Opiniated RAG for integrating GenAI in your apps 🧠Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.
Some tasks/questions can require retrieving a larger number of chunks than the default configuration. The option dynamic_chunk_retrieval will enable determining the optimal number of chunks to be used in the answer generation form the chunks' relevance scores. A retriever is necessary to enable this option.
linear[bot]
commented
3 weeks ago
Some tasks/questions can require retrieving a larger number of chunks than the default configuration. The option
dynamic_chunk_retrievalwill enable determining the optimal number of chunks to be used in the answer generation form the chunks' relevance scores. A retriever is necessary to enable this option.