ResearchMind — Personal Research Intelligence System

02 — Approach

Solution

The workflow below is a visual summary of the documented implementation; it is not a claim of additional system components.

1. 01

   Engineered a hybrid retrieval pipeline over 1,317 ML papers combining BM25 and dense retrieval with RRF fusion; benchmarked embedding models and FAISS index types, achieving Recall@10 of 0.97 with MPNet and 91% p95 latency reduction with HNSW32

   →
2. 02

   Built a 7-tool LangGraph agent with intent-based routing using a configurable LLM backend supporting both local and API-hosted models at temperature 0, achieving 100% classification accuracy on 110 labeled queries, supporting gap detection, methodology comparison, citation graph traversal, and multi-turn memory

   →
3. 03

   Implemented a 4-stage RAG validation pipeline covering citation grounding, hallucination scoring, and gap schema validation with a rejection threshold of 0.70, averaging a hallucination score of 0.80 on eval; clustered low-rated queries using k-means to surface systematic retrieval failures

03 — Engineering judgment

Key decisions

• 01

  Built a 7-tool LangGraph agent with intent-based routing using a configurable LLM backend supporting both local and API-hosted models at temperature 0, achieving 100% classification accuracy on 110 labeled queries, supporting gap detection, methodology comparison, citation graph traversal, and multi-turn memory

• 02

  Implemented a 4-stage RAG validation pipeline covering citation grounding, hallucination scoring, and gap schema validation with a rejection threshold of 0.70, averaging a hallucination score of 0.80 on eval; clustered low-rated queries using k-means to surface systematic retrieval failures

• 03

  Deployed on HuggingFace Spaces with a FastAPI backend, Redis caching achieving 93% latency reduction, and sustained 15 RPS at 80 concurrent users under Locust load testing with a RAGAS faithfulness baseline of 0.775

04 — Evidence

Results

This project record verifies the delivered implementation, but does not report a comparable performance metric.

Product & System Views