director-ai Files

Real-time LLM hallucination guardrail — NLI + RAG fact-checking

Brought to you by: anulum

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
sbom.json	2026-03-03	67.3 kB	0
README.md	2026-03-03	1.8 kB	0
v2.6.0 -- Review Response_ 9-Point Hardening source code.tar.gz	2026-03-03	1.5 MB	0
v2.6.0 -- Review Response_ 9-Point Hardening source code.zip	2026-03-03	1.7 MB	0
Totals: 4 Items		3.3 MB	0

v2.6.0 — Review Response: 9-Point Hardening

Addresses all 9 deficiencies from external review of v2.5.0.

Changed

R1: Empty default GroundTruthStore — GroundTruthStore() no longer ships hardcoded SCPN facts. Use GroundTruthStore.with_demo_facts() for demo/test data.
R3: Chunked NLI inner aggregation — inner agg changed from min to max. Most contradictory premise chunk drives the score (conservative for safety). Added inner_agg parameter.
R4: Catch rate improvements — heuristic scorer adds negation asymmetry (+0.25) and novel entity detection (+0.15). Claim decomposition via NLIScorer.score_decomposed(). New "summarization" profile.
R5: Retrieval wiring — build_store() supports vector_backend="sentence-transformer" with configurable embedding_model. CLI ingest subcommand handles directories and paragraph chunking.
R6: Reranker config wired — build_store() wraps backend with RerankedBackend when reranker_enabled=True.
R7: LLM judge structured output — requests JSON {"verdict": "YES"|"NO", "confidence": 0-100}, falls back to string matching. Configurable model via DIRECTOR_LLM_JUDGE_MODEL.
R8: Sanitizer scoring mode — InputSanitizer.score() returns weighted suspicion_score (0.0-1.0). Low-weight patterns flag without blocking. allowlist parameter for false-positive exemption.
R9: Clean branding — removed [AGI Output]: prefix, simplified halt message, changed disclaimer to [Unverified].
R2: Streaming docs — clarified accumulated-text re-scoring, added Limitations section.

Full Changelog

See CHANGELOG.md

Install

:::bash
pip install director-ai==2.6.0

Source: README.md, updated 2026-03-03

Other Useful Business Software

Go From AI Idea to AI App Fast Icon

Go From AI Idea to AI App Fast

One platform to build, fine-tune, and deploy ML models. No MLOps team required.

Access Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.

Try Free

AI-generated apps that pass security review Icon

AI-generated apps that pass security review

Stop waiting on engineering. Build production-ready internal tools with AI—on your company data, in your cloud.

Retool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.

Try Retool free

Go From AI Idea to AI App Fast

One platform to build, fine-tune, and deploy ML models. No MLOps team required.

Access Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.

Try Free

Recommended Projects

Node Director
The Node Director is a tool for managing distributed, hetergeneous UNIX Systems. Its functionality includes System Configuration, Application Distribution, NIS & NIS+ Management, User Creation and Dynamic System Documentation.
Opik
Debug, evaluate, and monitor your LLMapps, RAG systems, and agentic AI
DocsGPT
Private AI platform for agents, enterprise search and RAG pipelines
DeepEval
DeepEval is a simple-to-use, open-source LLM evaluation framework, for evaluating and testing large-language model systems. It is similar to Pytest but specialized for unit testing LLM outputs. DeepEval incorporates the latest research to evaluate LLM outputs based on metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., which uses LLMs and various other NLP models that run locally on your machine for evaluation. Whether your application is implemented via RAG or fine-tuning, LangChain, or LlamaIndex, DeepEval has you covered. With it, you can easily determine the optimal hyperparameters to improve your RAG pipeline, prevent prompt drifting, or even transition from OpenAI to hosting your own Llama2 with confidence.
Vector Admin
The universal tool suite for vector database management