Skip to content
View ovsilya's full-sized avatar
💭
Don't panic!
💭
Don't panic!
  • Telus Digital
  • Canada

Block or report ovsilya

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. ai-assistant-langgraph-backend ai-assistant-langgraph-backend Public

    Production LangGraph + FastAPI conversational AI backend: per-request agent graph with LLM-as-judge input/output guardrails, intent routing, RAG over a content-search API, multi-brand persona confi…

    Python 1

  2. email-qa-llm-pipeline email-qa-llm-pipeline Public

    LLM-powered email QA pipeline on AWS Bedrock (Claude) — scans 40k+ marketing emails for 15 issue types with parallel workers, checkpoint/resume, and precision/recall evaluation against ground truth

    Python 1

  3. llm-sentence-generation-eval llm-sentence-generation-eval Public

    Dual-LLM benchmarking platform (GPT-4.1 vs Gemini 2.5-flash): parallel generation over CEFR-leveled lesson data, token/cost accounting incl. Gemini thinking tokens, resume-from-checkpoint, and an 8…

    Python 1

  4. multi-agent-support-platform multi-agent-support-platform Public

    Slack-native multi-agent AI support platform (FastAPI + Gemini orchestrator on Cloud Run) with dashboard/log/hydraulics tools and BigQuery vector RAG, plus a Document AI + Gemini pipeline that fill…

    Python 1

  5. blu_baar_chatbot blu_baar_chatbot Public

    Bilingual (EN/DE) chatbot API — Flask + OpenAI with LangChain integrations, containerized and deployed on GCP Cloud Run with Cloud Build CI/CD

    Python

  6. CBC-news-RAG CBC-news-RAG Public

    RAG chatbot over CBC news articles and editorial guidelines — LangChain, GPT-4o, Pinecone, structured JSON responses with metadata

    Python