RAG, Agents & Fine-Tuning

32 free rag, agents & fine-tuning tools in the AI Tools collection — every one runs in your browser with no signup and no uploads.

AI Agent Escalation Policy Generator

Design a human-in-the-loop escalation policy for AI agents

AI Agent Design Planner

Design the architecture of your AI agent before writing code

Fine-Tune Training Data Builder (BYO Key)

Generate JSONL training pairs for fine-tuning your own LLM

Embedding Model Comparison Table

Compare text embedding models by dimensions, cost, and MTEB score

Batch Size Optimizer for Embedding Jobs

Find the optimal embedding batch size for throughput and cost

RAG Context Pruner

Drop low-relevance sentences from retrieved context to cut tokens before the LLM call.

Context Relevance Scorer (BYO-key)

Score retrieved context chunks for relevance to your question using an LLM.

Context Window Size vs Retrieval Quality Tradeoff

Model the cost-quality tradeoff as you retrieve more context chunks.

Cosine Similarity Calculator

Compute cosine similarity between two embedding vectors.

Embedding Dimension Visualizer

Project high-dimensional embedding vectors to 2D with PCA and see semantic clusters.

Embedding Freshness Decay Calculator

Model how document embedding relevance decays over time for time-sensitive RAG.

Embedding Model Comparison Table

Compare text embedding models by dimensions, cost, max tokens, and MTEB score.

Embedding Nearest Neighbor Finder (BYO-key)

Find the most similar text from a list using real embeddings.

Embedding Quantization Estimator

Estimate storage savings vs accuracy impact for embedding quantization.

Textual Inversion Embedding Guide

Use embeddings in SD prompts with correct syntax and placement

Paragraph Reorderer

Reorder paragraphs in a long LLM response to improve structure.

Multi-Query RAG Query Expander (BYO-key)

Generate multiple retrieval queries from one user question for better recall.

RAG Architecture Planner

Plan your Retrieval-Augmented Generation stack interactively

RAG Chunk Size & Overlap Calculator

Find the optimal chunk size and overlap for your RAG pipeline.

RAG Context Window Optimizer

Maximize relevant context in your prompt while staying within token limits.

RAG Document Metadata Tagger (BYO-key)

Auto-generate metadata tags for documents before indexing into a vector store.

RAG Eval Dataset Builder

Build question / context / answer triples for evaluating your RAG pipeline.

Hybrid Search Weight Tuner

Find the optimal alpha between BM25 and dense retrieval for hybrid RAG.

Parent-Child Chunker Preview

Preview parent-document + child-chunk splitting for hierarchical RAG.

RAG Pipeline Designer

Design your retrieval-augmented generation pipeline and export a diagram.

RAG Query Analyzer

Analyze your user queries to predict RAG retrieval difficulty and type.

RAG Query Rewriter

Rewrite user questions into better vector search queries

Retrieval Context Formatter

Format RAG-retrieved chunks into a clean context block for your prompt.

Retrieval Precision & Recall Calculator

Evaluate your RAG retrieval quality with precision, recall, and F1.

Top-K Retrieval Simulator

Simulate top-k retrieval and see recall, precision, and MRR for k = 1, 3, 5, 10.

Vector Arithmetic Playground

Perform add, subtract, and interpolate operations on embedding vectors.

Vector Distance Suite

Compare embedding vectors with cosine, dot, Euclidean, and Manhattan distance.