chatwithfile

Open a file and chat with the llm about it.

Load a file, it will add it to the input on each prompt as you ask questions about the data. Upload a new file to chat with a new file.

This loads the file with the langchain loaders and inserts it into the input modifier on each prompt. Haven't tested for huge files, consider this experimental.

Installation

1. Install the Text Generation Web UI as per instructions on GitHub as this is an extension for that.
2. Clone the chatwithfile repository: git clone https://github.com/brucepro/chatiwthfile.
3. Move the chatwithfile folder into the extensions directory of your TextGenWebUI installation.
4. In the chatwithfile folder, execute pip install -r requirements.txt to install dependencies. Let me know if I missed any.

Support

As always, if this adds value to your AI experience and you'd like to show your appreciation, consider supporting me, every bit helps:

• Buy me a coffee
• Ko-fi