Integrations: Chat Models

In LangChainGo every provider implements the same llms.Model interface, so a "chat model" is just a provider used with GenerateContent and chat messages. Construction is provider-specific; the calling code is identical.

Providers

Provider	Package	Constructor
OpenAI	llms/openai	openai.New()
Anthropic	llms/anthropic	anthropic.New()
Google Gemini	llms/googleai	googleai.New(ctx)
Vertex AI	llms/googleai/vertex	vertex.New(ctx)
AWS Bedrock	llms/bedrock	bedrock.New()
Mistral	llms/mistral	mistral.New()
Ollama	llms/ollama	ollama.New()
Hugging Face	llms/huggingface	huggingface.New()

OpenAI-compatible endpoints (Groq, DeepSeek, OpenRouter, NVIDIA, Ollama Cloud, …) use the llms/openai package with openai.WithBaseURL(...). See the per-provider pages under LLM Integrations for details.

Sending chat messages

import (
    "github.com/vxcontrol/langchaingo/llms"
    "github.com/vxcontrol/langchaingo/llms/openai"
)

llm, err := openai.New()

messages := []llms.MessageContent{
    llms.TextParts(llms.ChatMessageTypeSystem, "You are a helpful assistant."),
    llms.TextParts(llms.ChatMessageTypeHuman, "Hello!"),
}

resp, err := llm.GenerateContent(ctx, messages)
fmt.Println(resp.Choices[0].Content)

For detailed configuration options for each provider, see the Configure LLM Providers guide.