h2oGPTe icon

h2oGPTe

h2oGPTe is an AI-powered search assistant for your internal teams to answer questions gleaned from large volumes of documents, websites and workplace content.

Actions198

Overview

This node operation creates a job to add plain text content into a specified collection within the system. It is designed for scenarios where users want to ingest raw textual data as documents into a collection for further processing, indexing, or querying. This is particularly useful when you have text data that is not in file form but needs to be added to a document management or AI search system.

Practical examples include:

  • Adding meeting notes or transcripts directly as documents.
  • Ingesting user-generated content or logs as searchable documents.
  • Feeding plain text from emails or chat messages into a knowledge base collection.

The operation submits a job request to the backend API to handle the ingestion asynchronously, allowing large texts or batch operations without blocking.

Properties

Name Meaning
Collection ID String ID of the collection to add the ingested documents into.
File Name The file name string to assign to the ingested document (for identification purposes).
Text The actual plain text content to be ingested into the collection.
Additional Options Optional settings including:
- Gen Doc Summaries: Boolean to auto-generate document summaries using a language model (LLM).
- Gen Doc Questions: Boolean to auto-generate sample questions for each document (uses LLM).
- Metadata: JSON-encoded string with metadata for the document.
- Timeout: Number specifying timeout in seconds for the ingestion job.

Output

The output will contain the full response from the API after creating the ingestion job. Typically, this includes details about the job such as its unique identifier, status, and any relevant metadata confirming the job creation.

The json output field will hold this response data, which can be used to track the job progress or retrieve results once the ingestion completes.

No binary data output is expected from this operation.

Dependencies

  • Requires an API key credential for authentication with the backend service.
  • The node sends HTTP POST requests to the endpoint /ingest/plain_text/job.
  • The API expects the text content in the request body with Content-Type: text/plain.
  • Query parameters are used to pass collection ID, file name, and additional options.

Troubleshooting

  • Missing Required Fields: Ensure collection_id, file_name, and text are provided; otherwise, the API will reject the request.
  • Timeouts: If the ingestion job takes too long, consider increasing the timeout option or check network connectivity.
  • Invalid Metadata: The metadata field must be a valid JSON string; invalid JSON will cause errors.
  • Authentication Errors: Verify that the API key credential is correctly configured and has permissions to create ingestion jobs.
  • API Endpoint Issues: Confirm the base URL and endpoint path are correct and accessible.

Links and References


This summary is based on static analysis of the node's properties and routing configuration for the "Creates a Job to Add Plain Text to a Collection" operation under the "Document Ingestion" resource.

Discussion