lcel

Accelerate your Gen AI with NVIDIA NIM and NVIDIA AI Workbench

This code is an implementation of a chatbot using LLM chat model API and Langchain.

HR policy RAG assistant with LangChain LCEL, RunnableBranch, FAISS, FastAPI, and an OpenAI-compatible model API.

The "lcel-tutorial" repo is designed for mastering LangChain Expression Language (LCEL), offering exercises to build stateful, multi-actor LLM applications. It's a hands-on guide to leveraging LCEL for complex workflows and agent-like behaviors. Perfect for enthusiasts eager to explore LLM's potential.

The easiest way to supercharge your apps with LLM!

从 0 到迷你 Claude Code 的 LangChain Agent 学习仓库：LCEL · 记忆 · RAG · LangGraph · 自制 Agent Harness，全部可独立运行、默认走 OpenAI 兼容协议。

Hybrid RAG pipeline (Dense + BM25 + Cross-Encoder Reranker) with conversational memory and systematic evaluation. 5 retrieval experiments, 92.3% Hit Rate, 5.0/5.0 LLM-as-a-Judge. Built with LangChain LCEL & ChromaDB.

向量化、RAG增强、智能体Agent、LangChain LCEL 管道组合等等。持续更新...

An AI-powered multi-agent research platform that automates web search, content extraction, report generation, and report evaluation through a collaborative agent pipeline.

This is a simple application of the LLM (Lattice Conditional Execution Language) with the LCEL (Lattice Conditional Execution Language) library. The application is a simple calculator that can perform addition, subtraction, multiplication, and division.

A LangChain-based chat application running Llama 3 locally via Ollama, featuring a modern Streamlit chat UI and LCEL pipeline.

Chatbot de recrutamento e RH com IA, memória conversacional e análise estruturada de vagas.

End-to-end implementation of LangChain Runnables and LCEL with modular Python code, best practices, and real-world examples for building production-ready LLM applications.

AI agent built with LangChain + Google Gemini that generates professional, multilingual LinkedIn posts from a topic. CLI, Docker, and a modern Streamlit web UI. Shorter variant if you want it tighter: LangChain + Gemini AI agent that turns any topic into a polished LinkedIn post — in any language. CLI, Streamlit UI, and Docker ready.

A lightweight implementation of a LangChain Expression Language (LCEL)-inspired pipeline execution framework built from scratch in Python using Object-Oriented Programming, operator overloading, and composable runnable components.

Professional-grade AI legal auditor for contract analysis. Built with LangChain, Gemini 3 Flash, and Streamlit, this tool enables real-time, context-aware audits of complex legal documents with sub-second response streaming

Structure-aware PDF chunking for RAG. It builds a document hierarchy from multiple PDFs and splits chunks along section boundaries. Output is a NetworkX graph linking sections, tables, figures, cross-references and defined terms, with an interactive 3D/2D viewer. It uses LangChain LCEL, with PyMuPDF as the default parser and Docling as an option.

A Python MCP server that exposes RAG-powered note management as AI agent tools — combining PostgreSQL, ChromaDB, and Google Gemini via a LangChain LCEL pipeline.

RAG pipeline that lets you upload any PDF and query it in natural language.

An exploration of the modern LangChain Expression Language (LCEL), showcasing how to build powerful AI workflows with Runnables for RAG, conditional logic, and more.