TeamAI's Knowledge feature, also known as AI Data Hubs, allows builders to provide additional context to their AI agents(GPTs) by uploading relevant files. This article will guide you through the process of using Knowledge in your agents, highlighting its benefits and best practices.
What is Knowledge?
Knowledge, or Data Hubs, is a feature in TeamAI that enables builders to attach multiple collections, documents, and files to an agent. Unlike ChatGPT, which only allows attaching up to 20 files to a GPT, TeamAI provides greater flexibility in the number of files you can include.
How does Knowledge work?
Using the agent configure editor tab, select the desired collections or documents to your agent.
The GPT breaks the text into chunks, creates embeddings (mathematical representations of text), and stores them for later use.
When a user interacts with your GPT, the agent can access the uploaded files to obtain additional context and augment the user's query.
The GPT chooses one of the following methods based on the requirements of the user's prompt:
Semantic search: Returns relevant text chunks, preferred for "Q&A" style prompts where a specific portion of the source document is required.
Document review: Returns entire short documents and/or relevant excerpts of larger documents, including them along with the prompt as additional context.
The Knowledge Access Process
You ask your agent a question related to the information contained in your data hubs.
The agent searches through the selected data hubs to find relevant information.
The agent uses this information to provide a more accurate and contextually relevant response to your query.
By granting your agent access to data hubs, you can unlock their full potential and enable them to provide more valuable insights and assistance.
When to use Knowledge
Currently, the only way to manage files attached to a GPT in TeamAI is through the Data Hubs (Knowledge) feature. This makes it best suited for applications where context changes infrequently, such as employee handbooks, policy documents, or school curricula.
For more information on Data Hubs, refer to the following related documents:
Tips for getting the most out of Knowledge
- Agent to rely on Knowledge first before searching the internet or using any other custom plugin.
- Agents to "cite their sources" when providing information from the data hubs.
Best Practices for Data Hub Access
Only select collections and data hubs that are relevant to the tasks your agent will be performing to keep their knowledge focused and improve response accuracy.
Regularly review and update the data hub your agent has access to, ensuring they have the most up-to-date information.
If you have sensitive information in your data hubs, consider creating separate collections or data hubs specifically for your agent's use, rather than granting them access to your entire library.
By leveraging the power of Knowledge in TeamAI, you can create AI agents that provide more accurate, context-aware, and valuable responses to user queries.