Production-grade agentic RAG system for legal documents. Full pipeline from data sourcing through retrieval, reranking, and agent orchestration. Hybrid search combining semantic embeddings (bge-m3) with lexical retrieval (BM25). Web search included. Strong evaluation performance across retrieval, agentic search, citations/trustworthiness, and more. Evaluations can be found in the writeup below.
bge-m3
ChromaDB
Elasticsearch
bge-reranker
Gemini-2.5
Docker
GKE
Embeddings: bge-m3, gemini-embedding-001
Indexing: ChromaDB (HNSW), Elasticsearch (BM25)
Retrieval: Hybrid search with RRF, convex combination
Agents: Conversational + search agents, planning, self-triage
Training: 560M parameter model fine-tuning