Skip to content

Ai for service dev #749

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ashishguptaiitb merged 4 commits into from
Jun 26, 2026
Merged

Ai for service dev #749

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
24d28a6
Chunk Delete endpoint change
ShrutiKu-Kore Jun 26, 2026
260b59e
Update agentic-rag-and-business-rules.mdx
ShrutiKu-Kore Jun 26, 2026
377d03d
Update youtube.mdx
vishnubkore Jun 26, 2026
a89db09
Merge branch 'ai-for-service-dev' of https://github.com/Koredotcom/do…
vishnubkore Jun 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions ai-for-service/apis/searchai/chunk-apis.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,7 +150,7 @@ This API enables targeted deletion of indexed content without a full re-index. P
| Field | Value |
|---|---|
| **Method** | POST |
| **URL** | `/api/public/bot/{AppId}/search/delete-chunks-by-cond` |
| **URL** | `/api/public/bot/{AppId}/search/deleteChunksById` |
| **Content-Type** | `application/json` |
| **Authentication** | `auth: <JWT Token>` |
| **API Scope** | Chunk Management |
Expand All @@ -172,7 +172,7 @@ This API enables targeted deletion of indexed content without a full re-index. P
**Example: Delete by chunkId**

```bash
curl --location 'https://<HOST>/api/public/bot/<BOT_ID>/search/delete-chunks-by-cond' \
curl --location 'https://<HOST>/api/public/bot/<BOT_ID>/search/deleteChunksById' \
--header 'auth: <JWT_TOKEN>' \
--header 'Content-Type: application/json' \
--data '{
Expand All @@ -190,6 +190,7 @@ curl --location 'https://<HOST>/api/public/bot/<BOT_ID>/search/delete-chunks-by-
| `totalRequested` | Number of chunks requested for deletion. |
| `totalDeleted` | Number of chunks successfully deleted. |
| `totalNotFound` | Number of chunks that were not found. |
|`notFoundChunkIds`| Array of chunk Ids that were not found|

#### Sample Response

Expand All @@ -199,7 +200,8 @@ curl --location 'https://<HOST>/api/public/bot/<BOT_ID>/search/delete-chunks-by-
"Data": {
"totalRequested": 4,
"totalDeleted": 4,
"totalNotFound": 0
"totalNotFound": 0,
"notFoundChunkIds": []
}
}
```
Expand Down
4 changes: 0 additions & 4 deletions ai-for-service/searchai/agentic-rag-and-business-rules.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,10 +67,6 @@ Example:
- Extracted fields: Assignee, Status, Priority
- Action: Filter applied (no boost needed)

### Supported Models

Currently, only **OpenAI 4.0** and **Azure OpenAI 4.0** models are supported for Agentic RAG.

### Enabling Agentic RAG

**Prerequisites**
Expand Down
6 changes: 3 additions & 3 deletions ai-for-service/searchai/connectors/youtube.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,7 +143,7 @@ Once the sync is complete, go to the **Content** tab to review the ingested cont
The system converts each synced video into a single Markdown document. It extracts and indexes the following key fields:

- `title` - The video title.
- `content` - The full transcript organized by chapters (if available) with timestamps, plus the first 2,000 characters of the video description.
- `content` - The full transcript organized by chapters (if available) with timestamps.
- `doc_id` - A unique identifier for the ingested video document, derived from the YouTube video ID.
- `doc_source_type` - Identifies the source as a YouTube video.
- `doc_created_on` / `doc_updated_on` - Timestamp of video publishing and last update.
Expand All @@ -165,7 +165,7 @@ Each ingested video document follows this structured layout:

## Description

<First 2,000 characters of the video description>
<Description>

## Chapter Title 1 (0:00)

Expand All @@ -191,7 +191,7 @@ The connector fetches video captions or transcripts using the YouTube Captions A
| 4th | Auto-generated captions in any language |

- If a video has no captions at all, it's still synced - the video metadata and description are indexed without a transcript.
- Chapter markers in the video description (for example: `0:00 Introduction`, `5:30 Setup`) are automatically detected and used to organize the transcript into sections.
- Chapter markers in the video description (for example: `0:00 Introduction`, `5:30 Setup`) are automatically detected and used to organize the transcript into sections. This affects only the organization of content within each chunk. Chunks are still created using [token-based](/ai-for-service/searchai#chunking-strategies) splitting, regardless of chapter boundaries.

## API Quota

Expand Down
Loading