Welcome to the Literal AI Cookbooks and Guides repository! This repository is dedicated to providing users with comprehensive cookbooks and guides designed to help you understand and implement AI solutions effectively.
Literal AI is an end-to-end observability, evaluation and monitoring platform for building & improving production-grade LLM applications.
For more information, find the full documentation here. Cookbooks from this repo and more guides are presented in the docs with explanations.
Name | Category | Description |
---|---|---|
Context Relevancy with Ragas | Evaluation | Build a RAG application and evaluate this with RAGAS based on context relevancy. |
Evaluate User Satisfaction - Customer Support Conversations | Evaluation | Retrieve your Customer Support Conversations from Literal AI and evaluate user satisfaction on this conversational data. |
LlamaIndex Integration | Observability | Build a Q&A application with LLamaIndex and monitor it with Literal AI. |
Evaluate Agent Runs with Tools | Observability (Tools) & Evaluation | Build a simple agent which can use two tools. Monitor and evaluate the tool usage. |
A/B Testing Client-Side | Evaluation | Build two prompts, randomly assign to new conversations and A/B test on a metric. |
Name | Category | Description |
---|---|---|
Prompt Iteration with Promptfoo | Evaluation | Run a simple chat application and evaluate its results with two different prompt templates with Promptfoo. |
Chatbot using Next.js, Vercel ai SDK, OpenAI and Literal AI | Observablity | Create a personalized and monitored chatbot with OpenAI, Next.js and Literal AI. |