# Total Ingestion Tokens for Integration Syncs #### Overview Total Tokens Ingested refers to the amount of data synced with Bind AI through [integrations](/docs/basics/integrations.md) such as GitHub, Google Drive, or direct file uploads. This data is stored as [vector database embeddings](https://blog.getbind.co/2024/02/23/what-are-vector-database/), allowing the AI to access relevant context when you ask questions based on your data. #### What is a Token? A token is a unit of data, roughly equivalent to 4 characters or a small word (e.g. "Moon", or "Bird"). The concept of tokens is used to measure the amount of data ingested and stored by Bind AI. **How are Tokens Ingested different from Compute points?** Token ingested are only applicable for the data synced via integrations and uploads. Compute points are utilized for model queries. Both of them are independent of each other. The easiest way to understand is a below: * When you connect integrations or upload file -> Ingestion Tokens are utilized * When you make a query or ask question to AI -> Compute points are utilized #### How It Works When you sync files from GitHub or Google Drive, the content of these files is converted into tokens. These tokens are then stored as vector embeddings, which the AI uses to provide context-aware assistance. This process enables Bind AI to retrieve the most relevant pieces of your data when generating code or answering queries. #### Accessing Synced Data The synced data is accessible via a custom bot URL: . This URL allows you to interact with the AI using the context provided by your synced data. #### Plan Limits The Total Tokens Ingested is subject to the limits specified in your Bind AI subscription plan. For detailed information on plan limits, please refer to the pricing page: . #### Important Notes * Ensure that you are aware of your plan's token limits to optimize your usage of Bind AI's capabilities. For any questions please contact us via the Support Chat. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://bind-ai.gitbook.io/docs/basics/total-ingestion-tokens-for-integration-syncs.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.