curl --request POST \
--url https://api.trieve.ai/api/chunk_group/group_oriented_search \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--header 'TR-Dataset: <tr-dataset>' \
--data '{
"filters": {
"must": [
{
"field": "tag_set",
"match_all": [
"A",
"B"
]
},
{
"field": "num_value",
"range": {
"gte": 10,
"lte": 25
}
}
]
},
"get_total_pages": true,
"group_size": 1,
"highlight_options": {
"highlight_delimiters": [
"<string>"
],
"highlight_max_length": 1,
"highlight_max_num": 1,
"highlight_results": true,
"highlight_strategy": "exactmatch",
"highlight_threshold": 123,
"highlight_window": 1,
"post_tag": "<string>",
"pre_tag": "<string>"
},
"metadata": "<any>",
"page": 1,
"page_size": 1,
"query": {
"image_url": "<string>",
"llm_prompt": "<string>"
},
"remove_stop_words": true,
"score_threshold": 123,
"scoring_options": {
"fulltext_boost": {
"boost_factor": 123,
"phrase": "<string>"
},
"semantic_boost": {
"distance_factor": 123,
"phrase": "<string>"
}
},
"search_type": "fulltext",
"slim_chunks": true,
"sort_options": {
"location_bias": {
"bias": 123,
"location": {
"lat": 123,
"lon": 123
}
},
"mmr": {
"mmr_lambda": 123,
"use_mmr": true
},
"recency_bias": 123,
"sort_by": {
"direction": "desc",
"field": "<string>",
"prefetch_amount": 1
},
"tag_weights": {},
"use_weights": true
},
"typo_options": {
"correct_typos": true,
"disable_on_word": [
"<string>"
],
"one_typo_word_range": {
"max": 1,
"min": 1
},
"prioritize_domain_specifc_words": true,
"two_typo_word_range": {
"max": 1,
"min": 1
}
},
"use_quote_negated_terms": true,
"user_id": "<string>"
}'
{
"corrected_query": "<string>",
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"results": [
{
"chunks": [
{
"chunk": {
"chunk_html": "<p>Some HTML content</p>",
"content": "Some content",
"id": "d290f1ee-6c54-4b01-90e6-d701748f0851",
"link": "https://example.com",
"metadata": {
"key1": "value1",
"key2": "value2"
},
"time_stamp": "2021-01-01 00:00:00.000",
"weight": 0.5
},
"highlights": [
"highlight is two tokens: high, light",
"whereas hello is only one token: hello"
],
"score": 0.5
}
],
"file_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"group": {
"created_at": "2021-01-01 00:00:00.000",
"dataset_id": "e3e3e3e3-e3e3-e3e3-e3e3-e3e3e3e3e3e3",
"description": "All versions and colorways of the oversized t-shirt",
"metadata": {
"foo": "bar"
},
"name": "Versions of Oversized T-Shirt",
"tag_set": [
"tshirt",
"oversized",
"clothing"
],
"tracking_id": "SNOVERSIZEDTSHIRT",
"updated_at": "2021-01-01 00:00:00.000"
}
}
],
"total_pages": 123
}
This route allows you to get groups as results instead of chunks. Each group returned will have the matching chunks sorted by similarity within the group. This is useful for when you want to get groups of chunks which are similar to the search query. If choosing hybrid search, the top chunk of each group will be re-ranked using scores from a cross encoder model. Compatible with semantic, fulltext, or hybrid search modes.
curl --request POST \
--url https://api.trieve.ai/api/chunk_group/group_oriented_search \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--header 'TR-Dataset: <tr-dataset>' \
--data '{
"filters": {
"must": [
{
"field": "tag_set",
"match_all": [
"A",
"B"
]
},
{
"field": "num_value",
"range": {
"gte": 10,
"lte": 25
}
}
]
},
"get_total_pages": true,
"group_size": 1,
"highlight_options": {
"highlight_delimiters": [
"<string>"
],
"highlight_max_length": 1,
"highlight_max_num": 1,
"highlight_results": true,
"highlight_strategy": "exactmatch",
"highlight_threshold": 123,
"highlight_window": 1,
"post_tag": "<string>",
"pre_tag": "<string>"
},
"metadata": "<any>",
"page": 1,
"page_size": 1,
"query": {
"image_url": "<string>",
"llm_prompt": "<string>"
},
"remove_stop_words": true,
"score_threshold": 123,
"scoring_options": {
"fulltext_boost": {
"boost_factor": 123,
"phrase": "<string>"
},
"semantic_boost": {
"distance_factor": 123,
"phrase": "<string>"
}
},
"search_type": "fulltext",
"slim_chunks": true,
"sort_options": {
"location_bias": {
"bias": 123,
"location": {
"lat": 123,
"lon": 123
}
},
"mmr": {
"mmr_lambda": 123,
"use_mmr": true
},
"recency_bias": 123,
"sort_by": {
"direction": "desc",
"field": "<string>",
"prefetch_amount": 1
},
"tag_weights": {},
"use_weights": true
},
"typo_options": {
"correct_typos": true,
"disable_on_word": [
"<string>"
],
"one_typo_word_range": {
"max": 1,
"min": 1
},
"prioritize_domain_specifc_words": true,
"two_typo_word_range": {
"max": 1,
"min": 1
}
},
"use_quote_negated_terms": true,
"user_id": "<string>"
}'
{
"corrected_query": "<string>",
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"results": [
{
"chunks": [
{
"chunk": {
"chunk_html": "<p>Some HTML content</p>",
"content": "Some content",
"id": "d290f1ee-6c54-4b01-90e6-d701748f0851",
"link": "https://example.com",
"metadata": {
"key1": "value1",
"key2": "value2"
},
"time_stamp": "2021-01-01 00:00:00.000",
"weight": 0.5
},
"highlights": [
"highlight is two tokens: high, light",
"whereas hello is only one token: hello"
],
"score": 0.5
}
],
"file_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"group": {
"created_at": "2021-01-01 00:00:00.000",
"dataset_id": "e3e3e3e3-e3e3-e3e3-e3e3-e3e3e3e3e3e3",
"description": "All versions and colorways of the oversized t-shirt",
"metadata": {
"foo": "bar"
},
"name": "Versions of Oversized T-Shirt",
"tag_set": [
"tshirt",
"oversized",
"clothing"
],
"tracking_id": "SNOVERSIZEDTSHIRT",
"updated_at": "2021-01-01 00:00:00.000"
}
}
],
"total_pages": 123
}
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.
The API version to use for this request. Defaults to V2 for orgs created after July 12, 2024 and V1 otherwise.
V1
, V2
JSON request payload to semantically search over groups
The body is of type object
.
Group chunks which are similar to the embedding vector of the search query
The response is of type object
.
Was this page helpful?