{"repo":"Ambuj123-lab/agentic-rag-financial-parser","free":true,"listed":false,"github":"https://github.com/Ambuj123-lab/agentic-rag-financial-parser","clone":"git clone https://github.com/Ambuj123-lab/agentic-rag-financial-parser.git","description":"Enterprise RAG ecosystem managing 32000+ semantic chunks. Features hybrid parsing (LlamaParse/PyMuPDF) and 256-dim MRL embeddings for 512MB RAM environments","language":"Python","stars":106,"topics":["agentic-rag","fastapi","genai","langgraph","llmops","pinecone-db","python","rag","matryoshka-representation-learning"],"license":"AGPL-3.0","category":"ai-agents","readme_excerpt":"--- ⚡ What Is This? An autonomous, 11-node Agentic RAG pipeline that parses and queries complex Indian financial & legal documents — Union Budget, Finance Bill, Tax Laws, PF/Pension Schemes, RBI KYC, and Constitution of India — using a purpose-built state machine that thinks before it answers . Unlike traditional RAG (retrieve → generate), this system employs an agentic flow where each query passes through specialized nodes that classify intent, cross-question vague queries, guard against hallucinations, and verify answer grounding — all orchestrated via LangGraph StateGraph . --- 🌿 Branches Branch Description -------- ------------- main Production — stable, lean version live on Render (512MB RAM constraints) v2-local-heavy Parallel Vector Retrieval + Cohere Neural Reranking. 👉 View Architecture --- 🏗️ System Architecture 🔮 11-Node LangGraph StateGraph — Animated Architecture ✨ Classifier → 6-Path Routing → Retrieval → Rerank → Generate → Hallucination Guard → Post-Process --- 🧠 The 11-Node Agentic RAG Pipeline Node Purpose Key Detail ------ --------- ------------ 1. Classifier Intent detection + 6-path routing Returns structured JSON: intent · doc type · confidence · search intents 2. Reject Safety guard Blocks abusive + jailbreak queries with regex blocklist guardrail 3. Greet Efficiency bypass Handles greetings without hitting vector DB (zero cost) 4. CrossQuestioner HITL clarification Asks clarifying questions for vague queries (max 2 rounds) 5. Retriever Dual vector","default_branch":null,"files":null,"tree":[],"storefront":"/r/Ambuj123-lab","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Ambuj123-lab/agentic-rag-financial-parser/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}