Skip to main content
Back to Projects
RAG & SearchFeaturedOct 2024 → Present

Enterprise Voice Assistant & RAG Ecosystem

Voice-first enterprise assistant powered by vLLM-served LLMs, Pinecone vector search, Neo4j knowledge graph, and Whisper STT — answering HR and operations queries in real time.

PythonvLLMPineconeLangChainWhisperNeo4jFastAPIWebRTC
Voice p95
1.4s end-to-end
HR docs indexed
10k+
Answer accuracy
+42% vs keyword

Problem & Solution

The Problem

Enterprise employees waste time hunting through HR documents, policies, and tools for answers. Text chatbots don't fit on-the-go workflows, and most enterprise search is keyword-bound.

The Solution

Built a voice-first assistant pipeline. Speech is transcribed with Whisper, queries are routed through LangChain over a hybrid Pinecone + Neo4j retrieval layer, and answers are generated by an LLM served via vLLM for low-latency, self-hosted inference.

System Architecture

End-to-end flow from intake to outcome

  1. 01

    Voice Capture

    WebRTC

    Microphone audio is streamed in via WebRTC and chunked for STT.

  2. 02

    STT

    Whisper

    Whisper transcribes the audio stream into a text query.

  3. 03

    Hybrid Retrieval

    PineconeNeo4jLangChain

    Query → vector search in Pinecone + graph traversal in Neo4j, fused via LangChain.

  4. 04

    LLM Generation

    vLLM

    vLLM-hosted LLM produces a grounded, spoken-friendly answer.

  5. 05

    TTS

    TTS

    Answer is synthesized back to speech for the voice channel.

Engineering Challenges & Wins

Optimization results and engineering tradeoffs

Optimization Results

  • Whisper STT front-end for voice-first workflows.
  • Hybrid retrieval: Pinecone for vector similarity + Neo4j for relational HR context.
  • vLLM-served LLM for low-latency, self-hosted inference.

Engineering Challenges

  • Keeping end-to-end voice latency under 2 seconds for natural conversation.
  • Fusing vector and graph retrieval without doubling the answer-generation cost.

More case studies

Explore other production systems I've engineered end-to-end.

All Projects

Related Projects

Autonomous AI AgentsFeatured
OmniShield ICES: Asynchronous AI Email Security Middleware

Mail-server gateway (Postfix Milter) that intercepts every inbound message, runs a fine-tuned BERT core (M-BSCE) through an asynchronous inference pipeline (RabbitMQ + Celery), and adds multimodal threat detection (PaddleOCR for Quishing) with SOAP clawbacks to the upstream mail system.

Quishing detection
98%+
p95 classification
<400ms
Async throughput
5k msg/min
PythonPostfix MilterRabbitMQCeleryBERT+6
Autonomous AI AgentsFeatured
OpenClaw Multi-Channel Orchestration

Autonomous multi-channel AI platform that unifies chat, voice, and email behind microservices and an API gateway, with shared context across channels.

Channels
3 unified
Tenant onboard
<1 day
Cross-channel memory
100%
OpenClawFastAPIWebRTCWebSocketRabbitMQ+4