Travel Planning Agent with Couchbase Vector Search, Gemini 2.0 Flash and OpenAI

## AI Travel Agent Powered by Couchbase.

### You will need to:
1. Setup your Google API Credentials for the Gemini LLM
2. Setup your OpenAI Credentials for the OpenAI embedding nodes.
3. Create a Couchbase cluster (using [Couchbase Capella](https://cloud.couchbase.com/) in the cloud, or Couchbase Server)
4. Add [Database credentials](https://docs.couchbase.com/cloud/clusters/manage-database-users.html#create-database-credentials) with appropriate permissions for the operations you want to perform
5. Configure [Allowed IP addresses](https://docs.couchbase.com/cloud/clusters/allow-ip-address.html) for your n8n instance. Use `0.0.0.0/0` for easier testing.
6. Create a bucket, scope, and collection. We recommend the following:
   - Bucket: `travel-agent`
   - Scope: `vectors`
   - Collection: `points-of-interest`
7. Navigate to the Data Tools, click the Search tab, and click Import Search Index. Upload the following JSON file found [here](https://gist.github.com/ejscribner/6f16343d4b44b1af31e8f344557814b0).


Once all of that is configured you will need to send the loading webhook with some data points (see example).

This should create vectorized data in  `points-of-interest` collection.

Once you have data points there try to ask the Agent questions about the data points and test the response. Eg. "Where should I go for a romantic getaway?"