Adding Knowledge Bases to the Tess AI Copilot
Let's explain how to add knowledge bases to your Copilot in Tess AI so that it can answer questions based on your specific information.
AI Models in Copilot: The Tess AI Copilot offers several AI models, many with unlimited generation (free use).
What are Knowledge Bases?: Knowledge bases are sets of information that you provide to the Copilot so that it can learn and answer questions based on them. This allows you to personalize the Copilot with your own data.
Adding a Knowledge Base: Click the clip icon in the Copilot chat to add a knowledge base. You can add different types of files, such as:
Audio
CSV
Excel
Google Sheets
PDF
Website URLs
Audio Transcription: When adding an audio file, you can choose between different transcription models (Deepgram, REV AI, Vision, Whisper) and the language.
Accessing the Knowledge Base: After adding the knowledge base, it will be available in the chat and the Copilot will use it to answer your questions. You can view and manage your knowledge bases at any time.
Multiple Knowledge Bases: You can add multiple knowledge bases at the same time, allowing the Copilot to learn from different sources of information.
Examples of Use:
Add your company's brand guide.
Add a PDF with specific information.
Transcribe and analyze audio from meetings.
What if I need a very large knowledge base in my knowledge base? Understanding RAG
In this case, we recommend using the RAG methodology, a functionality that allows you to expand the knowledge of your chat templates beyond what the models support in content volume, opening possibilities to create increasingly trained chats.
LLMs are trained on massive datasets, which allows them to generate text, translate languages, and answer questions in an impressive way. However, this knowledge is static to some extent, that is, if the LLM has a context window of 200k tokens, the content you will use to train it in the Knowledge Base cannot be larger than that.
RAG breaks this barrier, allowing your chats to access and read extra information, in addition to the attachments in the Knowledge Base, complementing the context provided and bringing more complete answers.
To do this, simply select the context mode (Context Mode *) as RAG, see example below
In practice, RAG does the reading through associations and mentions of certain topics. That is, bringing an example: you can insert a 50-page file, but in RAG, the AI will only search for what is related to your question.
What is the difference in credit consumption?
When adding a knowledge base, there is a small processing cost that will consume your credits only once, exactly to access your loaded base.
And it's usually very little, don't worry. Without an additional base and unlimited model, you don't spend any of your credits!
Conclusion
Add your knowledge bases to the Tess AI Copilot right now and personalize your experience!