EXP-003 / AI System / Published

Graph-RAG Engine

An explainable retrieval-augmented generation system that combines vector search, graph expansion, citation-first answers, optional LLM generation, retrieval evaluation, FastAPI, and a Streamlit interface.

EXP-003 / question

Technical question

Can retrieval paths make RAG answers more explainable, grounded, and easier to inspect?

EXP-003 / method

Method and workflow

  1. Load and split documents into retrievable chunks.
  2. Build embeddings and FAISS-based semantic search.
  3. Construct concept and chunk relationships in an inspectable graph layer.
  4. Expand retrieval results with graph neighbors and ranking logic.
  5. Return extractive or optional LLM answers with source citations.
  6. Evaluate retrieval behavior using golden queries and automated tests.
documents chunks embeddings knowledge graph hybrid retriever citations answer UI

EXP-003 / evidence

Evidence of work

Hybrid retrieval

Vector search and graph expansion work together to improve context discovery and inspectability.

Evaluation

Golden-query metrics make retrieval quality measurable instead of anecdotal.

Interface

FastAPI and Streamlit layers make the system usable as a small RAG application.

EXP-003 / stack

Technical stack

PythonFastAPIPydanticUvicornSentence TransformersFAISSNetworkXNumPyStreamlitunittestGitHub Actions
Open repository ↗

EXP-003 / limitations

Limitations and honesty check

  • The graph layer is in-memory and would need persistence such as Neo4j for larger deployments.
  • Answer quality still depends on document coverage and retrieval quality.
  • Production use would need authentication, monitoring, cost controls, and citation validation.

EXP-003 / next

Next improvements

  • Add persistent graph storage.
  • Add larger benchmark corpora and citation-accuracy tests.
  • Add Docker deployment and API documentation.
  • Add feedback-based retrieval tuning.