speakDocGPT is a context-aware chatbot that operates over uploaded PDF documents. It leverages language models to provide text-based answers and generative AI audio responses. The chatbot is designed to assist users in extracting information and generating responses related to the content of the uploaded PDF document.
speakDocGPT_illustration.mp4
- Context-aware chatbot: The chatbot is capable of understanding and responding to user queries based on the content of the uploaded PDF document.
- Generative AI audio: The chatbot can produce audio responses generated by a language model, providing a more interactive and natural conversational experience.
- LLMs: The chatbot utilizes Language Models (LLMs) as the underlying technology to generate text-based responses.
- Chat models: The chatbot employs chat models, which are variations of LLMs specifically designed for chat-like interactions, to facilitate conversational interactions with users.
- Prompt templates: The chatbot utilizes prompt templates, which allow users to provide additional context and instructions to the model, enhancing the quality and relevance of the responses.
- Chains: The chatbot utilizes chains, which link together different components such as models, prompts, and other chains, to create a sequence of operations for processing user queries.
- Agents: The chatbot incorporates agents, which dynamically choose actions based on inputs, enabling complex workflows and multi-step interactions with the user.
- Memory: The chatbot employs a memory module that maintains application state and enables contextual understanding of new user messages based on past interactions.
First, run the development server:
npm run dev
# or
yarn dev
# or
pnpm devOpen http://localhost:3000 with your browser to see the result.
Additionally, run the fastAPI server via server.py
You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.