Overview
This node integrates with Yandex's GPT language models to generate text completions based on input prompts. It is designed for scenarios where users want to leverage Yandex Foundation Models for natural language processing tasks such as content generation, summarization, question answering, or conversational AI.
Typical use cases include:
- Generating creative or analytical text completions.
- Building chatbots or virtual assistants using Yandex GPT models.
- Automating content creation workflows with configurable model parameters.
The node allows selecting a specific Yandex GPT model either by providing a direct URI or choosing from a searchable list of available models. Users can customize generation behavior through options like temperature and maximum token count.
Properties
| Name | Meaning |
|---|---|
| Model | The Yandex GPT model used to generate the completion. Can be specified as a URI (e.g., gpt://<folder_id>/yandexgpt-lite/latest) or selected from a searchable list of available models. See Yandex Foundation Models documentation for details. |
| Options | Additional generation parameters: - Temperature: Controls randomness in the output, ranging from 0 (more deterministic) to 1 (more creative). - Max Tokens: Maximum number of tokens to generate in one completion. Must be > 0 and may depend on the chosen model. |
Output
The node outputs a JSON object containing the generated text completion from the selected Yandex GPT model. The output field is named "json" under the output named "Model". This output represents the AI-generated language model response.
No binary data output is produced by this node.
Dependencies
- Requires an API key credential for authenticating with Yandex Cloud's GPT service.
- The node depends on the
@langchain/yandex/chat_modelspackage for interfacing with Yandex GPT models. - Network access to Yandex Cloud APIs is necessary.
- Proper configuration of the API key and folder ID (used in model URIs) is required.
Troubleshooting
- Invalid URI error: If the model URI does not match the expected pattern (
^(gpt|ds)://(.+)/(.+)), the node will reject it. Ensure the URI format is correct, including protocol, folder ID, and model name. - Authentication failures: Verify that the provided API key credential is valid and has permissions to access the specified Yandex GPT models.
- Token limit errors: Setting
maxTokenstoo high may cause errors depending on the model limits. Adjust this value according to the model's documented constraints. - Empty or unexpected responses: Check that the model parameter is correctly set and that network connectivity to Yandex Cloud is stable.