Skip to main content

Makes a second request to the LLM, asking it if its original response was relevant to the prompt.

Project description

guardrails-ai-qa-relevance-llm-eval

Makes a second request to the LLM, asking it if its original response was relevant to the prompt.

Installation

pip install guardrails-ai-qa-relevance-llm-eval

This validator ships local models. After installing, run the post-install step to download them:

python -m guardrails_ai.qa_relevance_llm_eval.post_install

Usage

from guardrails import Guard
from guardrails_ai.qa_relevance_llm_eval import QARelevanceLLMEval

guard = Guard().use(QARelevanceLLMEval)

License

MIT — © Guardrails AI.

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

guardrails_ai_qa_relevance_llm_eval-0.0.2.tar.gz (4.4 kB view details)

Uploaded Source

Built Distribution

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

File details

Details for the file guardrails_ai_qa_relevance_llm_eval-0.0.2.tar.gz.

File metadata

File hashes

Hashes for guardrails_ai_qa_relevance_llm_eval-0.0.2.tar.gz
Algorithm Hash digest
SHA256 211d2b34c3a0915426a8d8e4c907931f5c53592840b1292c54b7ba0fc56a2883
MD5 3252e1afe8945152f740d07777128d04
BLAKE2b-256 005909839f0252f2565c67a5d531f720b31f053661b18cbcba7f15367d598285

See more details on using hashes here.

File details

Details for the file guardrails_ai_qa_relevance_llm_eval-0.0.2-py3-none-any.whl.

File metadata

File hashes

Hashes for guardrails_ai_qa_relevance_llm_eval-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 f14528560b38a8c392f0c61027d014213ea86d54cf00cc8ad5768d94e27627b2
MD5 66a2a4bd053f2668da6d7f82eccf7a1c
BLAKE2b-256 3b1627b614a83371c7c824dd7b42ae4a4f7dac339eb69ee24a7bd2913b2cbea1

See more details on using hashes here.

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