Ambuj123-lab/agentic-rag-financial-parser
Enterprise RAG ecosystem managing 15,000+ semantic chunks. Features hybrid parsing (LlamaParse/PyMuPDF) and 256-dim MRL embeddings for 512MB RAM environments
Orchestrates an 8-node LangGraph state machine that routes financial document queries through intent classification, clarification, retrieval, generation, and hallucination-guarding phases—avoiding unnecessary vector lookups for greetings and using Pinecone + Supabase parent-chunk deduplication. Integrates OpenRouter LLMs with Langfuse observability, circuit-breaker reliability, and semantic caching via Upstash Redis to index 20+ Indian government financial/legal documents with <100ms response latency.
Stars
40
Forks
18
Language
Python
License
—
Category
Last pushed
Mar 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Ambuj123-lab/agentic-rag-financial-parser"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LeDat98/NexusRAG
Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder...
Zakk-Yang/nexusync
Intuitive RAG system on top of LllamaIndex
masterFoad/NanoSage
Local LLM Powered Recursive Search & Smart Knowledge Explorer
Serhii2009/brix-protocol
Runtime Reliability Infrastructure for LLM Pipelines — enforce deterministic rules, measure the...
marcoguad-HR/pay-transparency-tool
RAG-powered assistant and pay gap analysis tool for EU Directive 2023/970 compliance