For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
DASHBOARDPLAYGROUNDDOCSCOMMUNITYLOG IN
Guides and conceptsAPI ReferenceRelease NotesLLMUCookbooks
Guides and conceptsAPI ReferenceRelease NotesLLMUCookbooks
    • Cookbooks
    • Agent API Calls
    • Short-Term Memory Handling for Agents
    • Agentic Multi-Stage RAG with Cohere Tools API
    • Agentic RAG for PDFs with mixed data
    • Analysis of Form 10-K/10-Q Using Cohere and RAG
    • Analyzing Hacker News with Six Language Understanding Methods
    • Article Recommender with Text Embedding Classification Extraction
    • Multi-Step Tool Use
    • Basic RAG
    • Basic Semantic Search
    • Basic Tool Use
    • Calendar Agent with Native Multi Step Tool
    • Chunking Strategies
    • Creating a QA Bot From Technical Documentation
    • Financial CSV Agent with Native Multi-Step Cohere API
    • Financial CSV Agent with Langchain
    • Migrating away from create_csv_agent in langchain-cohere
    • A Data Analyst Agent Built with Cohere and Langchain
    • Advanced Document Parsing For Enterprises
    • End-to-end RAG using Elasticsearch and Cohere
    • Semantic Search with Cohere Embed Jobs and Pinecone serverless Solution
    • Semantic Search with Cohere Embed Jobs
    • Fueling Generative Content with Keyword Research
    • Grounded Summarization Using Command R
    • Hello World! Meet Language AI
    • Long Form General Strategies
    • Migrating Monolithic Prompts to Command-R with RAG
    • Multilingual Search with Cohere and Langchain
    • PDF Extractor with Native Multi Step Tool Use
    • Pondr, Fostering Connection through Good Conversation
    • Deep Dive Into RAG Evaluation
    • RAG With Chat Embed and Rerank via Pinecone
    • Demo of Rerank
    • SQL Agent
    • Summarization Evals
    • Text Classification Using Embeddings
    • Topic Modeling AI Papers
    • Wikipedia Semantic Search with Cohere + Weaviate
    • Wikipedia Semantic Search with Cohere Embedding Archives
    • Build Chatbots That Know Your Business with MongoDB and Cohere
    • Finetuning on Cohere's Platform
    • Deploy your finetuned model on AWS Marketplace
    • Finetuning on AWS Sagemaker
    • SQL Agent with Cohere and LangChain (i-5O Case Study)
    • Introduction to Aya Vision
    • Retrieval Evaluation with LLM-as-a-Judge via Pydantic AI
    • Document Translation with Command A Translate
LogoLogodocs
DASHBOARDPLAYGROUNDDOCSCOMMUNITYLOG IN
Built with

Cookbooks

Explore what you can build on Cohere’s generative AI platform. These ready-made guides will get you started with best-practices that get the most out of Cohere’s models. Everything is set up and ready for you to start testing!

Use Cases

Click on one of the section headers below to jump to guides for that use case category.

Agents
Open Source Software Integrations
Search and Embeddings
Cloud
RAG
Summarization
Finetuning
Other

Agents

Learn how to build powerful agents that use tools to connect to external services, like search engines, APIs, and databases. Agents can be used to automate tasks, answer questions, and more.

agents

Calendar Agent with Native Multi Step Tool

A minimal working example of how to use our chat API to call tools.

Build this
agents

Basic Tool Use

Connect large language models to external tools, like search engines, APIs, and databases, to access and utilise a wider range of data.

Build this
agentsoss

Multi-Step Tool Use

Multi-step tool use allows developers to connect Cohere's models to external tools like search engines, APIs, and databases.

Build this
agentsoss

A Data Analyst Agent Built with Cohere and Langchain

Build a data analyst agent with Python and Cohere's Command R+ mode and Langchain.

Build this
agents

Short-Term Memory Handling for Agents

A walkthrough of how to use Langchain cohere_react_agent to effectively manage short-term chat history that contains tool calls with Langchain.

Marco Del TrediciMarco Del Tredici
Build this
agents

Agent API Calls

A walkthrough of how to use Langchain cohere_react_agent to make API calls to external services that require regex.

Marco Del TrediciMarco Del Tredici
Build this
agentsoss

Financial CSV Agent with Langchain

The notebook demonstrates how to setup a Langchain Cohere ReAct Agent to answer questions over the income statement and balance sheet from Apple's SEC10K 2020 form.

Shaan DesaiShaan Desai
Build this
agents

Agentic RAG for PDFs with mixed data

A walkthrough of how to use Langchain cohere_react_agent to run RAG as an agent tool to handle PDFs with mixed table and text data.

Shaan DesaiShaan Desai
Build this
agents

SQL Agent

In this notebook we explore how to setup a Cohere ReAct Agent to answer questions over SQL Databases using Langchain's SQLDBToolkit.

Shaan DesaiShaan Desai
Build this
agents

SQL Agent with Cohere and LangChain (i-5O Case Study)

Build a SQL agent with Cohere and LangChain in the manufacturing industry.

Build this
agents

Financial CSV Agent with Native Multi-Step Cohere API

This notebook demonstrates how to setup a Cohere Native API sequence of tool calls to answer questions over the income statement and balance sheet from Apple's SEC10K 2020 form.

Jason JungJason Jung
Build this
agents

PDF Extractor with Native Multi Step Tool Use

How we can leverage agents to extract information from PDFs?

Jason JungJason Jung
Build this
agents

Agentic Multi-Stage RAG with Cohere Tools API

How to use Agents to improve RAG performance.

Jason JungJason Jung
Build this

Open Source Software Integrations

Cohere integrates natively with a variety of popular Open Source Software tools like LangChain and LlamaIndex. These guides will help you get started with these integrations.

agentsoss

Multi-Step Tool Use

Multi-step tool use allows developers to connect Cohere's models to external tools like search engines, APIs, and databases.

Build this
agentsoss

A Data Analyst Agent Built with Cohere and Langchain

Build a data analyst agent with Python and Cohere's Command R+ mode and Langchain.

Build this
agentsoss

Financial CSV Agent with Langchain

The notebook demonstrates how to setup a Langchain Cohere ReAct Agent to answer questions over the income statement and balance sheet from Apple's SEC10K 2020 form.

Shaan DesaiShaan Desai
Build this
searchoss

Multilingual Search with Cohere and Langchain

Multilingual search with Cohere and Langchain.

Build this
osssearchrag

Creating a QA Bot From Technical Documentation

Create a chatbot that answers user questions based on technical documentation using Cohere embeddings and LlamaIndex.

Build this
agentsosscsv

Migrating away from deprecated create_csv_agent in langchain-cohere

This page contains a tutorial on how to build a CSV agent without the deprecated `create_csv_agent` abstraction in langchain-cohere v0.3.5 and beyond.

Build this

Search and Embeddings

Learn how to embed and search text with Cohere. These guides will help you build semantic search engines, search Wikipedia, and more.

search

Wikipedia Semantic Search with Cohere Embedding Archives

Find relevant Wikipedia passages with semantic search and Cohere embeddings.

Build this
cloudsearch

Semantic Search with Cohere Embed Jobs and Pinecone serverless Solution

Learn how to use Cohere's Embed Jobs and Pinecone's serverless solution to perform semantic search.

Build this
searchragcloud

End-to-end RAG using Elasticsearch and Cohere

Learn how to use Cohere and Elastic for semantic search and retrieval-augmented generation.

Build this
search

Semantic Search with Cohere Embed Jobs

Learn how to use Cohere Embed Jobs to create semantic search functionality.

Build this
search

Basic Semantic Search

Learn how to build a simple semantic search engine using sentence embeddings.

Build this
searchoss

Multilingual Search with Cohere and Langchain

Multilingual search with Cohere and Langchain.

Build this
search

Wikipedia Semantic Search with Cohere + Weaviate

Search 10 million Wikipedia vectors with Cohere's multilingual model and Weaviate's public dataset.

Build this
osssearchrag

Creating a QA Bot From Technical Documentation

Create a chatbot that answers user questions based on technical documentation using Cohere embeddings and LlamaIndex.

Build this
search

Demo of Rerank

Improve search results with Cohere's Relevance Endpoint, which reranks documents for better accuracy.

Build this
search

RAG with MongoDB and Cohere

Build a chatbot that provides actionable insights on technology company market reports.

Build this
search

Retrieval Evaluation with LLM-as-a-Judge via Pydantic AI

Evaluate retrieval systems using LLMs as judges via Pydantic AI.

Build this

Cloud

Learn how to use Cohere's cloud-based services in your preferred environment. Cohere is integrated with most major cloud providers. These guides will help you get started wherever your code lives.

cloudsearch

Semantic Search with Cohere Embed Jobs and Pinecone serverless Solution

Learn how to use Cohere's Embed Jobs and Pinecone's serverless solution to perform semantic search.

Build this
searchragcloud

End-to-end RAG using Elasticsearch and Cohere

Learn how to use Cohere and Elastic for semantic search and retrieval-augmented generation.

Build this

RAG

Learn how to use Cohere's foundation model for Retrieval-Augmented Generation (RAG). RAG can be used to improve the accuracy of language models by combining them with a retrieval system. This allows the model to generate completions that are grounded in provided sources of truth.

rag

Basic RAG

RAG boosts the accuracy of language models by combining them with a retrieval system.

Build this
searchragcloud

End-to-end RAG using Elasticsearch and Cohere

Learn how to use Cohere and Elastic for semantic search and retrieval-augmented generation.

Build this
rag

Chunking Strategies

Explore chunking strategies for RAG systems.

Ania BialasAnia Bialas
Build this
rag

Migrating Monolithic Prompts to Command-R with RAG

Command-R simplifies prompt migration to RAG, reducing hallucination and improving conciseness and grounding.

Build this
rag

RAG With Chat Embed and Rerank via Pinecone

This notebook shows how to build a RAG-powered chatbot with Cohere's Chat endpoint.

Build this
osssearchrag

Creating a QA Bot From Technical Documentation

Create a chatbot that answers user questions based on technical documentation using Cohere embeddings and LlamaIndex.

Build this
rag

Deep Dive Into RAG Evaluation

Learn how to evaluate RAG models.

Marco Del TrediciMarco Del Tredici
Aal PatankarAal Patankar
Build this

Summarization

Learn how to summarize long documents, meeting summaries, and technical reports. Summarization is a key feature of Cohere's Command model, which can be used to generate summaries of long documents with citations.

summarization

Analysis of Form 10-K/10-Q Using Cohere and RAG

Jumpstart financial analysis of 10-Ks or 10-Qs with Cohere's Command model and LlamaIndex tooling.

Alex BarbetAlex Barbet
Build this
summarization

Long Form General Strategies

Techniques to address lengthy documents exceeding the context window of LLMs.

Ania BialasAnia Bialas
Build this
summarization

Summarization Evals

This cookbook demonstrates an approach to evaluating summarization tasks using LLM evaluation.

Build this
summarization

Grounded Summarization Using Command R

Learn how to summarise long documents with citations, reducing cost and improving latency.

Build this

Finetuning

Learn how to finetune Cohere's models using custom data. Finetuning allows you to adapt Cohere's models to your specific use case, improving performance and accuracy.

finetuningwandb

Finetuning on Cohere's Platform

An example of finetuning using Cohere's platform and a financial dataset.

Komal TeruKomal Teru
Build this
finetuningsagemaker

Deploy your finetuned model on AWS Marketplace

Learn how to deploy your finetuned model on AWS Marketplace.

Youran QiYouran Qi
Build this
finetuningsagemaker

Finetuning on AWS Sagemaker

Learn how to finetune one of Cohere's models on AWS Sagemaker.

Mike MaoMike Mao
Build this

Other

Here are a variety of other fun and useful guides to help you get started with Cohere. From text classification to document parsing, there's something for everyone!

Fueling Generative Content with Keyword Research

Enhance content creation with keyword-based topic clusters, generating blog ideas with Cohere's Chat model.

Build this

Text Classification Using Embeddings

Build a text classifier with Cohere embeddings. This notebook shows you how to train a sentiment analysis model with a small dataset.

Build this

Article Recommender with Text Embedding Classification Extraction

Improve news article recommendations with embeddings, text classification, and keyword extraction.

Build this

Advanced Document Parsing For Enterprises

Learn how to parse PDFs into text with a real-world example.

Giannis ChatziveroglouGiannis Chatziveroglou
Justin LeeJustin Lee
Build this

Pondr, Fostering Connection through Good Conversation

Learn how to create Pondr, a game that fosters connections and meaningful conversations with friends and strangers.

Build this

Hello World! Meet Language AI

General quickstart with basic instructions on how to get started with generative AI.

Build this

Topic Modeling AI Papers

Learn how to build a topic modeling pipeline in Python.

Build this

Analyzing Hacker News with Six Language Understanding Methods

Learn how to analyze textual data using Cohere's tools.

Build this

Introduction to Aya Vision: A state-of-the-art open-weights vision model

Explore the capabilities of Aya Vision, which can take text and image inputs to generates text responses.

Build this

Document Translation with Command A Translate

Learn how to use Command A Translate for automated translation across 23 languages with industry-leading performance.

Build this