Navigating the Usage Dashboard

All your usage information is visible on the Usage dashboard, which you can access from your profile. Click your initials in the top right corner and choose Usage.

The top of the dashboard shows a summary of all the information. To see how the data breaks down by pipeline, check the table at the bottom of the dashboard.

You can check the following information:

1. Organization and usage cycle: Your organization name and the timeframe for the usage data.

2. Development pipelines: The number of pipelines set to a "development" service level that is currently deployed. Note that only deployed pipelines count towards the usage.
   To learn more about development pipelines, see Pipeline Service Levels.

3. Production pipelines: The number of pipelines set to a "production" service level that is currently deployed. Only deployed pipelines are considered.
   To understand production pipelines, see Pipeline Service Levels.

4. Document storage units (DSU): This number shows how much vector storage you're using.
   When you upload and index your files, we split them into smaller pieces called documents. These documents are stored and your DSU count depends on two key factors:

   • How many documents your files are split into.
   • The size (dimensionality) of the embedding model used to process them.

   The more documents or the larger the model, the more storage units you use.

   Calculating DSUs

   To calculate DSUs, we multiply the number of stored documents by a multiplier that reflects the embedding model's dimensionality:

   • A standard embedding model with 768 dimensions uses a multiplier of 1.
   • A larger model with 1,536 dimensions uses a multiplier of 2, meaning it needs twice as much storage.
   • If you use keyword-based search or don't use vector storage, the multiplier is just 0.2, so it uses much less storage.

   Example
   Say you upload 5,000 files which are split into 83,697 documents:

   • With the standard embedding model (768 dimensions): 83,697 documents × 1 = 83,697 storage units
   • With a larger model (1,536 dimensions): 83,697 documents × 2 = 167,394 storage units
   • With keyword search only or no vector storage: 83,697 documents × 0.2 = 16,739.4 storage units

5. Development hours: The number of hours the development pipelines were deployed during this usage cycle. This includes pipelines that were deployed and later deleted. When a pipeline is inactive, no hours are metered. This metric also covers time spent on indexing.

6. Production hours: The number of hours your production pipelines were deployed within the current cycle, including time spent on indexing. This includes pipelines that were already deleted but contributed to production hours during this usage cycle.

At the bottom of the page, you can check the detailed usage per pipeline:

For each pipeline, you can check the number of hours it was at the development and production service level and the workspace it's in. Draft pipelines are pipelines that are undeployed.

Managing Your Storage

Predicting Your Storage Needs

The number of documents you get from your files depends on how you split them during indexing and the embedding dimensions of the model you use with your Embedder to obtain vector representations of your files. The formula for calculating document storage units is: number of documents * multiplier. The vector dimension of the embedding model determines the multiplier. A dimension of 768 equates to a multiplier of 1. A dimension of 1024 equates to a multiplier of 1.3.

Let's assume you use one of the recommended embedding models, like intfloat/e5-base-v2, which has a vector dimension of 768 (equal to a multiplier of 1) and default DocumentSplitter's settings, which are:

splitter:
      type: haystack.components.preprocessors.document_splitter.DocumentSplitter
      init_parameters:
        split_by: word
        split_length: 200

This configuration splits files by word, resulting in documents of 200 words each. To calculate the anticipated number of documents, divide the total word count of your files by 200.

For example, with 5,000 files, each containing 1000 words, you have a total of 5 million words. Divide this total by 200 (the default split length), and you get 25,000 documents. If you use the intfloat/e5-base-v2 model, you must now multiply the document count by 1. You obtain 25,000 document storage units.

Optimizing Storage Usage

As you near your storage capacity, you can reduce storage consumption by:

• Deleting duplicate files.
• Reducing irrelevant files, starting from the largest ones. Detecting irrelevant files is specific to your use case. You can use the Search History endpoint to check user queries, files, and documents used.
• Adjusting settings in DocumentSplitter:
  • If your split_overlap setting is high, consider decreasing it.
  • If your split_lengthIf the setting is low, try increasing it. Remember that it's important to avoid too large values to prevent Retriever and Generator nodes from cutting the documents.