Welcome to the Central Hub View release of CamelotAI! This version introduces a central upload for you documents on the DocumentClient View and faster access to pdf viewers. This version does not have a dashboard and everything can be done from the Document Client View. The following are the added features:
Features
Multiple Document Upload: Users can upload up to six PDF documents simultaneously in any language they desire. The uploader has been moved to the DocumentClient View. This feature is ideal for those who need to manage multiple files and want a centralized area to conduct analyses.
Central Document Views: Each uploaded document is displayed in the DocumentsComponent via their pdf thumbnail. When a user clicks on one of the document an open modal shows up with the pdf viewer and they can scroll through the content.
Central Chat Functionality: Engage in dynamic conversations with CamelotAI about the contents of all your uploaded documents. It consists of one single chat instance for the user's session.
Text-to-Speech: Powered by ElevenLabs, text-to-speech feature allows users to hear chatbot responses. This not only enhances accessibility but also enriches the user experience, making interactions more engaging and understandable. You can chose up to 10 different voices that support languages such as English, French, Spanish, Portuguese, Italian, Hindi, Deutsch and Korean.
What’s Next?
Looking into implementation of Unstructured for greater ingestion capacity tailored to LLM use cases.
Installation
To get started with CamelotAI, please follow the installation instructions provided in the README on my GitHub repository.
Feedback
Feel free to give me feedback! You can message me through Github.
Thank you for trying out CamelotAI v1.4.0.
