Real-Time-3-pipeline-LLM-Financial-Advisor

3-Pipeline LLMOps Financial advisor. Steaming pipeline deployed on AWS, 24/7 collects, embeds live-data into QdrantDB. Training pipeline finetunes model on serverless GPU and logs best model on WandB Registry.Inference pipeline downloads best model from registry for inference, utilizes Langchain to maintain history and context retrieval.

Query-Router

Dynamic routing system for querying LLMs, boosting efficiency and optimizing costs