Skip to content

Commit

Permalink
Deployed d29c8e2 with MkDocs version: 1.5.3
Browse files Browse the repository at this point in the history
  • Loading branch information
@joshreini1
joshreini1 committed Jan 31, 2024
1 parent cb04830 commit 8450199
Show file tree
Hide file tree
Showing 75 changed files with 10,089 additions and 35,523 deletions.
561 changes: 141 additions & 420 deletions 404.html
View file

Large diffs are not rendered by default.

599 changes: 160 additions & 439 deletions conf/index.html
View file

Large diffs are not rendered by default.

83 changes: 53 additions & 30 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -102,22 +102,22 @@
</svg>
</a>
<ul class="nav__items">
<a href="nn-explainability.html">
<li>NN Explainability</li>
</a>
<a href="https://blog.trulens.org/">
<li>Blog</li>
</a>
<a href="https://github.com/truera/trulens/" target="_blank">
<li>GitHub</li>
</a>
<a href="nn-explainability.html">
<li>NN Explainability</li>
</a>
<a href="https://communityinviter.com/apps/aiqualityforum/josh" target="blank">
<li>Community</li>
</a>
<a href="https://go.truera.com/newsletter-archive" target="blank">
<li>Newsletter</li>
</a>
<a href="https://trulens.org/welcome/" target="_blank"
<a href="https://www.trulens.org/trulens_eval/install/" target="_blank"
class="header__btn nav__btn d-if fd-r ai-c jc-c mt-xxl-mob">
<svg class="hide-desktop" width="24" height="25" viewBox="0 0 24 25" fill="none"
xmlns="http://www.w3.org/2000/svg">
Expand Down Expand Up @@ -211,21 +211,42 @@ <h1>
</svg>
</div>
</div>

<div class="container__wrapper">
<section class="section container">

<div class="grid-columns-2">
<h2>TruLens:</br> scale up and accelerate LLM app evaluation</h2>
<p>
Create credible and powerful LLM apps, faster. TruLens is a software tool that helps you to
objectively measure the quality and effectiveness of your LLM-based applications using feedback
functions. Feedback functions help to programmatically evaluate the quality of inputs, outputs,
and intermediate results, so that you can expedite and scale up experiment evaluation. Use it
for a wide variety of use cases including question answering, retrieval-augmented generation,
and agent-based applications.
</p>
</div>
<div class="icons">
<a href="https://pypi.org/project/trulens-eval/" target="_blank">
<img src="https://img.shields.io/pypi/v/trulens_eval?label=trulens_eval&link=https%3A%2F%2Fpypi.org%2Fproject%2Ftrulens-eval%2F" alt="PyPI - Version" />
</a>
<a href="https://dev.azure.com/truera/TruLens/_build/latest?definitionId=9&branchName=master" target="_blank">
<img src="https://img.shields.io/azure-devops/build/truera/5a27f3d2-132d-40fc-9b0c-81abd1182f41/9" alt="Azure DevOps builds (job)" />
</a>
<a href="https://github.com/truera/trulens" target="_blank">
<img src="https://img.shields.io/github/license/truera/trulens" alt="GitHub" />
</a>
<a href="https://pypi.org/project/trulens-eval/" target="_blank">
<img src="https://img.shields.io/pypi/dm/trulens_eval" alt="PyPI - Downloads" />
</a>
<a href="https://communityinviter.com/apps/aiqualityforum/josh" target="_blank">
<img src="https://img.shields.io/badge/slack-join-green?logo=slack" alt="Slack" />
</a>
<a href="https://www.trulens.org/trulens_eval/install/" target="_blank">
<img src="https://img.shields.io/badge/docs-trulens.org-blue" alt="Docs" />
</a>
<a href="https://colab.research.google.com/github/truera/trulens/blob/main/trulens_eval/examples/quickstart/quickstart.ipynb" target="_blank">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" />
</a>
</div>
<div style="margin-top: 20px;">
<h2>TruLens: Don't just vibe check your LLM app!</h2>
<p>
Create credible and powerful LLM apps, faster. TruLens is a software tool that helps you to
objectively measure the quality and effectiveness of your LLM-based applications using feedback
functions. Feedback functions help to programmatically evaluate the quality of inputs, outputs,
and intermediate results, so that you can expedite and scale up experiment evaluation. Use it
for a wide variety of use cases including question answering, summarization, retrieval-augmented generation,
and agent-based applications.
</p>
</div>

<div class="grid-columns-3 mt-xxl">
<div class="box">
Expand All @@ -235,8 +256,8 @@ <h3>Evaluate</h3>
</p>
<ul class="custom-list mt-xl">
<li>Groundedness</li>
<li>Relevance</li>
<li>Toxicity</li>
<li>Context Relevance</li>
<li>Safety</li>
</ul>
</div>
<div class="box">
Expand All @@ -249,7 +270,7 @@ <h3>Iterate</h3>
<div class="box">
<h3>Test</h3>
<p>
Compare different LLM chains on a metrics leaderboard to pick the best performing one.
Compare different LLM apps on a metrics leaderboard to pick the best performing one.
</p>
</div>
</div>
Expand All @@ -272,7 +293,7 @@ <h2 class="ta-l">How it works</h2>
<div class="container__wrapper">
<section class="section container">
<h2>Why Use TruLens for LLM applications?</h2>
<p class="subtitle mb-xxl">The fastest, easiest way to test and iterate on your LLM app.</p>
<p class="subtitle mb-xxl">The fastest, easiest way to validate your LLM app.</p>
<div class="grid-columns-2 mb-xxl">
<div class="mb-xll-mob">
<div class="btn__shadow mb-xl">
Expand Down Expand Up @@ -314,7 +335,7 @@ <h3>Start with a few lines of code.</h3>
<p>
TruLens fits easily into your LLM app dev process. Simply pip install from <a
href="https://pypi.org/project/trulens-eval/" target="_blank">PyPI</a>,
and add a couple of lines to your LLM app.
and add a couple of lines to your LLM app. Track any application, and evaluate with the model of your choice.
</p>
</div>
<div>
Expand Down Expand Up @@ -372,12 +393,13 @@ <h3>Get the breadth of feedback you need to evaluate app performance.</h3>
performance and minimize risk:
</p>
<ul class="col-2 custom-list">
<li>Truthfulness</li>
<li>Question answering relevance</li>
<li>Context Relevance</li>
<li>Groundedness</li>
<li>Answer Relevance</li>
<li>Comprehensiveness</li>
<li>Harmful or toxic language</li>
<li>User sentiment</li>
<li>Language mismatch</li>
<li>Response verbosity</li>
<li>Fairness and bias</li>
<li>Or other custom feedback functions you provide</li>
</ul>
Expand All @@ -394,18 +416,19 @@ <h2>TruLens can work with any LLM-based app</h2>
</p>
<ul class="grid-columns-2 custom-list">
<div class="box">
<h3>TruLens can be used to ensure AI Quality in a wide variety of use cases, such as:</h3>
<li>Customer service chatbots for retail, manufacturing, insurance, banking, and more!</li>
<li>Informational chatbots for consumer research, corporate research, weather, healthcare, and
more.</li>
<h3>TruLens is loved by thousands of users for applications such as:</h3>
<li>Retrieval Augmented Generation (RAG)</li>
<li>Summarization</li>
<li>Co-pilots</li>
<li>Agents</li>
</div>
<div class="box">
<h3>TruLens can also help you to identify which of your LLM app versions is the best performing
</h3>
<li>Understand which version of your LLM apps is producing the best results across a variety of
metrics
</li>
<li>Understand which model version has the lowest dollar cost (via API call volume) or risk
<li>Make informed trade-offs between cost, latency and response quality.
</li>
</div>
</ul>
Expand Down
4 changes: 2 additions & 2 deletions nn-explainability.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -113,11 +113,11 @@
<a href="https://github.com/truera/trulens" target="_blank">
<li>GitHub</li>
</a>
<a href="/welcome/">
<a href="/trulens_explain/install/">
<li>Documentation</li>
</a>
<a href="/">
<li>TruLens for LLMs</li>
<li>TruLens-Eval</li>
</a>

<a href="https://pypi.org/project/trulens/" target="_blank"
Expand Down
Loading

0 comments on commit 8450199

Please sign in to comment.