Feat: pptx and xlsx loader (#1118)

* perf: plan tip

* perf: upload size controller

* feat: add image ttl index

* feat: new upload file ux

* remove file

* feat: support read pptx

* feat: support xlsx

* fix: rerank docker flie
This commit is contained in:
Archer
2024-04-01 19:01:26 +08:00
committed by GitHub
parent f9d266a6af
commit 21288d1736
90 changed files with 2707 additions and 1678 deletions

View File

@@ -2,6 +2,7 @@ import { PushDatasetDataChunkProps } from '@fastgpt/global/core/dataset/api';
import {
DatasetSearchModeEnum,
DatasetTypeEnum,
ImportDataSourceEnum,
TrainingModeEnum
} from '@fastgpt/global/core/dataset/constants';
import {
@@ -67,3 +68,24 @@ export type SearchTestResponse = {
similarity: number;
usingQueryExtension: boolean;
};
/* =========== training =========== */
export type PostPreviewFilesChunksProps = {
type: `${ImportDataSourceEnum}`;
sourceId: string;
chunkSize: number;
overlapRatio: number;
customSplitChar?: string;
};
export type PostPreviewFilesChunksResponse = {
fileId: string;
rawTextLength: number;
chunks: string[];
}[];
export type PostPreviewTableChunksResponse = {
fileId: string;
totalChunks: number;
chunks: { q: string; a: string; chunkIndex: number }[];
errorText?: string;
}[];

View File

@@ -1,5 +0,0 @@
/* ================= dataset ===================== */
/* ================= collection ===================== */
/* ================= data ===================== */