This project provides a lightweight Streamlit application for web research, enabling users to query information using various search tools, vector stores, and LLMs. It's designed for developers and researchers who need a flexible interface for integrating different AI components for web-based information retrieval.

How It Works

The application leverages LangChain's Web Research Retriever, allowing users to configure their preferred search API (e.g., Google Search), vector store (e.g., Chroma), and LLM (e.g., OpenAI). This modular design facilitates easy experimentation and integration of different AI models and data sources for web exploration tasks.

Quick Start & Requirements

• Install via pip install streamlit langchain-google-community langchain-openai chromadb.
• Requires API keys for Google Search (API Key and CSE ID) and OpenAI (API Key and Base URL).
• Set API keys as environment variables (e.g., in .streamlit/secrets.toml or directly in the script).
• Run the application using streamlit run web_explorer.py.

Highlighted Details

• Integrates with Google Search API for web queries.
• Supports Chroma as a vector store.
• Compatible with OpenAI's LLM API.

Maintenance & Community

No specific information on contributors, sponsorships, or community channels is provided in the README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial use or closed-source linking is not detailed.

Limitations & Caveats

The project is described as "lightweight" and requires manual configuration of API keys and component selection. The README does not mention any specific limitations or known issues.