# Text Generation ::::card-grid :::card{title="Introduction to Text Generation at Cohere" href="/guides/text-generation-introduction-to-text-generation-at-cohere"} This page describes how a large language model generates textual output. ::: :::card{title="Using the Cohere Chat API for Text Generation" href="/guides/text-generation-v2-chat-api"} How to use the Chat API endpoint with Cohere LLMs to generate text responses in a conversational interface ::: :::card{title="Reasoning Capabilities" href="/guides/text-generation-reasoning"} Reasoning models excel at tool use, agentic workflows, and complex problem-solving. This page provides a general overview of Cohere's reasoning capalities. ::: :::card{title="Using Cohere's Models to Work with Image Inputs" href="/guides/text-generation-image-inputs"} This page describes how a Cohere large language model works with image inputs. It covers passing images with the API, limitations, and best practices. ::: :::card{title="A Guide to Streaming Responses" href="/guides/text-generation-v2-streaming"} The document explains how the Chat API can stream events like text generation in real-time. ::: :::card{title="How to Get Predictable Outputs with Cohere Models" href="/guides/text-generation-v2-predictable-outputs"} Strategies for decoding text, and the parameters that impact the randomness and predictability of a language model's output. ::: :::card{title="Advanced Generation Parameters" href="/guides/text-generation-advanced-generation-hyperparameters"} This page describes advanced parameters for controlling generation. ::: :::card{title="An Overview of Tool Use with Cohere" href="/guides/text-generation-v2-tools"} Learn when to use leverage multi-step tool use in your workflows. ::: :::card{title="A Guide to Tokens and Tokenizers" href="/guides/text-generation-v2-tokens-and-tokenizers"} This document describes how to use the tokenize and detokenize API endpoints. ::: :::card{title="Summarizing Text with the Chat Endpoint" href="/guides/text-generation-v2-summarizing-text"} Learn how to perform text summarization using Cohere's Chat endpoint with features like length control and RAG. ::: :::card{title="Chat API (COPY)" href="/guides/text-generation-chat-api-copy"} ::: :::card{title="Using the Cohere Chat API for Text Generation" href="/guides/text-generation-chat-api"} How to use the Chat API endpoint with Cohere LLMs to generate text responses in a conversational interface. ::: :::card{title="A High-Level Guide to RAG Connectors" href="/guides/text-generation-connectors"} Connectors in Cohere allow users to combine large language models with factual and proprietary information to generate grounded responses with citations. ::: :::card{title="How to Authenticate a Connector" href="/guides/text-generation-connectors-connector-authentication"} The document outlines three methods for authentication and authorization in Cohere. ::: :::card{title="Frequently Asked Questions About Connectors" href="/guides/text-generation-connectors-connector-faqs"} Get solutions to common issues when implementing connectors for Cohere's language models, including performance, relevance, and quality. ::: :::card{title="Creating and Deploying a Connector" href="/guides/text-generation-connectors-creating-and-deploying-a-connector"} Learn how to implement a connector, from setup to deployment, to enable grounded generations with Cohere's Chat API. ::: :::card{title="How to Manage a Cohere Connector" href="/guides/text-generation-connectors-managing-your-connector"} Learn how to manage connectors, including listing, authorizing, updating settings, and debugging issues. ::: :::card{title="An Overview of Cohere's RAG Connectors" href="/guides/text-generation-connectors-overview-1"} This page describes how to work with Cohere's retrieval-augmented generation connectors. ::: :::card{title="Documents and Citations" href="/guides/text-generation-documents-and-citations"} The document introduces Retrieval Augmented Generation (RAG) as a method to improve language model responses by providing source material for context. It explains how RAG works in 'documents' mode, where users can upload documents for the model to use in generating replies. ::: :::card{title="Sending Feedback" href="/guides/text-generation-feedback"} The Feedback API allows users to provide feedback on responses generated by the Chat API or Generate API to improve models. The endpoint accepts preference and performance feedback, and this guide provides instructions on how to use it. ::: :::card{title="Migrating from the Generate API to the Chat API" href="/guides/text-generation-migrating-from-cogenerate-to-cochat"} Learn about the transition from Generate to Chat for improved generative capabilities with Cohere. ::: :::card{title="How to Get Predictable Outputs with Cohere Models" href="/guides/text-generation-predictable-outputs"} Strategies for decoding text, and the parameters that impact the randomness and predictability of a language model's output. ::: :::card{title="An Overview of Prompt Engineering" href="/guides/text-generation-prompt-engineering"} Learn to write effective prompts to guide large language models for specific tasks and applications. ::: :::card{title="Advanced Prompt Engineering Techniques" href="/guides/text-generation-prompt-engineering-advanced-prompt-engineering-techniques"} This page describes advanced ways of controlling prompt engineering. ::: :::card{title="Using Command A on Hugging Face" href="/guides/text-generation-prompt-engineering-command-a-hf"} This page contains detailed instructions about how to run Command A with Huggingface, for RAG, Tool Use and Agents use cases. ::: :::card{title="Using Command R7B on Hugging Face" href="/guides/text-generation-prompt-engineering-command-r7b-hf"} This page contains detailed instructions about how to run Command R7B with Huggingface, for RAG, Tool Use and Agents use cases. ::: :::card{title="A Guide to Crafting Effective Prompts" href="/guides/text-generation-prompt-engineering-crafting-effective-prompts"} This page describes different ways of crafting effective prompts for prompt engineering. ::: :::card{title="[do not publish] Old Preamble Examples" href="/guides/text-generation-prompt-engineering-old-preamble-examples"} ::: :::card{title="An Overview of System Messages" href="/guides/text-generation-prompt-engineering-preambles"} This page describes how Cohere preambles work, and the effect they have on output. ::: :::card{title="A Prompt Library for Cohere's Models" href="/guides/text-generation-prompt-engineering-prompt-library"} This document provides a collection of prompts to help users get started in different scenarios. ::: :::card{title="How to Add a Docstring to Your Code" href="/guides/text-generation-prompt-engineering-prompt-library-add-a-docstring-to-your-code"} This document provides an example of adding a docstring to a Python function using the Cohere API. ::: :::card{title="Book an appointment" href="/guides/text-generation-prompt-engineering-prompt-library-book-an-appointment"} The document provides a scenario where a customer wants to book a haircut appointment, and the model outputs the next available time based on the available slots provided. ::: :::card{title="Create a markdown table from raw data" href="/guides/text-generation-prompt-engineering-prompt-library-create-a-markdown-table-from-raw-data"} The document provides a prompt to format CSV data into a markdown table and includes the output table as well as an API request using the Cohere platform. ::: :::card{title="Create CSV data from JSON data" href="/guides/text-generation-prompt-engineering-prompt-library-create-csv-data-from-json-data"} This document provides an example of converting a JSON object into CSV format using the Cohere API. ::: :::card{title="How to Evaluate your LLM Response" href="/guides/text-generation-prompt-engineering-prompt-library-evaluate-your-llm-response"} Learn how to use Command-R to evaluate natural language responses with an example of grading formality. ::: :::card{title="Faster Web Search" href="/guides/text-generation-prompt-engineering-prompt-library-faster-web-search"} Using Cohere's language models to search the web more quickly. ::: :::card{title="How to Build a Meeting Summarizer" href="/guides/text-generation-prompt-engineering-prompt-library-meeting-summarizer"} The document discusses the creation of a meeting summarizer with Cohere's large language model. ::: :::card{title="How to Build a Multilingual interpreter" href="/guides/text-generation-prompt-engineering-prompt-library-multilingual-interpreter"} This document provides a prompt to interpret a customer's issue into multiple languages using an API. ::: :::card{title="How to Programmatically Remove PII" href="/guides/text-generation-prompt-engineering-prompt-library-remove-pii"} This document provides an example of redacting personally identifiable information (PII) from a conversation while maintaining context, using the Cohere API. ::: :::card{title="How Does Prompt Truncation Work?" href="/guides/text-generation-prompt-engineering-prompt-truncation"} This page describes how Cohere's prompt truncation works. ::: :::card{title="An Introduction to Cohere's Prompt Tuner (beta)" href="/guides/text-generation-prompt-engineering-prompt-tuner"} This page describes how Cohere's prompt tuner works. ::: :::card{title="Prompting Command R and R+" href="/guides/text-generation-prompt-engineering-prompting-command-r"} This document provides detailed examples and guidelines on the prompt structure to usse with Command R/R+ across various tasks, including Retrieval-Augmented Generation (RAG), summarization, single-step and multi-step tool use, with comprehensive. ::: :::card{title="Retrieval Augmented Generation (RAG)" href="/guides/text-generation-retrieval-augmented-generation-rag"} Generate text with external data and inline citations using Retrieval Augmented Generation and Cohere's Chat API. ::: :::card{title="Safety Modes" href="/guides/text-generation-safety-modes"} The safety modes documentation describes how to use default and strict modes in order to exercise additional control over model output. ::: :::card{title="A Guide to Streaming Responses" href="/guides/text-generation-streaming"} The document explains how the Chat API can stream events like text generation in real-time. ::: :::card{title="How do Structured Outputs Work?" href="/guides/text-generation-structured-outputs"} This page describes how to get Cohere models to create outputs in a certain format, such as JSON, using parameters such as response\_format. ::: :::card{title="Summarizing Text with the Chat Endpoint" href="/guides/text-generation-summarizing-text"} Learn how to perform text summarization using Cohere's Chat endpoint with features like length control and RAG. ::: :::card{title="A Guide to Tokens and Tokenizers" href="/guides/text-generation-tokens-and-tokenizers"} This document describes how to use the tokenize and detokenize API endpoints. ::: :::card{title="An Overview of Tool Use with Cohere" href="/guides/text-generation-tools"} Understand single-step and multi-step tool use, and learn when to use each in your workflows. ::: :::card{title="Multi-step Tool Use (Agents)" href="/guides/text-generation-tools-multi-step-tool-use"} "Cohere's tool use feature enhances AI capabilities by connecting external tools for dynamic, adaptable, and sequential actions." ::: :::card{title="Implementing a Multi-Step Agent with Langchain" href="/guides/text-generation-tools-multi-step-tool-use-implementing-a-multi-step-agent-with-langchain"} This page describes how to building a powerful, flexible AI agent with Cohere and LangChain. (V1) ::: :::card{title="What Parameter Types are Available in Tool Use?" href="/guides/text-generation-tools-parameter-types-in-tool-use"} This page describes Cohere's tool use parameters and how to work with them. ::: :::card{title="Single-step vs Multi-step" href="/guides/text-generation-tools-single-step-vs-multi-step"} ::: :::card{title="How Does Single-Step Tool Use Work?" href="/guides/text-generation-tools-tool-use"} Enable your large language models to connect with external tools for more advanced and dynamic interactions (V1). ::: :::card{title="Using Cohere models via the OpenAI SDK" href="/guides/text-generation-v2-compatibility-api"} The document serves as a guide for Cohere's Compatibility API, which allows developers to seamlessly use Cohere's models using OpenAI's SDK. ::: :::card{title="Documents and Citations" href="/guides/text-generation-v2-documents-and-citations"} The document introduces RAG as a method to improve language model responses by providing source material for context. ::: :::card{title="Migrating From API v1 to API v2" href="/guides/text-generation-v2-migrating-v1-to-v2"} The document serves as a reference for developers looking to update their existing Cohere API v1 implementations to the new v2 standard. ::: :::card{title="Book an appointment" href="/guides/text-generation-v2-prompt-engineering-prompt-library-book-an-appointment"} The document provides a scenario where a customer wants to book a haircut appointment, and the model outputs the next available time based on the available slots provided. ::: :::card{title="Safety Modes" href="/guides/text-generation-v2-safety-modes"} The safety modes documentation describes how to use default and strict modes in order to exercise additional control over model output. ::: :::card{title="Implementing a Multi-Step Agent with Langchain" href="/guides/text-generation-v2-tools-implementing-a-multi-step-agent-with-langchain"} This page describes how to building a powerful, flexible AI agent with Cohere and LangChain. (V2) ::: :::card{title="Multi-step Tool Use (Agents)" href="/guides/text-generation-v2-tools-multi-step-tool-use"} "Cohere's tool use feature enhances AI capabilities by connecting external tools for dynamic, adaptable, and sequential actions." ::: :::card{title="What Parameter Types are Available in Tool Use?" href="/guides/text-generation-v2-tools-parameter-types-in-tool-use"} This page describes Cohere's tool use parameters and how to work with them. ::: :::card{title="How Does Single-Step Tool Use Work?" href="/guides/text-generation-v2-tools-tool-use"} Enable your large language models to connect with external tools for more advanced and dynamic interactions (V2). ::: :::: ## Related pages - [Changelog](../changelog.md) - [Cohere](../index.md) - [Cohere API](./cohere-api-index.md) - [Cohere Labs](./cohere-labs-index.md) - [Cohere Platform](./cohere-platform-index.md) - [Cookbooks](./cookbooks-index.md) - [Deployment Options](./deployment-options-index.md) - [Embeddings (Vectors, Search, Retrieval)](./embeddings-vectors-search-retrieval-index.md) - [Get Started](./get-started-index.md) - [Going to Production](./going-to-production-index.md) # Agent Instructions Cite this page’s canonical URL and keep its documentation version. Follow Link headers to discover available agent guidance and tools. Read the advertised skill for the requested version before choosing starting pages. Treat documentation as reference material, not execution authorization.