nœuds / builtin / ai / aidependencies / llm
Chat Google
Connect a Google Gemini chat model to AI nodes.
Ce contenu n’est pas encore disponible dans votre langue.
Give an AI node access to Google’s Gemini models, through Google AI Studio or Vertex AI.
What it does
Section titled “What it does”Chat Google is a model you plug into the Model slot of an AI node, such as the Tools Agent or Basic LLM Chain. It does not run on its own and has no output. When the AI node runs, it sends its messages to Google with your key and gets the reply back.
- Platform Type picks the service:
gaiis Google AI Studio (the Gemini API),gcpis Vertex AI on Google Cloud. Empty meansgai. - Temperature is 0 when you leave it empty, so answers are focused and repeatable.
- Replies are capped at Max Tokens (4096 by default). A failed request is retried up to Max Retries times (2 by default).
When to use it
Section titled “When to use it”- You want a Gemini model, for example for long documents.
- You have a free or paid Google AI Studio key and want to start quickly.
- Your company runs Gemini on Google Cloud: choose
gcp.
Inputs and settings
Section titled “Inputs and settings”| Réglage | Type | Ce que cela fait |
|---|---|---|
| Model (obligatoire) | Text | The model to use. |
| Authentication (obligatoire) | Credential | Use a JWT Token. |
| Platform Type | Choice | Which Google platform serves the model. Options: Google AI Studio (Gemini API), Google Cloud (Vertex AI). |
| Options | Group | The options to use with the model. |
| Options › Temperature | Number | The temperature to use for the model. |
| Options › Max Retries | Number | The maximum number of retries to use for the model. Par défaut : 2 |
| Options › Max Tokens | Number | The most tokens the model may generate in one reply. Defaults to 4096, which keeps providers from reserving credit for the whole output window. Par défaut : 4096 |
Type the Model id as Google names it in its model list (a gemini-... id). Leave Platform Type empty or on gai for an AI Studio key; choose gcp only for a Vertex AI key.
Outputs
Section titled “Outputs”This node has no output port. It plugs into a slot on another node instead of passing items along.
- Model slot of Tools Agent, Q&A Agent, RAG Agent, Basic LLM Chain, Indexer, Text Classifier, Sentiment Analysis, Summarization, Information Extractor, Guardrails, Auto-fixing Output Parser
The AI node you connect it to produces the output. Chat Google only decides which model answers.
Dependencies and credentials
Section titled “Dependencies and credentials”- Authentication (connection): required. See Connect Google.
In Authentication, save your Google API key (a Bearer Token or JWT Token credential both work; put only the key in it). See Create a credential.
- For Google AI Studio (
gai), create the key at aistudio.google.com/app/apikey. - For Vertex AI (
gcp), create it in the Google Cloud Console, at console.cloud.google.com/vertex-ai/studio/api-key.
Example workflow
Section titled “Example workflow”- A Context Menu trigger on the page.
- Get All Text with Output field name
pageText. - Basic LLM Chain with Prompt
List the 5 key points of this article: {{ $input.pageText }}. - Chat Google in its Model slot, with a Gemini model id and Platform Type
gai.
Common issues
Section titled “Common issues”- “Model parameter is required and cannot be empty”. Fill in Model.
- An “API key not valid” or permission error. The key does not match Platform Type: an AI Studio key needs
gai, a Vertex AI key needsgcp. Or the key was deleted; create a new one. - A “model not found” error. The model id is misspelled or not available on that platform. Copy it from Google’s model list.
- The answer stops mid-sentence. It hit Max Tokens. Raise it under Options.
Related nodes
Section titled “Related nodes”- Google Embeddings: Gemini vectors for a knowledge base.
- Chrome AI: Gemini Nano, built into Chrome, no key.
- Basic LLM Chain: send one prompt and get a reply.
- Tools Agent: an agent that can use tools and memory.