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
director_ai-3.11.0-py3-none-any.whl.sigstore.json	2026-03-27	9.1 kB	0
director_ai-3.11.0.tar.gz.sigstore.json	2026-03-27	9.2 kB	0
sbom.json	2026-03-27	72.6 kB	0
director_ai-3.11.0-py3-none-any.whl	2026-03-27	300.0 kB	0
director_ai-3.11.0.tar.gz	2026-03-27	508.0 kB	0
README.md	2026-03-27	1.2 kB	0
v3.11.0 source code.tar.gz	2026-03-27	14.2 MB	0
v3.11.0 source code.zip	2026-03-27	14.7 MB	0
Totals: 8 Items		29.8 MB	0

Director-AI v3.11.0

Highlights

ProductionGuard — batteries-included API bundling calibrated scoring, human feedback loop, conformal confidence intervals, and agent tool-call verification
Atomic claim verification — VerifiedScorer.verify(atomic=True) decomposes compound sentences into atomic claims with multi-span evidence attribution
Hybrid retrieval factory — VectorGroundTruthStore.grounded() sets up BM25 + dense embeddings + RRF fusion in one line
New integrations — Semantic Kernel, DSPy/Instructor, Helm chart
Signed releases — Sigstore signatures + SLSA provenance attestations on every release
Observability pack — Grafana dashboard (9 panels) + Prometheus alert rules (6 alerts)

Fixed

Streaming false-halt benchmark — three bugs corrected. Measured result: 4.4% (was broken 0.0%)
Domain profile claims — medical/finance FPR=100% without KB grounding now documented honestly
Summarization auto-routing — bidirectional NLI now activates automatically for summarisation tasks

Install

pip install director-ai==3.11.0

Full changelog: CHANGELOG.md

Source: README.md, updated 2026-03-27

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

Try Google Cloud Risk-Free With $300 in Credit Icon

Try Google Cloud Risk-Free With $300 in Credit

No hidden charges. No surprise bills. Cancel anytime.

Use your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.

Start 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