Tess AI offers a wide range of AI models that can be used by the AI Copilot or in templates. However, even the most advanced LLMs (Large Language Models) have an inherent limitation: the training context window. This is where RAG (Retrieval-Augmented Generation) comes in, a feature that allows you to expand the knowledge of your chat templates beyond what the models can support in terms of content volume, opening up possibilities to create increasingly trained chats.
LLMs are trained on massive datasets, allowing them to generate text, translate languages, and answer questions impressively. However, this knowledge is static to a certain extent; that is, if the LLM has a context window of 200k tokens, the content you use to train it in the Knowledge Base cannot exceed that.
RAG breaks this barrier by allowing your chats to access and read additional information beyond the Knowledge Base attachments, complementing the provided context and bringing more comprehensive answers.
Reading the file with RAG: Tess AI provides the integration, and you only need to select the file to be used. In practice, RAG reads by making associations and mentions about specific topics. For example, you can insert a 50-page file, but in RAG, the AI will only retrieve what is related to your question. Because of this optimized work, RAG allows for the expansion of that LLM's context window.
Searching for information: After uploading a file via the RAG configuration, you can finalize the prompt of your template, and the reading will be done automatically.
1. Open "AI Studio"
2. Click on "Add New Agent"
[IMG]
3. When configuring the type of template, click on "Chat" and select "GPTs"
[IMG]
4. Open the Advanced Settings
[IMG]
5. Upload the files
[IMG]
RAG is a powerful tool to elevate your chats to a new level of intelligence and context. Try this feature in Tess AI and discover new usage possibilities with files and materials!
