Make stages replaceable
Parser, chunker, embedding, retrieval, model and speech modules have separate boundaries. Per-format chunking and YAML configuration let the pipeline adapt to the corpus.
Retrieval · Voice / Configurable prototype
Voice-Based RAG
A configurable document question-answering pipeline with text or voice input, hybrid retrieval, reranking and speech output.
01 / THE PROBLEM
Documents arrive in different formats, while people may prefer speaking to typing. A reusable retrieval system must normalize inputs, select relevant context and keep speech handling separate from retrieval and generation.
02 / FOLLOW THE WORKFLOW
A simplified example of the documented flow. Sample outputs are authored illustrations, not live model predictions.
Multi-format document ingestion
Handbook.pdf → searchable passages
Parse and chunk source documents.
Example query
“How do I submit an expense?”
Accept a typed or transcribed question.
Context selected from the documents
Dense + BM25 → ranked passages
Combine retrieval and reranking.
Illustrative pipeline, no microphone used
Retrieved context → answer → audio
Generate a response with optional speech.
Step 1 of 4 · Ingest
03 / ENGINEERING
Parser, chunker, embedding, retrieval, model and speech modules have separate boundaries. Per-format chunking and YAML configuration let the pipeline adapt to the corpus.
Dense retrieval can combine with BM25, followed by a cross-encoder. Chroma is the default vector store; FAISS and Qdrant are configurable alternatives.
Whisper variants handle transcription, and configurable TTS engines provide output. Text mode and muted speech remain available. Ollama supports a local runtime; Groq is an optional hosted provider.
04 / EVIDENCE & LIMITS
The README documents end-to-end orchestration through PipelineOrchestrator and Gradio, with multi-format parsers, configurable chunkers, hybrid retrieval and reranking. It reports implementation and tests, without a fixed-corpus Recall@k or grounded-answer benchmark.
Retrieval quality depends on corpus preparation, chunking and model choice. A useful next evaluation compares dense, hybrid and reranked retrieval on the same fixed questions and sources, with answer grounding and end-to-end latency measured separately.
05 / READ THE SOURCE
Based on public repository documentation reviewed on 7 November 2026. Results are attributed to the project’s recorded evaluations; they were not rerun for this portfolio.
TOOLS BEHIND THE WORK
Explore the stack. Drag the ribbon or select a tool.