UpTrain

UpTrain is an open-source (Apache-2.0) unified platform to evaluate and improve generative AI and LLM applications. It ships a Python framework plus a managed evaluation API that grades responses against 20+ preconfigured checks - context relevance, factual accuracy, response completeness, hallucination, tonality, prompt injection and more - and performs root cause analysis on failure cases.

4 APIs 0 Features

AILLMEvaluationLLM EvaluationObservabilityOpen Source

APIs

UpTrain Evaluations API

Runs evaluations (POST /evaluate) on supplied LLM input/output/context rows against a list of named checks such as context_relevance, factual_accuracy, response_completeness and...

UpTrain Log and Evaluate API

Logs evaluation data under a named project and evaluates it in one call (POST /log_and_evaluate), persisting results so they appear on the managed UpTrain dashboard with real-ti...

UpTrain Root Cause Analysis API

Performs root cause analysis (POST /perform_root_cause_analysis) on failing RAG or LLM responses, classifying why a response was poor - e.g. incomplete context, poor retrieval, ...

UpTrain Runs and Datasets API

Manages evaluation datasets, checksets (reusable bundles of checks), and runs that pair a dataset with a checkset - create a run (POST /run), poll its status (GET /run/{run_id})...

Resources

👥

GitHubOrganization

Sources

aid: uptrain
url: https://raw.githubusercontent.com/api-evangelist/uptrain/refs/heads/main/apis.yml
name: UpTrain
kind: company
description: UpTrain is an open-source (Apache-2.0) unified platform to evaluate and
  improve generative AI and LLM applications. It ships a Python framework plus a managed
  evaluation API that grades responses against 20+ preconfigured checks - context
  relevance, factual accuracy, response completeness, hallucination, tonality, prompt
  injection and more - and performs root cause analysis on failure cases.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- LLM
- Evaluation
- LLM Evaluation
- Observability
- Open Source
created: '2026-06-20'
modified: '2026-06-20'
specificationVersion: '0.19'
apis:
- aid: uptrain:uptrain-evaluations-api
  name: UpTrain Evaluations API
  tags:
  - Evaluation
  - LLM
  - Checks
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.uptrain.ai/
  baseURL: https://demo.uptrain.ai/api/public
  properties:
  - url: https://docs.uptrain.ai/getting-started/introduction
    type: Documentation
  - url: https://docs.uptrain.ai/predefined-evaluations/overview
    type: APIReference
  - url: openapi/uptrain-openapi.yml
    type: OpenAPI
  description: Runs evaluations (POST /evaluate) on supplied LLM input/output/context
    rows against a list of named checks such as context_relevance, factual_accuracy,
    response_completeness and response_conciseness, returning per-row grades and
    explanations. Authenticated with an uptrain-access-token header.
- aid: uptrain:uptrain-log-and-evaluate-api
  name: UpTrain Log and Evaluate API
  tags:
  - Logging
  - Evaluation
  - Projects
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.uptrain.ai/
  baseURL: https://demo.uptrain.ai/api/public
  properties:
  - url: https://docs.uptrain.ai/getting-started/quickstart
    type: Documentation
  - url: openapi/uptrain-openapi.yml
    type: OpenAPI
  description: Logs evaluation data under a named project and evaluates it in one call
    (POST /log_and_evaluate), persisting results so they appear on the managed UpTrain
    dashboard with real-time monitoring. The same endpoint backs evaluate_experiments
    for A/B comparison of prompt or model variants.
- aid: uptrain:uptrain-root-cause-analysis-api
  name: UpTrain Root Cause Analysis API
  tags:
  - Root Cause Analysis
  - RAG
  - Diagnostics
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.uptrain.ai/
  baseURL: https://demo.uptrain.ai/api/public
  properties:
  - url: https://docs.uptrain.ai/predefined-evaluations/overview
    type: Documentation
  - url: openapi/uptrain-openapi.yml
    type: OpenAPI
  description: Performs root cause analysis (POST /perform_root_cause_analysis) on
    failing RAG or LLM responses, classifying why a response was poor - e.g. incomplete
    context, poor retrieval, or hallucination - to guide remediation.
- aid: uptrain:uptrain-runs-api
  name: UpTrain Runs and Datasets API
  tags:
  - Runs
  - Datasets
  - Checksets
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.uptrain.ai/
  baseURL: https://demo.uptrain.ai/api/public
  properties:
  - url: https://docs.uptrain.ai/getting-started/quickstart
    type: Documentation
  - url: openapi/uptrain-openapi.yml
    type: OpenAPI
  description: Manages evaluation datasets, checksets (reusable bundles of checks),
    and runs that pair a dataset with a checkset - create a run (POST /run), poll its
    status (GET /run/{run_id}) and download its results (GET /run/{run_id}/results).
common:
- type: GitHubOrganization
  url: https://github.com/uptrain-ai
- type: LinkedIn
  url: https://www.linkedin.com/company/uptrain-ai
- type: Website
  url: https://uptrain.ai/
- type: Documentation
  url: https://docs.uptrain.ai/
- type: Plans
  url: plans/uptrain-plans-pricing.yml
- type: RateLimits
  url: rate-limits/uptrain-rate-limits.yml
- type: FinOps
  url: finops/uptrain-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com