Models01 Intro Basics (0)02 Prepare Dataset (0)A Data Analyst Agent Built with Cohere and Langchain (0)A2A vs MCP (0)A2A vs MCP (0)Access the W&B MCP Server (0)Add labels to runs with tags (0)Add W&B (wandb) to your code (0)Add W&B to a Python library (0)Advanced Document Parsing For Enterprises (0)Agent definitions (0)Agent Workflows (0)Agentic RAG for PDFs with mixed data (0)Agents & Conversations (0)Agents Function Calling (0)Agents Handoffs (0)Agents Introduction (0)AI Capabilities and Limitations (0)AI Evaluations UI (0)AI for Everyone (0)AI Landscape for Product Leaders (0)AI Models for ADK agents (0)AI Vendor & Platform Evaluation (0)Amazon Bedrock (0)Ambassador (0)An Overview of Cohere's Models (0)An Overview of Cohere's Rerank Model (0)An Overview of The Cohere Platform (0)An Overview of the Developer Playground (0)Analysis of Form 10-K/10-Q Using Cohere and RAG (0)Annotate collections (0)Annotations (0)Anthropic (0)Antitrust Policy (0)Apigee AI Gateway (0)Apply patch (0)Architecture (0)Architecture overview (0)Artifact data privacy and compliance (0)Audio & Transcription (0)Authorization (0)Authorization Extensions (0)Automation events and scopes (0)Available models (0)Available Models (0)AWS Bedrock (0)AWS Certified AI Practitioner (0)AWS Private Deployment Guide (EC2 and EKS) (0)Aya Expanse (0)Aya Family of Models (0)Aya Vision (0)Azure AI (0)Azure AI Fundamentals (AI-900) (0)Azure OpenAI Fine-Tuning (0)Bar plots (0)Baseten (0)Basic OCR (0)Basic RAG (0)Basic Semantic Search with Cohere Models (0)Batch Inference (0)Bedrock (0)Bedrock (0)BEMA for Reference Model (0)Bienvenue to Mistral AI Documentation (0)Build an evaluation (0)Build an MCP App (0)Build an MCP client (0)Build an MCP server (0)Build an Onboarding Assistant with Cohere! (0)Build with Agent Skills (0)Build with Claude — Overview (0)Build with Fireworks AI (0)Building AI (0)Building RAG models with Cohere (0)Cancellation (0)Cerebras (0)Chat (0)Checkpoints and Resume (0)Choosing A Model (0)Chroma BM25 (0)Chroma Cloud Qwen (0)Chroma Cloud Splade (0)Citation Formatting (0)Citations and References (0)Classifier Factory (0)Claude (0)Claude API Essentials (0)Claude Code (0)Claude with Amazon Bedrock (0)Claude with Google Cloud's Vertex AI (0)CLI command reference (0)Clone and export reports (0)Cloud (0)Cloudflare Workers AI (0)Code Embeddings (0)Code generation (0)Code Interpreter (0)Code Interpreter (0)Coding (0)Cohere (0)Cohere (0)Cohere Chat on LangChain (Integration Guide) (0)Cohere Embed on LangChain (Integration Guide) (0)Cohere Models on Amazon Bedrock (0)Cohere on Amazon Web Services (AWS) (0)Cohere on Oracle Cloud Infrastructure (OCI) (0)Cohere on the Microsoft Azure Platform (0)Cohere Rerank on LangChain (Integration Guide) (0)Cohere Text Generation Tutorial (0)Cohere's Command A Reasoning Model (0)Cohere's Command A Translate Model (0)Cohere's Command A Vision Model (0)Cohere's Command R Model (0)Cohere's Command R+ Model (0)Cohere's Command R7B Model (0)Cohere's Embed Models (Details and Application) (0)Cohere's Rerank Model (Details and Application) (0)Collaborate on reports (0)Command R and Command R+ Model Card (0)Compare and rank models (0)Compare model performance using the Evaluation Playground (0)Compare models provided by VertexAI on RAG-based Q&A task using Ragas metrics (0)Compare run metrics (0)Compare runs across projects (0)Compare traces and other logged information (0)Completion (0)Configuration (0)Configure experiments (0)Configure prompt settings (0)Configure registry access (0)Connect Claude Code to tools via MCP (0)Connect to a custom model (0)Connect to an OpenAI compliant model provider/proxy (0)Connect to any LLM (0)Connect to local MCP servers (0)Connect to remote MCP Servers (0)Connectors and MCP servers (0)Connectors Overview (0)Console logs (0)Contribute (0)Contributing to MCP (0)Contributor Communication (0)Contributor Ladder (0)Conversation Simulator Model Callback (0)Conversation state (0)Cost optimization (0)Cost Optimization (0)Counting tokens (0)Create a collection (0)Create a registry (0)Create a report (0)Create a Slack automation (0)Create a webhook automation (0)Create an artifact (0)Create an artifact alias (0)Create an artifact version (0)Create an experiment (0)Create and track plots from experiments (0)Create Model (0)Custom Model Cost (0)Custom model providers (0)Custom model providers (0)Custom models (0)Custom Models (0)Custom Structured Output (0)Customise models (0)Customize log axes (0)Customize run colors (0)Customizing Prompts (0)Data modeling (0)Debug model vs. Pinecone recall issues (0)Debugging (0)Dedicated Inference (0)Dedicated Models (0)Deep Learning Specialization (0)Deep research (0)DeepSeek R1 Quickstart (0)Delete an artifact (0)Delete Model (0)Delete Model Checkpoints (0)Delete registry (0)Delete runs (0)Deploy Finetuned Command Models from AWS Marketplace (0)Deploy with Cerebrium (0)Deploy with Cloudflare Workers AI (0)Deploy with SkyPilot (0)Deploy your finetuned model on AWS Marketplace (0)Deploying a Fine-tuned Model (0)Deploying Fine Tuned Models (0)Deploying Models in Private Environments (0)Deployment Options - Overview (0)Deployments Quickstart (0)Design Principles (0)Direct Model Requests (0)Direct preference optimization (0)Document AI (0)Document Library (0)Document QnA (0)Download an artifact from a registry (0)Download and use artifacts (0)download the validation and reformat script (0)Edit a report (0)Elicitation (0)Embed a report (0)Embed objects (0)Embeddings & Reranking (0)Embeddings Overview (0)Enterprise-Managed Authorization (0)Environment variables (0)Evaluate a hosted API model (0)Evaluate a model checkpoint (0)Evaluate external models (0)Evaluate using local scorers (0)Evaluating Text Summarization Models (0)Evaluation (0)Evaluation benchmark catalog (0)Evaluations with Vertex AI models (0)Example Clients (0)Example reports (0)Example Servers (0)Example tables (0)Experiments limits and performance (0)Explore artifact lineage graphs (0)Export table data (0)Extended Thinking (0)Extension Support Matrix (0)Extensions Overview (0)Filter runs (0)Financial CSV Agent with Langchain (0)Financial CSV Agent with Native Multi-Step Cohere API (0)Find and customize a run's ID or name (0)Find registry items (0)Fine-tuning (0)Fine-Tuning Across Providers (0)Fine-tuning best practices (0)Fine-tuning BYOM (0)Fine-tuning Guide (0)Fine-Tuning Large Language Models (0)Finetuning Cohere Models on AWS Sagemaker (0)Fireworks Agent Overview (0)Fireworks Agent: Classification (0)Fireworks Agent: Preference Learning (DPO/ORPO) (0)Fork a run (0)Frequently Asked Questions (0)Frequently Asked Questions About Cohere (0)Fueling Generative Content with Keyword Research (0)Function calling (0)Function calling (0)Function Calling Fine-tuning (0)Fundamentals of Deep Learning (0)Gemini (0)Gemma (0)Generate dense embeddings (0)Generate sparse embeddings (0)Generative AI Explained (0)Generative AI Foundations (0)Generative AI Glossary for Business Leaders (0)Generative AI's Act Two (0)get data from hugging face (0)Get Started with W&B Models (0)GitHub Copilot (0)Glossary (0)Going Live with a Cohere Model (0)Google (0)Google (0)Google Cloud ML Engineer Learning Path (0)Google Gemini (0)Governance and Stewardship (0)Groq (0)Groq (0)Grounded Summarization Using Command R (0)Group Charter Template (0)Guides Using Custom Embedding Models (0)How 100 Enterprise CIOs Are Building and Buying Gen AI in 2025 (0)How do Structured Outputs Work? (0)How Does Cohere's Pricing Work? (0)How to Authenticate When Publishing to the Official MCP Registry (0)How to Automate Publishing with GitHub Actions (0)How to Get Predictable Outputs with Cohere Models (0)How to handle model rate limits (0)How To Improve Search With Rerankers (0)How to use Cline with DeepSeek V3 to build faster (0)How to use OpenCode with Together AI to build faster (0)How to use Qwen Code with Together AI for enhanced development workflow (0)Hugging Face (0)Hugging Face (0)Hugging Face (0)Hugging Face Accelerate (0)Hugging Face Diffusers (0)Hugging Face Server (0)Hugging Face Simple Transformers (0)Hugging Face Transformers (0)Hydra (0)IBM watsonx.ai (0)Image generation (0)Image Generation (0)Image Generation with Flux2 (0)Import and export data (0)Initialize a sweep (0)Initialize runs (0)Instructor (0)Instructor (0)Integrating Embedding Models with Other Tools (0)Integrations (0)Intro to Deep Learning (0)Intro to Machine Learning (0)Introduction to AI (0)Introduction to Generative AI (0)Introduction to Text Generation at Cohere (0)Introduction to the Anthropic Platform (0)Jina AI (0)JSON mode (0)Keras (0)Key Changes (0)Keyboard shortcuts (0)Kimi K2 family (0)Kimi K2 QuickStart (0)Kimi K2 Thinking QuickStart (0)Kimi K2.5 Quickstart (0)La Plateforme (0)LangChain overview (0)LangChain overview (0)LangDB Integration (0)LangSmith shared responsibility model (0)Language Models (0)Learn How Cohere's Rerank Models Work (0)Learn more about sweeps (0)Lifecycle (0)Line plot reference (0)Lineage graphs and audit history (0)Link an artifact version to a collection (0)List Model Checkpoints (0)List Models (0)List Models (0)LiteLLM (0)LiteLLM integration (0)LiteRT-LM (0)Llama 4 Quickstart (0)LlamaIndex and Cohere's Models (0)LLM Call Hooks (0)LLM Course (0)LLM gateway configuration (0)LLMs (0)Log (0)Log distributed training experiments (0)Log media and objects (0)Log models (0)Log summary metrics (0)Log tables (0)Log tables (0)Logging (0)LoRA Fine-Tuning and Inference (0)Machine Learning Specialization (0)Manage algorithms locally (0)Manage artifact data retention (0)Manage artifact storage and memory allocation (0)Manage costs effectively (0)Manage model configurations (0)Manage sweeps (0)Manage workspace, section, and panel settings (0)Managed Fine-Tuning Overview (0)Master Reranking with Cohere Models (0)MCP (0)MCP Apps (0)MCP Inspector (0)MCP Registry Aggregators (0)MCP Registry Supported Package Types (0)MCP Tools (0)Media panels (0)Meeting minutes (0)Microsoft Foundry (0)Migration Guide (0)Mistral (0)Mistral (0)Mistral (0)MistralAI (0)Mixed adapter types (0)Model configuration (0)Model Context Protocol (0)Model Context Protocol (MCP) (0)Model Context Protocol (MCP) (0)Model Context Protocol (MCP) (0)Model Context Protocol (MCP) and Weave (0)Model customization (0)Model Deprecations (0)Model Gallery (0)Model Lifecycle (0)Model merging (0)Model optimization (0)Model providers (0)Model selection (0)Model selection (0)Model Vault (0)Model weights (0)Models (0)Models (0)Models (0)Models (0)Models (0)Models (0)Models and providers (0)Models Benchmarks (0)Models Overview (0)Moderation (0)Morph (0)Move a run to a different project or team (0)NLP Course (0)Nomic (0)null (0)OAuth Client Credentials (0)Observability (0)Official MCP Registry Terms of Service (0)Ollama (0)Ollama (0)OpenAI (0)OpenAI (0)OpenAI API (0)OpenAI API Essentials (0)OpenAI Compatibility (0)OpenAI Fine-Tuning (0)OpenAI GPT-OSS Quickstart (0)OpenAI Gym (0)OpenAI models in Amazon Bedrock (0)OpenCLIP (0)OpenRouter (0)Organize runs (0)Organize versions with tags (0)Other resources (0)Outlines (0)Outscale (0)Overview (0)Overview (0)Overview (0)Overview (0)Overview (0)Overview (0)Overview (0)Pagination (0)Parallel coordinates (0)Parallelize agents (0)Parameter importance (0)Parameter Tuning (0)PEFT configurations and models (0)Perplexity (0)Pin and compare runs (0)Ping (0)Playground (0)Point aggregation (0)Practical Deep Learning for Coders (0)Predicted outputs (0)Predicted Outputs (0)Prefix (0)Pricing (0)Private Deployment – Setting Up (0)Private Deployment Overview (0)Private Deployment Usage (0)Progress (0)Projects (0)Prompt engineering (0)Prompt Engineering Across Providers (0)Prompting capabilities (0)Prompts (0)Publishing Remote Servers (0)Pydantic Model (0)PyTorch (0)PyTorch Geometric (0)PyTorch Ignite (0)PyTorch Lightning (0)Pytorch torchtune (0)Quantization (0)Quickstart (0)Quickstart: Flux Kontext (0)Quickstart: FLUX.2 (0)Quickstart: How to do OCR (0)Quickstart: How to Use OpenClaw with Together AI (0)Quickstart: Publish an MCP Server to the MCP Registry (0)Quickstart: Using Hugging Face Inference With Together (0)Quickstart: Using Mastra with Together AI (0)Quickstart: Using Vercel AI SDK With Together AI (0)Quickstart: Wan 2.7 T2V (0)Rate limit and usage tiers (0)Reasoning (0)Reasoning (0)Reasoning (0)Reasoning best practices (0)Reasoning Capabilities (0)Reasoning Fine-tuning (0)Reasoning models (0)Reasoning Models Guide (0)Reasoning tokens (0)Reasoning tokens (0)Recommended Models (0)Reference an artifact version with aliases (0)Reference overview (0)Regions (0)Reinforcement fine-tuning (0)Reinforcement fine-tuning use cases (0)Reinforcement Learning Course (0)Reproduce experiments (0)Reranking - Cohere on Azure AI Foundry (0)Reranking - quickstart (0)Resources (0)Resume a run (0)Retrieval augmented generation (RAG) - Cohere on Azure AI Foundry (0)Retrieval augmented generation (RAG) - quickstart (0)Reward Modeling (0)Rewind a run (0)Roadmap (0)Roboflow (0)Roots (0)Run states (0)Safety Modes (0)Sampling (0)Sampling (0)Save and diff code (0)Scatter plots (0)Schema Reference (0)SDK Clients (0)SDK Tiering System (0)SDKs (0)Search runs (0)Secure Training (BYOB) (0)Security Best Practices (0)Self-deployment (0)Semantic run plot legends (0)Semantic search - Cohere on Azure AI Foundry (0)Semantic search - quickstart (0)Semantic Search with Cohere Models (0)Send an alert (0)Sentence Transformer (0)SEP Guidelines (0)SEP-1024: MCP Client Security Requirements for Local Server Installation (0)SEP-1024: MCP Client Security Requirements for Local Server Installation (0)SEP-1034: Support default values for all primitive types in elicitation schemas (0)SEP-1034: Support default values for all primitive types in elicitation schemas (0)SEP-1036: URL Mode Elicitation for secure out-of-band interactions (0)SEP-1036: URL Mode Elicitation for secure out-of-band interactions (0)SEP-1046: Support OAuth client credentials flow in authorization (0)SEP-1046: Support OAuth client credentials flow in authorization (0)SEP-1302: Formalize Working Groups and Interest Groups in MCP Governance (0)SEP-1302: Formalize Working Groups and Interest Groups in MCP Governance (0)SEP-1303: Input Validation Errors as Tool Execution Errors (0)SEP-1303: Input Validation Errors as Tool Execution Errors (0)SEP-1319: Decouple Request Payload from RPC Methods Definition (0)SEP-1319: Decouple Request Payload from RPC Methods Definition (0)SEP-1330: Elicitation Enum Schema Improvements and Standards Compliance (0)SEP-1330: Elicitation Enum Schema Improvements and Standards Compliance (0)SEP-1577: Sampling With Tools (0)SEP-1577: Sampling With Tools (0)SEP-1613: Establish JSON Schema 2020-12 as Default Dialect for MCP (0)SEP-1613: Establish JSON Schema 2020-12 as Default Dialect for MCP (0)SEP-1686: Tasks (0)SEP-1686: Tasks (0)SEP-1699: Support SSE polling via server-side disconnect (0)SEP-1699: Support SSE polling via server-side disconnect (0)SEP-1730: SDKs Tiering System (0)SEP-1730: SDKs Tiering System (0)SEP-1850: PR-Based SEP Workflow (0)SEP-1850: PR-Based SEP Workflow (0)SEP-1865: MCP Apps - Interactive User Interfaces for MCP (0)SEP-1865: MCP Apps - Interactive User Interfaces for MCP (0)SEP-2085: Governance Succession and Amendment Procedures (0)SEP-2085: Governance Succession and Amendment Procedures (0)SEP-2133: Extensions (0)SEP-2133: Extensions (0)SEP-2148: MCP Contributor Ladder (0)SEP-2149: MCP Group Governance and Charter Template (0)SEP-2207: OIDC-Flavored Refresh Token Guidance (0)SEP-2260: Require Server requests to be associated with a Client request. (0)SEP-414: Document OpenTelemetry Trace Context Propagation Conventions (0)SEP-414: Document OpenTelemetry Trace Context Propagation Conventions (0)SEP-932: Model Context Protocol Governance (0)SEP-932: Model Context Protocol Governance (0)SEP-973: Expose additional metadata for Implementations, Resources, Tools and Prompts (0)SEP-973: Expose additional metadata for Implementations, Resources, Tools and Prompts (0)SEP-985: Align OAuth 2.0 Protected Resource Metadata with RFC 9728 (0)SEP-985: Align OAuth 2.0 Protected Resource Metadata with RFC 9728 (0)SEP-986: Specify Format for Tool Names (0)SEP-986: Specify Format for Tool Names (0)SEP-990: Enable enterprise IdP policy controls during MCP OAuth flows (0)SEP-990: Enable enterprise IdP policy controls during MCP OAuth flows (0)SEP-991: Enable URL-based Client Registration using OAuth Client ID Metadata Documents (0)SEP-991: Enable URL-based Client Registration using OAuth Client ID Metadata Documents (0)SEP-994: Shared Communication Practices/Guidelines (0)SEP-994: Shared Communication Practices/Guidelines (0)Server Card Charter (0)Serverless Models (0)Serverless Overview (0)Serverless Pricing (0)Short-Term Memory Handling for Agents (0)Signal handling and sweep runs (0)Single-Turn Training Quickstart (0)Smolagents (0)Smooth line plots (0)Snowflake Cortex (0)Specification (0)Specification Enhancement Proposals (SEPs) (0)Specification Enhancement Proposals (SEPs) (0)Speculative Decoding (0)Start a sweep agent (0)Stop runs (0)Streaming API responses (0)Structured model outputs (0)Structured Output (0)Supervised Fine Tuning - Text (0)Supervised Fine Tuning - Vision (0)Supervised fine-tuning (0)Support (0)Support: Models (0)Supported Models (0)Supported Models (0)Sweep configuration options (0)Sweeps troubleshooting (0)Sweeps UI (0)Tasks (0)TensorFlow (0)TensorRT (0)Text & Vision Fine-tuning (0)Text and Chat Completions (0)Text Classification Using Embeddings (0)Text Embeddings (0)Text generation - Cohere on Azure AI Foundry (0)Text generation - quickstart (0)Text Generation Inference (0)Text Models (0)Text2Vec (0)The MCP Registry (0)The MCP Registry Moderation Policy (0)Together AI (0)Together AI (0)Together's IAM Model (0)Tokenization (0)Tool Calling (0)Tool use & agents - Cohere on Azure AI Foundry (0)Tool use & agents - quickstart (0)Tools (0)Topic Modeling System for AI Papers (0)Trace grading (0)Trace Mistral applications (0)Track application versions with models (0)Track CSV files with experiments (0)Track external files (0)Track Jupyter notebooks (0)Training Shapes (0)Transports (0)Triggers and Events Charter (0)Tutorial: App versioning (0)Tutorial: Create sweep job from project (0)Tutorial: Create, track, and use a dataset artifact (0)Tutorial: Define, initialize, and run a sweep (0)Tutorial: Log tables, visualize and query data (0)Tutorial: Use custom charts (0)UI Guide (0)Understanding Authorization in MCP (0)Understanding MCP clients (0)Understanding MCP servers (0)Unit testing (0)Unit testing (0)Update an artifact (0)Upgrading to GPT-5.4 (0)Upgrading to GPT-5.5 (0)Upload a Model (0)Upload via REST API (0)Usage Limits & Analytics (0)Usage Policy (0)Use an Assistant MCP server (0)Use environment variables for model providers (0)Use model after training (0)Use Serverless LoRA Inference (0)Use W&B Skills (0)Use Weave with W&B Models (0)Use Weave with W&B training runs (0)Use your trained models (0)Using Cohere models via the OpenAI SDK (0)Using Cohere's Models to Work with Image Inputs (0)Using GPT-5.2 (0)Using realtime models (0)Verifiers (0)Versioning (0)Versioning Published MCP Servers (0)Vertex AI (0)Vertex AI hosted (0)Video & Audio Inputs (0)Video Generation with Wan 2.1 (0)View a specific run in a project (0)View an automation's history (0)View experiments results (0)View runs in a project (0)Vision (0)Vision & Multimodal AI (0)Vision fine-tuning (0)Vision Inputs (0)Vision LLMs (0)Vision Models (0)Vision-Language Fine-tuning (0)Visualize and analyze tables (0)Visualize CoreWeave infrastructure alerts (0)Visualize sweep results (0)vLLM (0)vLLM (0)VoyageAI (0)W&B Mobile App (iOS) (0)W&B Models (0)W&B Quickstart (0)Warm Start from Fine-Tuned Models (0)Websearch (0)What is the Model Context Protocol (MCP)? (0)What Product Managers Need to Know About LLMs (0)Whats New Claude 4 6 (0)Which model should I use? (0)Working and Interest Groups (0)Working with evals (0)Working With Messages (0)Workspace setup (0)Workspace setup (0)Workspaces (0)xAI (0)XGBoost (0)YOLOv5 (0)YOLOX (0)