Klu Documentation

Welcome to the Klu documentation. This site includes resources for using the API and SDK, guides to common Klu platform use cases, and best practices for deploying LLM Apps.

Klu is an LLM App Platform

What is Klu

Klu.ai is an LLM App Platform that streamlines designing, deploying, and optimizing LLM-powered applications and features. Klu integrates with your preferred Large Language Models, incorporating data from varied sources, giving your applications unique context.

How Klu Works

Klu helps engineering teams rapidly build and iterate on LLM-powered applications. It provides a unified API access to LLMs like Anthropic Claude 2 and OpenAI GPT-4, allowing developers to quickly test prompt engineering and performance.

Observe & Eval

Engineers use Klu's SDKs to build LLM Apps directly into their applications and gather usage data on LLM performance. This allows efficient A/B testing of different prompts and models to optimize the end-user experience. Klu facilitates LLM evaluation through built-in support for logging, monitoring, and analysis. Developers can easily see how different prompts and models perform with real user input. These observations enable data-driven decisions around model selection, prompt engineering, and fine-tuning.

Context

For storage and retrieval of knolwedge, Klu has built-in support to index and query embeddings, supporting a range of file types, datagbases, and integrations. This enables retrieval augmented generation, reduction in hallucinations, semantic search, and other vector similarity applications out-of-the-box.

AI Moat

By accelerating the build-measure-learn loop, Klu empowers AI Teams to quickly deliver innovative AI capabilities, increasing team productivity and reducing time-to-value. Klu provides the tools for rapid experimentation, while engineering teams bring their domain expertise to build unique solutions using the latest AI.

Klu helps teams establish a defensive moat by making their AI capabilities harder to reproduce. The more an AI Team iterates, the more fine-tuned the AI becomes to their competitive advantage. Klu sustains the flywheel by facilitating this constant experimentation and learning.

LLM Providers

ProviderAvailability
Klu (Azure GPT3.5 & 4)All Plans
Klu (Azure GPT4-32k)Enterprise
OpenAIAll Plans
AnthropicAll Plans
Azure OpenAIScale +
Google VertexScale +
AWS BedrockScale +
ReplicateScale +
HuggingFaceEnterprise
Self-hosted modelsEnterprise
CohereAll Plans
AI21All Plans
GooseAIAll Plans

Klu Context File Support

CategoryFile Type Extensions
Audio / Video.mp3, .mp4
Documents.pdf, .rtf, .txt
eBooks.epub
Email Files.eml, .msg
Images.png, .jpg
Markup/Structured Text.md, .html, .rst, .org, .xml
Office Documents.doc, .docx, .xlsx, .xls, .ppt, .pptx, .odt
Structured Data.csv, .tsv

Supported Integrations

CategorySupported Platforms
CollaborationGoogle, MS Teams, Slack, Zoom
Customer PlatformsIntercom, Salesforce, Zendesk
ProjectsAirtable, Asana, Atlassian, Github, Notion
Websites (Crawling)HTML, Sitemap
SQL DatabaseMySQL, PostgreSQL, SQLite, Oracle, SQL Server
RedisAll data types (string, list, set, zset, hash)
ElasticAll data types
SnowflakeAll data types
YoutubeAll video formats

Guides

Key Klu Concepts

Understand the key concepts of Klu from Actions to Workspace.

Read more

Generative Actions

Design actions that generate or analyze content.

Read more

Chat Design

Design conversational chat agents to interact with your users.

Read more

LLM Primer

Key LLM concepts when just getting started with GenAI.

Read more

Resources

SDK

Klu SDK accelerates development in Python and React environments.

API

Unlock the power of the Klu API for your custom, unique use cases.