I want to set up a system where each file corresponds to its own vector database because combining different files requires rebuilding the vector database. This approach is intended to reduce the cost of vectorization using OpenAI’s embedding model. However, the issue I’m facing is that the OpenAI API for assistants only supports a single vector database. How can I achieve a system that allows retrieval across multiple vector databases?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How can I attach more than 1 Vector File DB to an Assistant? | 0 | 105 | July 5, 2025 | |
| One Assistant Multiple Vector Stores? | 1 | 2388 | June 20, 2024 | |
| Some questions about the vector store | 4 | 2242 | June 16, 2024 | |
| Feature Request: Support Multiple Vector Stores per Run in Assistants API (Custom GPT Parity) | 1 | 423 | May 19, 2025 | |
| Assistant API with external Vector stores | 3 | 1195 | August 2, 2024 |