POST
/
api
/
message

Authorizations

Authorization
string
headerrequired

Headers

TR-Dataset
string
required

The dataset id or tracking_id to use for the request. We assume you intend to use an id if the value is a valid uuid.

Body

application/json
new_message_content
string
required

The content of the user message to attach to the topic and then generate an assistant message in response to.

topic_id
string
required

The ID of the topic to attach the message to.

concat_user_messages_query
boolean | null

If concat user messages query is set to true, all of the user messages in the topic will be concatenated together and used as the search query. If not specified, this defaults to false. Default is false.

context_options
object

Context options to use for the completion. If not specified, all options will default to false.

filters
object

ChunkFilter is a JSON object which can be used to filter chunks. This is useful for when you want to filter chunks by arbitrary metadata. Unlike with tag filtering, there is a performance hit for filtering on metadata.

highlight_options
object

Highlight Options lets you specify different methods to highlight the chunks in the result set. If not specified, this defaults to the score of the chunks.

llm_options
object

LLM options to use for the completion. If not specified, this defaults to the dataset's LLM options.

no_result_message
string | null

No result message for when there are no chunks found above the score threshold.

page_size
integer | null

Page size is the number of chunks to fetch during RAG. If 0, then no search will be performed. If specified, this will override the N retrievals to include in the dataset configuration. Default is None.

Required range: x > 0
score_threshold
number | null

Set score_threshold to a float to filter out chunks with a score below the threshold. This threshold applies before weight and bias modifications. If not specified, this defaults to 0.0.

search_query
string | null

Query is the search query. This can be any string. The search_query will be used to create a dense embedding vector and/or sparse vector which will be used to find the result set. If not specified, will default to the last user message or HyDE if HyDE is enabled in the dataset configuration. Default is None.

search_type
enum<string>
Available options:
fulltext,
semantic,
hybrid,
bm25
sort_options
object

Sort Options lets you specify different methods to rerank the chunks in the result set. If not specified, this defaults to the score of the chunks.

use_group_search
boolean | null

If use_group_search is set to true, the search will be conducted using the search_over_groups api. If not specified, this defaults to false.

user_id
string | null

The user_id is the id of the user who is making the request. This is used to track user interactions with the RAG results.

Response

200 - text/plain

The response is of type string.