langsearch
от vaibhav1805
Web & Frontend DevelopmentКратко
Free web search and semantic reranking API for AGI applications.
Описание
Что делает этот навык
LangSearch provides a free API for web search and semantic reranking. It uses hybrid search combining keyword matching with vector-based similarity to retrieve current web documents. Built for RAG pipelines and LLM applications that need up-to-date real-world context.
Free tier combines hybrid keyword and vector search with built-in semantic reranking, removing the need to wire together separate search and reranking services.
Когда его использовать
- Fetching recent news or events for an AI chatbot response
- Building a RAG pipeline that pulls live web content
- Reranking search results by semantic relevance to a specific query
- Answering questions about topics beyond an LLM's training cutoff
- Aggregating results from multiple queries into a research context
Пример сценария
User asks: What are the best practices for deploying ML models in production?
- 1
Sends query to the LangSearch web search endpoint with summary enabled
- 2
Retrieves top 10 results including titles, snippets, and markdown summaries
- 3
Prepares result snippets as documents and passes them to the rerank endpoint
- 4
Returns top 5 semantically reranked documents as grounded context
- 5
Formats context for the LLM to generate a current, sourced response
Top 5 reranked web results formatted as context for LLM response generation
Требования
- LANGSEARCH_API_KEY environment variable
- Free LangSearch account at langsearch.com/api-keys
Установка
clawhub install vaibhav1805/langsearchВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.