Does anyone host their own agent stack?
I've just been informed that I could possibly host an agent to interact with a vector database to solve my issue LLMs being utterly retarded in terms of contex...
You can also use a self-hosted OpenSearch instance and build out the index. You can use local llm for embedding and have all your data in your local network. Give your agent the skill to query the index (I’ve found hybrid search works well) and it can pull relevant info into context.
1❤️1🤔1