Skip to main content

LLM-powered risk statement generator and evidence validator for Evidentia

Project description

evidentia-ai

LLM-powered features for Evidentia: risk statement generation and (in Phase 3) evidence validation.

Uses LiteLLM for provider-agnostic LLM calls and Instructor for structured output extraction into Pydantic models.

Provides

  • Risk Statement Generator — Convert control gaps into NIST SP 800-30-compliant risk statements
  • Evidence Validator (Phase 3) — Assess evidence sufficiency using LLM analysis
  • LLM Client — Provider-agnostic wrapper around LiteLLM with retry, rate limiting, and structured output

Supported providers

Any provider supported by LiteLLM:

  • Anthropic Claude (default: claude-sonnet-4-6)
  • OpenAI GPT
  • Google Gemini
  • AWS Bedrock
  • Azure OpenAI
  • Local models via Ollama, vLLM, etc.

Install

pip install evidentia-ai

License: Apache 2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

evidentia_ai-0.7.8.tar.gz (18.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

evidentia_ai-0.7.8-py3-none-any.whl (23.6 kB view details)

Uploaded Python 3

File details

Details for the file evidentia_ai-0.7.8.tar.gz.

File metadata

  • Download URL: evidentia_ai-0.7.8.tar.gz
  • Upload date:
  • Size: 18.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for evidentia_ai-0.7.8.tar.gz
Algorithm Hash digest
SHA256 3224ab8efeabd976b7a30b20a39f02e3f6afd86cfa9a7e086c3b2c6c0ca6163e
MD5 a1dd007d06ac962ffdb788a7fce66875
BLAKE2b-256 31b7e12582f7a61d63617185a16bf72dcd90197d421dae4b5e46b3fd738ebb44

See more details on using hashes here.

Provenance

The following attestation bundles were made for evidentia_ai-0.7.8.tar.gz:

Publisher: release.yml on allenfbyrd/evidentia

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file evidentia_ai-0.7.8-py3-none-any.whl.

File metadata

  • Download URL: evidentia_ai-0.7.8-py3-none-any.whl
  • Upload date:
  • Size: 23.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for evidentia_ai-0.7.8-py3-none-any.whl
Algorithm Hash digest
SHA256 3dd04bf945fedc91ac8c44e4e7032366c1eee21e69e167cdcb86d26bf07967f2
MD5 85fd5f4587fd053f2f3a235a261dbfd4
BLAKE2b-256 6e6036c925d4e48f64bbe9aae1b83d51d52f14f189d75deffbd015989d1c626b

See more details on using hashes here.

Provenance

The following attestation bundles were made for evidentia_ai-0.7.8-py3-none-any.whl:

Publisher: release.yml on allenfbyrd/evidentia

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page