Conversational search Conversation history RAG Prerequisites Using conversational search Step 1: Create a connector to a model Step 2: Register and deploy the model Step 3: Cr...

Expose and graph Kong AI Metrics Overview Grafana dashboard Available metrics Accessing the metrics Expose and graph Kong AI Metrics This guide walks you through collecting...

LMStudio LLM Connecting to LMStudio LMStudio LLM LMStudio (opens in a new tab) is a popular user-interface, API, and LLM engine that allows you to download any GGUF model fr...

Retrieval-augmented generation processor Request fields Context field list Example Creating a search pipeline Using a search pipeline Retrieval-augmented generation process...

FAQ Questions Common issues FAQ Below is a list of frequently asked questions and common issues encountered. Questions Question What models are recommended? Answer S...

Upstream formats Raw format Ollama format OpenAI format Using the plugin with Llama2 Prerequisites Provider configuration Set up route and plugin Test the configuration T...

Anthropic LLM Connecting to Anthropic Anthropic LLM Anthropic (opens in a new tab) is a model provider popular for hosting models like Claude-3 that boast much larger contex...

Cohere LLM Connecting to Cohere Cohere LLM Cohere (opens in a new tab) provides industry-leading large language models (LLMs) and RAG capabilities tailored to meet the needs...

Embedded Chat Widgets Configuration Options Workspace Allowed Chat Method Restrict Requests from Domains Max Chats per Day Max Chats per Session Enable Dynamic Model Use Enab...

Mistral AI LLM Connecting to Mistral AI Mistral AI LLM Mistral AI (opens in a new tab) is the creator of the popular, uncensored, open-source Mistral-7B model. They provid...