web-augmented-generation
This Node.js application performs web-augmented generation using various LLM providers and web search results from SearXNG.
Rephrases user queries for web search, fetches results from a SearXNG instance, summarizes the content, and generates a final response via an OpenAI-compatible API (supporting Ollama, together.ai, llama.cpp). Streams responses for real-time output and implements content similarity checks with repetition detection. Ships with an interactive CLI and detailed logging.
Related \\
-
bedrock-proxy-endpoint
Spin up your own custom OpenAI API server endpoint for easy AWS Bedrock LLM text inference (using standard baseUrl, and apiKey params)
-
bedrock-wrapper
Bedrock Wrapper is an npm package that simplifies the integration of existing OpenAI-compatible API objects with AWS Bedrock's serverless inference LLMs. Fol...
-
down-craft
Node.js package to simplify the process of converting documents (PDF, DOCX, PPTX, and XLSX) into Markdown format. It uses tesseract.js, mammoth, pdf.js, and...