Skip to content

Repository files navigation

🏢 Insurellm Advanced Expert Assistant

An enterprise-grade, localized Retrieval-Augmented Generation (RAG) platform optimized for private context retrieval, semantic indexing, and multi-stage query optimization. Built entirely on an open-source, local-first architecture to maintain complete data privacy.


🚀 Architectural Blueprint

This project implements an advanced pipeline designed to maximize context precision over standard RAG implementations:

  1. Multi-Query Expansion: Utilizes llama3.2 to rewrite raw chat intents into highly specific vector search terms.
  2. Context Deduplication & Merging: Aggregates original inputs and expanded query variations, resolving semantic duplicate boundaries.
  3. LLM-Based Reranking: Dynamically orders extracted segments via a cross-encoder model paradigm to fit strict token budgets.
  4. Automated Evaluation: Continuous tracing and dataset benchmarking hooked up with LangSmith.

🛠️ Technology Stack

  • LLM Core Framework: Ollama (llama3.2)
  • Vector Vectorstore: ChromaDB
  • Embeddings: HuggingFace (all-MiniLM-L6-v2)
  • Orchestration: LangChain & LiteLLM
  • UI Interface: Gradio 6.0
  • Observability: LangSmith Trace Integration

📥 Setup and Installation

1. Clone & Set up Environment

Ensure you have the uv package manager installed, then configure your environment:

uv venv
.venv\Scripts\activate
uv pip install -r requirements.txt

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages