Collection tag (#2266)

* feat: collection metadata filter (#2211)

* feat: add dataset collection tags (#2231)

* dataset page

* workflow page

* move

* fix

* add plus filter

* fix

* fix

* fix

* perf: collection tag code

* fix: collection tags (#2249)

* fix

* fix

* fix tags of dataset page

* fix tags of workflow page

* doc

* add comments

* fix: collection tags (#2264)

* fix: metadata filter

* feat: search filter

---------

Co-authored-by: heheer <1239331448@qq.com>
Co-authored-by: heheer <heheer@sealos.io>
This commit is contained in:
Archer
2024-08-05 12:08:46 +08:00
committed by GitHub
parent 56f6e69bc7
commit fe71efbbd2
46 changed files with 1914 additions and 112 deletions

View File

@@ -119,14 +119,44 @@ export class PgVectorCtrl {
}
};
embRecall = async (props: EmbeddingRecallCtrlProps): Promise<EmbeddingRecallResponse> => {
const { teamId, datasetIds, vector, limit, forbidCollectionIdList, retry = 2 } = props;
const {
teamId,
datasetIds,
vector,
limit,
forbidCollectionIdList,
filterCollectionIdList,
retry = 2
} = props;
// Get forbid collection
const formatForbidCollectionIdList = (() => {
if (!filterCollectionIdList) return forbidCollectionIdList;
const list = forbidCollectionIdList
.map((id) => String(id))
.filter((id) => !filterCollectionIdList.includes(id));
return list;
})();
const forbidCollectionSql =
forbidCollectionIdList.length > 0
? `AND collection_id NOT IN (${forbidCollectionIdList.map((id) => `'${String(id)}'`).join(',')})`
: 'AND collection_id IS NOT NULL';
// const forbidDataSql =
// forbidEmbIndexIdList.length > 0 ? `AND id NOT IN (${forbidEmbIndexIdList.join(',')})` : '';
formatForbidCollectionIdList.length > 0
? `AND collection_id NOT IN (${formatForbidCollectionIdList.map((id) => `'${id}'`).join(',')})`
: '';
// Filter by collectionId
const formatFilterCollectionId = (() => {
if (!filterCollectionIdList) return;
return filterCollectionIdList
.map((id) => String(id))
.filter((id) => !forbidCollectionIdList.includes(id));
})();
const filterCollectionIdSql = formatFilterCollectionId
? `AND collection_id IN (${formatFilterCollectionId.map((id) => `'${id}'`).join(',')})`
: '';
// Empty data
if (formatFilterCollectionId && formatFilterCollectionId.length === 0) {
return { results: [] };
}
try {
// const explan: any = await PgClient.query(
@@ -150,6 +180,7 @@ export class PgVectorCtrl {
from ${DatasetVectorTableName}
where team_id='${teamId}'
AND dataset_id IN (${datasetIds.map((id) => `'${String(id)}'`).join(',')})
${filterCollectionIdSql}
${forbidCollectionSql}
order by score limit ${limit};
COMMIT;`