rag-embedding-generator

What problem does it solve?

The RAG Embedding Generator converts raw text and chunked datasets into vector representations, enabling efficient retrieval in vector databases for RAG workflows, while preserving useful metadata for source attribution.

Core Features & Use Cases

• Embeds a single text, a list of texts, or dataset chunks from RAG Content Chunker or Website Content Crawler.
• Supports batched API requests to maximize throughput with OpenAI and Cohere, while maintaining controls on input size and errors.
• Outputs embeddings with pass-through metadata (chunk_id, source_url, page_title, section_heading) ready for storage in Pinecone, Qdrant, Weaviate, Chroma, or similar vectors stores.
• Quick Use Case: Transform a website's content into a searchable vector store for rapid retrieval in a knowledge base.

Quick Start

Run the actor with an API key and input (text, texts, or dataset_id) to generate embeddings and metadata for downstream storage.