Connects to LangChain for advanced language model interactions. Provides seamless access to local and remote AI models with configurable parameters and system prompts. Ideal for natural language processing, AI-powered conversations, and intelligent content generation workflows.
| Name: | langchain |
| Class: | covia.adapter.LangChainAdapter |
This adapter provides 40 MCP tool(s) for AI agent integration:
| Tool Name | Description |
|---|---|
| langchain_anthropic | Model preset for claude-opus-5 through the anthropic provider operation. |
| langchain_anthropic | Model preset for claude-sonnet-5 through the anthropic provider operation. |
| langchain_anthropic | Model preset for claude-fable-5 through the anthropic provider operation. |
| langchain_openrouter | Model preset for openai/gpt-5.4-mini through the openrouter provider operation. |
| langchain_mistral | Model preset for mistral-large-latest through the mistral provider operation. |
| langchain_openrouter | Model preset for openrouter/auto through the openrouter provider operation. |
| langchain_gemini | Chat with current Gemini models through Google's OpenAI-compatible endpoint. |
| langchain_gemini | Model preset for gemini-3.5-flash-lite through the gemini provider operation. |
| langchain_deepseek | Chat with DeepSeek V4 through its OpenAI-compatible endpoint. V4 Flash is the balanced/economical default; V4 Pro targets harder work. |
| langchain_openai | Model preset for gpt-5.6-sol through the openai provider operation. |
| langchain_mistral | Model preset for codestral-latest through the mistral provider operation. |
| langchain_deepseek | Model preset for deepseek-v4-flash through the deepseek provider operation. |
| langchain_ollama | Example operation that chats with a local Ollama-served LLM via LangChainAdapter |
| langchain_xai | Chat with current xAI Grok models via the OpenAI-compatible xAI API. Grok 4.3 is the balanced default, 4.5 targets highest-quality work, and Grok Build is coding-specific. |
| langchain_openrouter | Model preset for google/gemini-3.5-flash through the openrouter provider operation. |
| langchain_gemini | Model preset for gemini-3.6-flash through the gemini provider operation. |
| langchain_openrouter | Model preset for anthropic/claude-sonnet-5 through the openrouter provider operation. |
| langchain_mistral | Model preset for mistral-small-latest through the mistral provider operation. |
| langchain_xai | Model preset for grok-4.5 through the xai provider operation. |
| langchain_openai | Model preset for gpt-5.4-nano through the openai provider operation. |
| llm_models | Discover model operations from v/models/, grouped by serving provider, with CALLER-RELATIVE readiness. Returns provider defaults and recommendations as catalog paths, compatible model-id lists, and detailed operation entries. Hosted readiness means YOUR secret store or the venue environment supplies the conventional key (never returned); Ollama readiness is live reachability. |
| langchain_gemini | Model preset for gemini-3.5-flash through the gemini provider operation. |
| langchain_openrouter | Chat with any model behind OpenRouter's OpenAI-compatible endpoint — one API key, many vendors. Model ids are vendor-prefixed (anthropic/…, openai/…, google/…, deepseek/…, mistralai/…); openrouter/auto (the default) lets the router choose. Any OpenRouter model id is accepted, not only the advertised list. |
| langchain_ollama | Model preset for qwen through the ollama provider operation. |
| langchain_openrouter | Model preset for deepseek/deepseek-v4-flash through the openrouter provider operation. |
| langchain_deepseek | Model preset for deepseek-v4-pro through the deepseek provider operation. |
| langchain_ollama_qwen3 | This is an example operation that gets a response from the Qwen3 LLM via ollama |
| langchain_anthropic | Model preset for claude-haiku-4-5-20251001 through the anthropic provider operation. |
| langchain_xai | Model preset for grok-build-0.1 through the xai provider operation. |
| langchain_mistral | Model preset for ministral-8b-latest through the mistral provider operation. |
| langchain_anthropic | Chat with Anthropic Claude models using the native Anthropic API. API key resolution prefers the caller/public secret store (ANTHROPIC_API_KEY by default), then the venue process environment; override by passing apiKey explicitly or as 's/<SECRET_NAME>'. Supports system prompts, tools, and structured output. Prompt caching is on by default: tools, system prompt and the caller's cacheMarks are cache breakpoints; usage reports cacheRead and cacheWrite tokens. |
| langchain_openrouter | Model preset for mistralai/mistral-medium-latest through the openrouter provider operation. |
| langchain_mistral | Model preset for magistral-medium-latest through the mistral provider operation. |
| langchain_mistral | Chat with Mistral models through Mistral's OpenAI-compatible endpoint. mistral-medium-latest is the balanced default; mistral-large-latest for quality, mistral-small-latest for economy, codestral-latest for code, magistral-medium-latest for reasoning. The -latest aliases track Mistral's current release of each family. |
| langchain_xai | Model preset for grok-4.3 through the xai provider operation. |
| langchain_openai | Model preset for gpt-5.6-luna through the openai provider operation. |
| langchain_openai | Model preset for gpt-5.6-terra through the openai provider operation. |
| langchain_openai | Chat with an OpenAI-compatible LLM. Supports messages-based and prompt-based input. API key resolved from user's secret store (OPENAI_API_KEY by default). Compatible with OpenAI, DeepSeek, Gemini, and other OpenAI-compatible endpoints — set the url parameter to use a different provider. |
| langchain_openai | Model preset for gpt-5.4-mini through the openai provider operation. |
| langchain_mistral | Model preset for mistral-medium-latest through the mistral provider operation. |