adm_ai_rag_chunks_v

Detailed view of RAG chunks with collection, file and document information, the chunk text and the embedding status, for monitoring chunk and embedding progress. AI Pack.

Overview

Group: Administrative reporting

Category: RAG collections - Monitoring of RAG collections: files, chunks, queue and search log

Use Cases

Inspect the chunks a document was split into
Find chunks that are still waiting for an embedding

Columns

The view contains 19 columns providing comprehensive information:

Column Name	Description
`rag_chunk_id`	Primary key of the RAG chunk.
`rag_collection_file_id`	Foreign key to the RAG collection file.
`chunk_index`	Sequential index of the chunk within the document.
`chunk_start_pos`	Start position of the chunk within the document content.
`chunk_length`	Length of the chunk in characters.
`embedded_at`	Timestamp when the chunk was embedded in the vector database.
`created_date`	Timestamp when the chunk was created.
`created_by`	User who created the chunk.
`rag_collection_id`	Foreign key to the RAG collection.
`collection_name`	Name of the RAG collection.
`file_is_active`	Y if the parent file is currently active in the collection.
`version_id`	Foreign key to the document version.
`document_id`	Foreign key to the document.
`document_name`	Name of the document.
`file_mime_type`	MIME type of the document.
`version_number`	Version number of the document.
`chunk_text`	The actual text content of the chunk extracted from the document.
`embedding_status`	Status of the chunk: EMBEDDED or PENDING.
`hours_since_created`	Hours elapsed since the chunk was created.

Description: Detailed view of RAG chunks with collection, file, and document information for monitoring chunk status and embedding progress.

Key Features

One row per chunk
Chunk text cut from the indexed text of the version
Embedding status EMBEDDED or PENDING