Skip to content

[FEA]: Add support for arbitrary text chunks passed as list #2345

Description

@randerzander

Is this a new feature, an improvement, or a change to existing functionality?

New Feature

How would you describe the priority of this feature request

Significant improvement

Please provide a clear description of problem this feature solves

Some users have custom ingestion jobs for pulling chunks from JIRA, remote document stores, and web services of many kinds.

Instead of making a custom pipeline for those, it'd be convenient for NRL to make it super easy to ingest lists of text chunks. It should support go through the default text splitting, embedding, and writing to VDB tasks.

Describe the feature, and optionally a solution or implementation and any alternatives

Something like:

def get_remote_data():
   return ["some chunk", "another chunk"]

ingestor.chunks(get_remote_data())
.embed()
.vdb_upload()

Additional context

No response

Metadata

Metadata

Assignees

Type

No type

Fields

No fields configured for issues without a type.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions