#143 · Primary category: Knowledge Base & RAG

embedJs

ai chatgpt claude cohere embedding embeddings gpt gpt-4 gpt-4o huggingface large-language-models llm mistral ollama openai pinecone rag vector-database vertex-ai

A NodeJS RAG framework to easily work with LLMs and embeddings

Project last updated:06/26/26

GitHub Stars

601

Forks

75

Contributors

17

License

Apache-2.0

Why we included this project

EmbedJs is a Node.js library that handles the retrieval side of LLM applications without you having to assemble the pipeline yourself. It takes your source data, splits it into chunks, generates embeddings, and stores them in a vector database, so you can ask questions about your own documents in plain language. The framework works with a range of embedding models and LLM backends, so you can pick providers based on cost or hosting constraints. That makes it a practical starting point for teams that want a working retrieval loop quickly but expect to swap components later. It also suits developers who would rather keep their whole stack in JavaScript than move to Python for AI work.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category