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.
Given the constraints of PGVector, we are currently limited to using text embeddings with a fixed dimension. This limits our ability to test and use text embeddings from different suppliers (e.g., closed- vs open-weights) and with different dimensions (e.g. to exploit "Matrioska" embeddings).
linear[bot]
commented
2 weeks ago
Given the constraints of PGVector, we are currently limited to using text embeddings with a fixed dimension. This limits our ability to test and use text embeddings from different suppliers (e.g., closed- vs open-weights) and with different dimensions (e.g. to exploit "Matrioska" embeddings).