How dhananjaylab/web_search_app works
Project type and purpose
• Its purpose is to extract text from URLs or documents, generate embeddings over that text, perform a search over those embeddings, and finally craft a user-facing prompt or result.
File structure
• Top-level scripts:
• wsearch.py – likely the CLI entry point / orchestrator.
• text_extractor.py – pulls raw text from web pages or documents.
• embedding_search.py – computes or loads vector embeddings and performs nearest-neighbor search.
• prompt_generator.py – builds the final prompt or human-readable output for the user.
• No separate frontend/backend directories: it’s a single-process Python pipeline.
• No explicit database; embeddings are probably in memory or in local files.
• No web server or long-lived service—this is a CLI tool.
README for additional insights
• The README is minimal (“# web_search_app”), so most architecture clues come from the filenames and typical patterns:
• text extraction → vectorization → search → prompt assembly → output.