GPT Embed

Specifies the identifier of the OpenAI-compatible model that will be used to generate vector embeddings for each text chunk. The list of available models is provided by the configured LLM Connector and may include official OpenAI models (such as text-embedding-ada-002) or custom/third-party models.

Changing this value determines the dimensionality, quality, and cost of the generated embeddings. Choose a model that is compatible with your embedding requirements and API provider. For example, use text-embedding-ada-002 for general-purpose semantic search, or select a custom model if your provider supports it.

If true, any previously generated embeddings for the document (with the same model and chunking settings) will be replaced. If false, embeddings will only be generated if they do not already exist for the current configuration.

Set this to false in production to avoid unnecessary API calls and costs, unless you need to refresh embeddings due to model or chunking changes. For example, if you update the 'Model' or 'Chunking' settings, set 'Overwrite' to true to ensure embeddings are regenerated.

Controls how the document text is split into segments (chunks) before generating embeddings. Proper chunking improves the quality and relevance of semantic search and retrieval.

The Chunk Settings object allows you to specify chunk size, overlap, and other options. Adjust these settings to optimize for your document types and search requirements. For example, use a chunk size of 500 tokens with 50-token overlap for long-form documents, or smaller chunks for short documents.

Smaller chunks provide finer search granularity but may lose context; larger chunks preserve more context but may dilute search precision. Overlapping chunks can help maintain context across boundaries.

A combination of the following flags:

The Error Disposition property determines the system's response to errors that occur while executing the activity.

• Flag: The affected Batch Folder or Batch Page will be flagged for review.
• Log: The error will be written to the Grooper event log.
• Stop: Processing will halt, the Batch will be set to an error state, and all pending tasks will be deleted.

You can combine multiple options using the IssueDisposition flags.
Adjust this property to match your organization's error handling and escalation policies.

If the number of consecutive errors reaches this value, a critical stop will occur and the Activity Processing service will halt further processing.

• Use this property to prevent runaway failures and to ensure that persistent errors are escalated for review.
• Set to a higher value to allow more retries before stopping, or to a lower value for stricter error control.

Can be one of the following values:

The Concurrency Mode property determines whether the activity can be executed in parallel across multiple Batch Objects, or if it must run sequentially.

• This setting affects which Processing Queue the activity is submitted to and how tasks are distributed.
• Choose the appropriate mode based on the activity's thread safety and resource requirements.