3d3ac59bfb
Update the default LLM to llama3-8B on cpu/nvgpu/amdgpu/gaudi for docker-compose deployment to avoid the potential model serving issue or the missing chat-template issue using neural-chat-7b. Slow serving issue of neural-chat-7b on ICX: #1420 Signed-off-by: Wang, Kai Lawrence <kai.lawrence.wang@intel.com>
ChatQnA Conversational UI
📸 Project Screenshots
🧐 Features
Here're some of the project's features:
- Start a Text Chat：Initiate a text chat with the ability to input written conversations, where the dialogue content can also be customized based on uploaded files.
- Context Awareness: The AI assistant maintains the context of the conversation, understanding references to previous statements or questions. This allows for more natural and coherent exchanges.
- Upload File: The choice between uploading locally or copying a remote link. Chat according to uploaded knowledge base.
- Clear: Clear the record of the current dialog box without retaining the contents of the dialog box.
- Chat history: Historical chat records can still be retained after refreshing, making it easier for users to view the context.
- Conversational Chat : The application maintains a history of the conversation, allowing users to review previous messages and the AI to refer back to earlier points in the dialogue when necessary.
🛠️ Get it Running
-
Clone the repo.
-
cd command to the current folder.
-
Modify the required .env variables.
DOC_BASE_URL = '' -
Execute
npm installto install the corresponding dependencies. -
Execute
npm run devin both environments