feat: add stream_query_with_web async generator to chain.py

fix: URL size guard for OOM prevention, eliminate double retrieval in chat, fix print

fix: use langchain_core.prompts for PromptTemplate, propagate citation_index in run_query

feat: add citation_index to retriever + numbered doc prompt in QA chain

feat: rebrand FinRAG → Prism (collection names, system prompt, UI branding)

feat: Migrate LLM to Groq, fix web search pipeline, add structured logging

feat: Add RAGAS eval, score passthrough, docs, and hybrid retrieval config

Add Dockerfile and Render config