enterprise-rag-evaluation logo

enterprise-rag-evaluation

Free

A production-style, two-stage Financial RAG architecture analyzing SEC 10-K reports.

Visit Website
Related by shared tags and keywordspdf-chatbotbmaged23blender-plugin
generative-aibaai-bge-large-en-v15bi-encoderchromadbcross-encoderaiai assistantautomation

Overview

A production-style, two-stage Financial RAG architecture analyzing SEC 10-K reports. Features an evaluation sandbox (RAGAS) and an asynchronous, containerized FastAPI backend powered by Gemini Flash and ChromaDB.

Pricing

Free

Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.

Visit Website

Prices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.

Use Cases

  • Teams use the Laboratory core to benchmark retrieval strategies and determine optimal chunk sizes before production.
  • Teams use the custom LLM-as-a-Judge to score faithfulness and answer relevancy of generated responses.
  • Teams use the production runtime to serve concurrent users with sub-second retrieval latency.
  • Teams use the stateful query rewriting to resolve coreferences in multi-turn conversations.
  • Teams use the trace attribution UI to audit latency, cross-encoder scores, rewritten queries, and retrieved snippets.
  • Teams use the idempotent ETL pipeline to prevent ChromaDB duplication and improve vector search accuracy.

Features

Analyzes SEC 10-K financial reports

Uses a two stage RAG architecture

Retrieves content with BAAI embeddings

Stores vectors in ChromaDB

Evaluates responses with RAGAS

Serves requests through asynchronous FastAPI

Packages deployment with Docker Compose

Reviews

No reviews yet. Be the first to share your experience!