Platform • Docs • Blog • Discord

Together Cookbook

The Together Cookbook is a collection of code and guides designed to help developers build with open source models using Together AI. The best way to use the recipes is to copy code snippets and integrate them into your own projects!

Contributing

We welcome contributions to this repository! If you have a cookbook you'd like to add, please reach out to use the Discord or open a pull request!

Prerequisites

To make the most of the examples in this cookbook, you'll need a Together AI API key (sign up for free here).

While the code examples are primarily written in Python/JS, the concepts can be adapted to any programming language that supports interaction with the Together API.

Cookbooks

Cookbook	Description	Open
Agents
Serial Chain Agent Workflow	Chain multiple LLM calls sequentially to process complex tasks.
Conditional Router Agent Workflow	Create an agent that routes tasks to specialized models.
Parallel Agent Workflow	Run multiple LLMs in parallel and aggregate their solutions.
Orchestrator Subtask Agent Workflow	Break down tasks into parallel subtasks executed by LLMs.
Looping Agent Workflow	Build an agent that iteratively improves responses.
Together Open Deep Research	An open source deep-research implementation with multi-step web search.
Together Open Data Science Agent	An open data-science agent that analyzes datasets end-to-end.
Agno Agents	Build agents with the Agno framework on Together.
Arcade Agents	Build agents with Arcade.dev tool integrations.
Composio Agents	Use Composio tools to build production-grade agents.
DSPy Agents	Build optimized agents with DSPy and Together models.
Klavis AI Agents	Use Klavis AI to give agents access to MCP-based tools.
Agentic RAG with LangGraph	Build an agentic RAG pipeline with LangGraph.
LangGraph Planning Agent	Build a plan-and-execute agent with LangGraph.
PydanticAI Agents	Build type-safe agents with PydanticAI and Together.
Evals
Classification Evals	LLM-as-a-Judge for safety evaluation and classification tasks.
Compare Evals	Head-to-head model comparison on summarization tasks.
Prompt Evals	Prompt optimization through A/B testing and comparison.
Optimizing LLM Judges	Tune LLM-as-judge configurations for better alignment with humans.
GEPA Optimization	Optimize prompts via genetic prompt evolution (GEPA) on Together.
Fine-tuning
End-to-end Fine-tuning Guide	Fine-tuning basics and best practices.
LoRA Inference and Fine-tuning	Perform LoRA fine-tuning and inference on Together AI.
Preference Tuning - DPO	Fine-tuning LLMs with preference data using DPO.
Continual Fine-tuning	Continuously fine-tune model checkpoints on new data.
Function Calling Fine-tuning	Fine-tune LLMs for tool/function-calling use cases.
Reasoning Fine-tuning	Fine-tune LLMs with reasoning traces.
Vision-Language Fine-tuning	Fine-tune VLMs on image+text data.
Long Context Fine-tuning for Repetition	Fine-tune LLMs to repeat back words in long sequences.
Summarization Long Context Fine-tuning	Long context fine-tuning to improve summarization.
Multi-turn Conversation Fine-tuning	Fine-tune LLMs on multi-step conversations.
Retrieval-augmented generation
RAG with Reasoning Models	RAG + source citations with DeepSeek R1.
Multimodal RAG with Nvidia Slide Deck	Multimodal RAG using Nvidia investor slides.
Open Contextual RAG	An implementation of Contextual Retrieval using open models.
Contextual RAG on Union	Deploy a contextual RAG service end-to-end on Union.ai.
Text RAG	Text-based Retrieval-Augmented Generation.
Search
Multimodal Search and Conditional Image Generation	Text-to-image and image-to-image search and conditional image generation.
Embedding Visualization	Visualize vector embeddings.
Search with Reranking	Improve search results with rerankers.
Semantic Search	Vector search with embedding models.
Multimodal — Vision
OCR	Text extraction, multilingual OCR, and text spotting with Qwen3-VL.
2D Grounding	Object detection with 2D bounding boxes and point grounding.
3D Grounding	3D bounding boxes, camera parameters, depth perception.
Spatial Understanding	Object relationships, affordances, embodied reasoning.
Video Understanding	Video description, temporal localization, video Q&A.
Omni Recognition	Universal recognition for celebrities, anime, food, landmarks.
Document Parsing	Convert documents to HTML/Markdown with coordinates.
Image to Code	Screenshot to HTML, chart to matplotlib code.
Long Document Understanding	Multi-page PDF analysis and Q&A.
Examples
Together Code Interpreter	Execute code with Together Code Interpreter (TCI).
Thinking Augmented Generation	Give R1 thinking tokens to small models.
Flux LoRA Inference	Generate images with fine-tuned Flux LoRAs.
Structured Text Extraction from Images	Extract structured text from images.
Summarization Evaluation	Summarize and evaluate outputs with LLMs.
PDF to Podcast	Generate a podcast from PDF content (NotebookLM-style).
Knowledge Graphs with Structured Outputs	Get LLMs to generate knowledge graphs.
Getting Started with Llama 4	Get started with Llama 4 models.
Batch Inference & Evals	Batch inference and evaluation workflows.
Third-Party Integrations
Tool Use with Toolhouse	Use Toolhouse tools with Together's function-calling models.
OpenEnv
OpenEnv Code Interpreter	An OpenEnv environment that wraps the Together Code Interpreter.	—
OpenEnv GRPO BlackJack	Train Blackjack policies via GRPO using OpenEnv on Together.	—

Explore Further

Looking for more resources to enhance your experience with open source models? Check out these helpful links:

• Together AI developer documentation
• Together AI API support docs
• Together AI Discord community

Additional Resources

• Together AI Research: Explore papers and technical blog posts from our research team.
• Together AI Blog: Explore technical blogs, product announcements and more on our blog.