the server will use the default value of 5 |
| object_types |
[str] |
List of object types to filter the search and visualization building. If empty or null, all object types are considered. |
[optional] |
| relevant_score_threshold |
float |
Score, above which we return found objects. Below this score objects are not relevant. |
[optional] if omitted the server will use the default value of 0.45 |
| search_score_threshold |
float |
Score, above which we return found object(s) and don't call LLM to create new objects. |
[optional] if omitted the server will use the default value of 0.9 |
| thread_id_suffix |
str |
Chat History thread suffix appended to ID generated by backend. Enables more chat windows. |
[optional] |
| title_to_descriptor_ratio |
float |
Temporary for experiments. Ratio of title score to descriptor score. |
[optional] if omitted the server will use the default value of 0.7 |
| user_context |
UserContext |
|
[optional] |
| any string name |
bool, date, datetime, dict, float, int, list, str, none_type |
any string name can be used but the value must be the correct type |
[optional] |