Ide01 Intro Basics (0)02 Prepare Dataset (0)A Guide to Tokens and Tokenizers (0)A2A vs MCP (0)Access the W&B MCP Server (0)Access your invoices (0)Access your invoices (0)Account quotas (0)Actions in ChatKit (0)Adapter injection (0)Adapters (0)Advanced integrations with ChatKit (0)Advanced usage (0)Agent Client Protocol (ACP) (0)Agent Client Protocol (ACP) (0)Agent evals (0)Agent identity (0)Agent Skills (0)Agentic IDEs and CLIs (0)Agentic Memory (0)Agentic Search (0)Agents (0)Agents SDK (0)Agno (0)AI Evaluations UI (0)Ambassador (0)An Amazon SageMaker Setup Guide (0)Anthropic (0)Anthropic Api (0)Apify Actors (0)Apply patch (0)Architecture (0)Assistants API deep dive (0)Assistants migration guide (0)Audio and speech (0)Audit & Access Logs (0)AutoGen (0)Automate workflows with hooks (0)Automatically track function calls using Ops (0)Awesome A2A (0)AWS (0)AWS Private Deployment Guide (EC2 and EKS) (0)Azure (0)Azure OpenAI Setup (0)Back up a pod-based index (0)Back up an index (0)Background mode (0)Backups overview (0)Basic RAG (0)Batch API (0)Bedrock (0)Bring your own cloud (BYOC) (0)Build an MCP App (0)Build Chatbots with MongoDB and Cohere (0)Build Crew (0)Build with Agent Skills (0)Build Your First Crew (0)Build Your First Flow (0)Building with AI (0)Call schema reference (0)Cerebras (0)Change your payment method (0)Change your payment method (0)Chat Prefix Completion (0)Chat through the OpenAI-compatible interface (0)Chat through the standard interface (0)ChatGPT Developer mode (0)ChatKit (0)ChatKit widgets (0)Check data freshness (0)Choose a pod type and size (0)Chroma and Cohere (Integration Guide) (0)Chroma's Thin-Client (0)Chunking (0)CI/CD with Pinecone Local and GitHub Actions (0)Citation Formatting (0)Citations and References (0)Citations for tool use (function calling) (0)Claude Agent SDK (0)Claude Code Mastery (0)Claude Code overview (0)Client-side performance optimization (0)Code generation (0)Code Interpreter (0)Coding (0)Coding Tools (0)Cohere (0)Cohere and LangChain (Integration Guide) (0)Cohere Chat on LangChain (Integration Guide) (0)Cohere Embed on LangChain (Integration Guide) (0)Cohere Labs Acceptable Use Policy (0)Cohere Models on Amazon Bedrock (0)Cohere Rerank on LangChain (Integration Guide) (0)Cohere Tools on LangChain (Integration Guide) (0)Cohere's Command R Model (0)Collect and track datasets (0)Collect feedback and use annotations (0)Combined API docs (0)Command R and Command R+ Model Card (0)Common workflows (0)Compaction (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 traces and other logged information (0)Comparison Testing (0)Completions API (0)Completions API (0)Components Guide (0)Composio Tool (0)Concepts (0)Configure audit logs (0)Configure audit logs (0)Configure customer-managed encryption keys (0)Configure Private Endpoints for AWS PrivateLink (0)Configure SSO with Okta (0)Configure SSO with Okta (0)Configure Weave environment variables (0)Connect an authentication provider (0)Connect to an OpenAI compliant model provider/proxy (0)Connect to any LLM (0)Connectors and MCP servers (0)Content Moderation (0)Context snippets overview (0)Contribute (0)Contribute to PEFT (0)Control automatic LLM call tracking (0)Conversation state (0)Cookbooks (0)Crafting Effective Agents (0)Create a pod-based index (0)Create a project (0)Create a project (0)Create an assistant (0)Create an index (0)Create and manage saved views (0)Create Custom Tools (0)Create dynamic Leaderboards in Evaluations (0)Creating a client (0)CrewAI (0)Custom MCP Servers (0)Custom model providers (0)Custom model providers (0)Custom models (0)Customize Agents (0)Customizing Prompts (0)Cybersecurity checks (0)Data deletion on Pinecone (0)Data ingestion overview (0)Data modeling (0)Data Residency (0)Data Security (0)Debugging (0)Debugging (0)Decrease latency (0)Dedicated Read Nodes (0)Define and log attributes (0)Delete records (0)Delete source (0)Deploy Finetuned Command Models from AWS Marketplace (0)Deploy to AMP (0)Deploying Dedicated Endpoints (0)Deployments (0)DeploymentSampler (0)Design Principles (0)Direct preference optimization (0)Directory Read (0)Disable tracing (0)Distributed/Cloud Performance (0)Docker (0)Downgrade your plan (0)Downgrade your plan (0)Download a usage report (0)Download a usage report (0)download the validation and reformat script (0)DSPy (0)Elasticsearch and Cohere (Integration Guide) (0)Embeddings & Reranking (0)Enable Crew Studio (0)End-to-end example of RAG with Chat, Embed, and Rerank (0)Enterprise-Managed Authorization (0)Error codes (0)Error handling (0)Evaluate answers (0)Evaluate external models (0)Evaluate using local scorers (0)Evaluation (0)Evaluation overview (0)Evaluations overview (0)Export evaluation data (0)Fetch records (0)File inputs (0)Files (0)Files in Pinecone Assistant (0)Filter by metadata (0)Fim Completion (0)Find and customize a run's ID or name (0)Fine-tuning (0)Fine-tuning Guide (0)Fingerprinting (0)Fireworks Agent: Supervised Fine-Tuning (0)Flex processing (0)from_provider (0)Frontend prompt instructions (0)Fueling Generative Content with Keyword Research (0)Full-text search (0)Function calling (0)GCP (0)General (0)Generate dense embeddings (0)Generate sparse embeddings (0)Get a handle to the Call object during execution (0)get data from hugging face (0)Get invocation (0)Get source (0)Get Started (0)Getting Started (0)Gmail Trigger (0)Google (0)Google Agent Development Kit (ADK) (0)Google Calendar Trigger (0)Google Drive Trigger (0)Google Slides Integration (0)Graders (0)Groq (0)Guardrails (0)Guides Ai Agent Evaluation (0)Guides Ai Agent Evaluation Metrics (0)Guides Answer Correctness Metric (0)Guides Building Custom Metrics (0)Guides Homepage (0)Guides Llm As A Judge (0)Guides Llm Observability (0)Guides Multi Turn Evaluation (0)Guides Multi Turn Evaluation Metrics (0)Guides Multi Turn Simulation (0)Guides Optimizing Hyperparameters (0)Guides Rag Evaluation (0)Guides Rag Triad (0)Guides Red Teaming (0)Guides Regression Testing In Cicd (0)Guides Tracing Ai Agents (0)Guides Tracing Multi Turn (0)Guides Tracing Rag (0)Guides Using Custom Embedding Models (0)Guides Using Custom Llms (0)Guides Using Synthesizer (0)Haystack and Cohere (Integration Guide) (0)Hierarchical Process (0)HITL Workflows (0)How To Build An Open Source NotebookLM: PDF To Podcast (0)How to upload experiments run outside of LangSmith with the REST API (0)HubSpot Trigger (0)Hugging Face Hub (0)Hybrid search (0)Hybrid Search with RRF (0)IA3 (0)IA3 (0)IBM watsonx.ai (0)Identity and access management (IAM) (0)Image generation (0)Image, Audio, Video & Document Input (0)Images and vision (0)Implement multitenancy (0)Import and export data (0)Import records (0)Increase search relevance (0)Increase throughput (0)Indexing overview (0)Inference Error Codes (0)Inference for RL Rollouts (0)Installation (0)Instructor (0)Integrate with Amazon S3 (0)Integrate with Azure Blob Storage (0)Integrate with Google Cloud Storage (0)Integrations (0)Intro to Retrieval (0)IP egress ranges (0)JetBrains IDEs (0)Json Mode (0)Kickoff Crew (0)Koog (0)Kv Cache (0)LangChain (0)LangChain v1 migration guide (0)LangChain v1 migration guide (0)LangGraph v1 migration guide (0)LangGraph v1 migration guide (0)Latency optimization (0)Learn (0)Learn (0)Lexical search (0)Link a W&B run to trace function calls (0)List record IDs (0)LiteLLM (0)LiteLLM integration (0)LlamaIndex (0)LLM gateway configuration (0)LLMs (0)Local development with Pinecone Local (0)Local shell (0)Log evaluation data from your code (0)Log media (0)Look at Your Data (0)LoRA methods (0)Manage a trace (0)Manage API keys (0)Manage API keys (0)Manage assistants (0)Manage cost (0)Manage files (0)Manage namespaces (0)Manage organization members (0)Manage organization members (0)Manage permissions in the OpenAI platform (0)Manage pod-based indexes (0)Manage project members (0)Manage project members (0)Manage projects (0)Manage projects (0)Manage serverless indexes (0)Manage service accounts at the organization-level (0)Manage service accounts at the organization-level (0)Manage service accounts at the project-level (0)Manage service accounts at the project-level (0)Manage storage integrations (0)Manage Weave Projects (0)Managing costs (0)Map columns in datasets (0)Mastering Flow State Management (0)MCP Apps (0)MCP Inspector (0)MCP Security Considerations (0)Microsoft Azure (0)Microsoft Foundry (0)Microsoft Teams Trigger (0)Migrate a pod-based index to serverless (0)Migrate from Agent Builder (0)Migrate from prompt objects (0)Migrate to the Responses API (0)Migration (0)Migration Guide (0)Migration Guide (0)Migration Guide (0)Migration Guide (0)Milvus and Cohere (Integration Guide) (0)MistralAI (0)Mixed adapter types (0)Model Context Protocol (MCP) and Weave (0)Model Gallery (0)Model merging (0)Model optimization (0)Model providers (0)Model selection (0)Model Vault (0)Model weights (0)MongoDB and Cohere (Integration Guide) (0)Monitor performance (0)Monitor usage and cost (0)Monitor usage and costs (0)Moving from LangGraph to CrewAI: A Practical Guide for Engineers (0)Multi Round Chat (0)Multi-modal Messages (0)Multimodal context for assistants (0)Navigate the Weave Trace view (0)Node reference (0)null (0)NVIDIA NIM (0)Observability (0)Observability (0)OneDrive Trigger (0)Open Search and Cohere (Integration Guide) (0)Open Telemetry Logs (0)OpenAI (0)OpenAI Agents SDK (0)OpenAI models in Amazon Bedrock (0)OpenAI Realtime API (0)OpenRouter (0)Optimize your terminal setup (0)Optimizing LLM Accuracy (0)Organizations overview (0)Orthogonal Finetuning (OFT and BOFT) (0)Other resources (0)Outlook Trigger (0)Overview (0)Overview (0)Parameter types for tool use (function calling) (0)Part 1. Intro to streaming (0)Part 2. Sending messages (0)Part 3. Event handling (0)Part 4. Run configuration (0)Part 5. Audio, Images, and Video (0)PEFT checkpoint format (0)Performance (0)Pinecone and Cohere (Integration Guide) (0)Pinecone Assistant (0)Pinecone Assistant: n8n quickstart (0)Pinecone Assistant: SDK quickstart (0)Pinecone documentation (0)Platforms and integrations (0)Playground (0)Predicted Outputs (0)Prefix (0)Prepare for Deployment (0)Pricing and limits (0)Priority processing (0)Private Deployment Overview (0)Private Package Registries (0)Processes (0)Production checklist (0)Production notes on GPT Actions (0)Projects overview (0)Prompt caching (0)Prompt caching (0)Prompt engineering (0)Prompt generation (0)Prompt guidance for GPT-5.4 (0)Prompt optimizer (0)Prompt template format guide (0)Prompt-based methods (0)Prompting capabilities (0)Publish Custom Tools (0)PydanticAI (0)Python Guide (0)Python v2 SDK Migration Guide (0)Qdrant and Cohere (Integration Guide) (0)Quantization (0)Query and export Calls (0)Quickstart (0)Quickstart (0)Quickstart: How to do OCR (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)RAG Citations (0)RAG Streaming (0)Rate limits (0)React Component Export (0)Realtime API (0)Realtime API with MCP (0)Realtime API with SIP (0)Realtime API with WebRTC (0)Realtime API with WebSocket (0)Realtime conversations (0)Realtime guide (0)Realtime transcription (0)Realtime translation (0)Realtime transport (0)Reasoning (0)Reasoning Capabilities (0)Reasoning models (0)Reasoning Models Guide (0)Redact PII from traces (0)Redis and Cohere (Integration Guide) (0)Reliability and Error Handling (0)Repository on GitHub (0)Rerank results (0)Reranking - Cohere on Azure AI Foundry (0)Reranking - quickstart (0)Responses API (0)Restore a pod-based index (0)Restore an index (0)Retrieval (0)Retrieval Augmented Generation (RAG) (0)Retrieval augmented generation (RAG) - Cohere on Azure AI Foundry (0)Retrieval augmented generation (RAG) - quickstart (0)Retrieve context snippets (0)Review items in an annotation queue (0)Running Chroma in Client-Server Mode (0)Salesforce Trigger (0)Sample Methods (0)Sampling (0)Sandbox (0)Sandbox (0)Sandboxing (0)Scale pod-based indexes (0)Scoring Overview (0)Search (0)Search or list items within a namespace prefix. (0)Search overview (0)Secure MCP Tunnel (0)Security Best Practices (0)Security overview (0)Security overview (0)Semantic search (0)Semantic search - Cohere on Azure AI Foundry (0)Semantic search - quickstart (0)Send OpenTelemetry Traces to Weave (0)SEP Guidelines (0)SEP-1699: Support SSE polling via server-side disconnect (0)SEP-1699: Support SSE polling via server-side disconnect (0)SEP-994: Shared Communication Practices/Guidelines (0)SEP-994: Shared Communication Practices/Guidelines (0)Sequential Processes (0)Set Call display name (0)Set up a self-managed W&B Weave instance (0)Set up annotation queues (0)Set up automations (0)Set up guardrails (0)Set up monitors (0)Set up the LLM auth proxy (0)Shell (0)Single-Node Performance (0)Skills (0)Skills Guide (0)Slack Trigger (0)Smolagents (0)Soft prompts (0)Speech to text (0)Spider Scraper (0)Standard trial (0)Store and track versions of prompts (0)Store and track versions of prompts (0)Strategic LLM Selection Guide (0)Streaming API responses (0)Streaming for tool use (function calling) (0)Structured model outputs (0)Target an index (0)Tasks (0)Team Management (0)TensorRT (0)Test Pinecone at scale (0)Text generation (0)Text generation - Cohere on Azure AI Foundry (0)Text generation - quickstart (0)Text Models (0)Text to speech (0)The Cohere Datasets API (and How to Use It) (0)Theming and customization in ChatKit (0)Thinking Mode (0)Thinking Mode Api Example Non Streaming (0)Thinking Mode Api Example Streaming (0)Together AI (0)Together AI Skills (0)Together's IAM Model (0)Tokenization (0)Tool Calling (0)Tool Calls (0)Tool integrations (0)Tool integrations (0)Tool Repository (0)Tool search (0)Tool use & agents - Cohere on Azure AI Foundry (0)Tool use & agents - quickstart (0)torch.compile (0)Trace generator functions (0)Trace grading (0)Trace your code (0)Tracing Basics (0)Track and version objects (0)Track application versions with models (0)Track costs (0)Track threads (0)Training Guide: UI (0)Triggers Overview (0)Troubleshoot Weave issues (0)Troubleshooting (0)TypeScript Guide (0)TypeScript SDK: Third-Party Integration Guide (0)UI Guide (0)Under 18 API Guidance (0)Understanding A2A (0)Understanding collections (0)Understanding cost (0)Understanding LoRA performance (0)Understanding organizations (0)Understanding pod-based indexes (0)Understanding projects (0)Update an artifact (0)Update and delete Calls (0)Update Crew (0)Update records (0)Update W&B license and version (0)Upgrade your plan (0)Upgrade your plan (0)Upgrading to GPT-5.4 (0)Upgrading to GPT-5.5 (0)Upload files (0)Upsert records (0)Usage patterns for tool use (function calling) (0)Use an Assistant MCP server (0)Use builtin scorers (0)Use Claude Code in VS Code (0)Use environment variables for model providers (0)Use federated identities with SDK (0)Use server-side caching (0)Use the Pinecone MCP server (0)Use the Playground to experiment with prompts (0)Use trace plots (0)Use Weave with W&B training runs (0)Using Cohere models via the OpenAI SDK (0)Using CrewAI Without LiteLLM (0)Using GPT-5.2 (0)Using predicted outputs (0)Vector embeddings (0)Verdict (0)Verifiers (0)Vespa and Cohere (Integration Guide) (0)Video & Audio Inputs (0)Video Generation (0)Video generation with Sora (0)Video Generation with Wan 2.1 (0)View and customize trace display (0)Vision fine-tuning (0)Vision Models (0)Voice activity detection (VAD) (0)Voice agents (0)Weaviate and Cohere (Integration Guide) (0)Webhook Automation (0)Webhooks (0)Webhooks and server-side controls (0)WebSocket Mode (0)Week 14 · March 30 – April 3, 2026 (0)Welcome to LLM University! (0)Where Filters (0)Which model should I use? (0)YouTube Video RAG Search (0)Zapier Trigger (0)Zero Data Retention (0)Zilliz and Cohere (Integration Guide) (0)