Description
Chatty for LLMs is a Chrome extension designed to bridge the gap between your web browser and your locally installed Large Language Models (LLMs) powered by Ollama. This tool empowers users to engage in direct conversations with their LLMs and leverage Retrieval Augmented Generation (RAG) capabilities on documents found within the active browser tab.
To utilize Chatty for LLMs, users must have Ollama running locally. The extension requires a specific command to be executed in the terminal: `export OLLAMA_ORIGINS=chrome-extension://* ; ollama serve`. This command ensures that Ollama is configured to accept connections from the Chrome extension, allowing seamless communication between the browser and the local AI models.
The primary function of Chatty for LLMs is to facilitate interactive chat sessions with your chosen LLMs. Beyond simple conversation, the extension supports RAG, enabling it to process and understand information from web pages. This means you can ask questions about the content of a webpage, and the LLM, augmented with the page's information, can provide more contextually relevant and accurate answers.
The target audience for Chatty for LLMs includes AI enthusiasts, developers, researchers, and anyone interested in experimenting with or integrating local LLMs into their daily web browsing workflow. It's particularly useful for those who prefer to keep their data private by running models on their own hardware or who want to fine-tune their AI interactions without relying on cloud-based services.
The value proposition of Chatty for LLMs lies in its ability to bring the power of local LLMs directly into the browser. It offers a convenient and integrated way to chat with AI, perform document analysis on web content, and explore the capabilities of open-source LLMs without complex setup or external dependencies beyond Ollama itself. The extension aims to make local LLM interaction more accessible and practical for everyday web use.
Chatty for LLMs's Core Features
Chat with locally running LLMs via Ollama
Perform Retrieval Augmented Generation (RAG) on active tab documents
Requires Ollama to be installed and running locally
Uses specific command for Ollama origin configuration
Integrates AI chat directly into the browser
Facilitates contextually relevant answers from LLMs
Supports interaction with various local LLM models
Designed for privacy-conscious users running local AI
Enhances web browsing with AI capabilities
Enables document analysis of web page content
How to use Chatty for LLMs?
Install Chatty for LLMs Chrome extension
Ensure Ollama is installed and running on your local machine
Open your terminal and run the command: export OLLAMA_ORIGINS=chrome-extension://* ; ollama serve
Navigate to a webpage you wish to interact with
Open the Chatty for LLMs extension interface
Select your desired local LLM
Start chatting or ask questions about the webpage content
Chatty for LLMs's Use Cases
- Local LLM Chat
- Web Content Analysis
- RAG Implementation
- Privacy-Focused AI
- Browser-Based AI Interaction
- LLM Experimentation








