Skip to content

Latest commit

 

History

History
35 lines (26 loc) · 1.87 KB

File metadata and controls

35 lines (26 loc) · 1.87 KB

Chat

Conversational search request handled by Manticore Buddy via CALL CHAT. When this object is set, the /search endpoint answers through an LLM using KNN-retrieved rows as context instead of returning regular search hits. Required fields are query, table, and model_name. Chat model management (CREATE CHAT MODEL, etc.) remains SQL-only. For more information see Conversational search

Properties

Name Type Description Notes
query str User question to send to the chat model
table str Vectorized table to retrieve context from
model_name str Name of the chat model
conversation_uuid str Existing conversation id to continue the dialog, or an empty string to start a new conversation. If omitted, a new id is generated. [optional]
vector_field str A specific vector field to search by. If omitted, Buddy uses the first `FLOAT_VECTOR` field from `SHOW CREATE TABLE`. [optional]
fields str Legacy alias for `vector_field`. A request must not include both `vector_field` and `fields`. [optional]

Example

from manticoresearch.models.chat import Chat

# TODO update the JSON string below
json = "{}"
# create an instance of Chat from a JSON string
chat_instance = Chat.from_json(json)
# print the JSON string representation of the object
print(Chat.to_json())

# convert the object into a dict
chat_dict = chat_instance.to_dict()
# create an instance of Chat from a dict
chat_from_dict = Chat.from_dict(chat_dict)

[Back to Model list] [Back to API list] [Back to README]