Couchbase's Coding Assistant Goes GA |
Written by Nikos Vaggalis | |||
Monday, 11 March 2024 | |||
Capella iQ, the AI coding assistant for developers that makes interacting with Couchbase using natural language possible, has gone from private beta to being generally available. Couchbase is getting pumped with AI, sticking to the Couchbase is adding support for vector search across its entire product line including Capella, Enterprise Server, and Mobile. Support has also been added for retrieval-augmented generation (RAG) techniques through large language models (LLMs) via LangChain and LlamaIndex interfaces On top of that it also added an AI coding assistant called iQ on its managed service NoSQL database, Capella. As of last September 2023 and in Couchbase Adds AI To Capella the assistant was in private beta and not much information on its capabilities had been disclosed. Capella iQ is an AI cloud service that developers can interact with using natural language conversations. It can suggest common prompts, and it knows Couchbase-specific context such as database, collection, and index definitions. iQ is powered by ChatGPT, and will soon let the developer pick the LLM. Come to this January and we finally found out what it is capable of, since it went out of beta to being generally available. So Capella iQ speeds up a variety of common tasks to accelerate the development cycle in natural language. Some examples are:
A quick official demo goes through populating a wine store database utilizing English and abstractions which iQ understands, turns into SQL and finally populates the database. Then you can start asking questions on your tables like "create a query to show all data from Modavi" etc. That's not all though;iQ can also make suggestions such as to create an index for faster retrievals. As such, in the Capella workbench you'll find tools like query, index advisor, query path explanation, and visual profiling to complete the workflow from question to SQL optimization. The important thing here is that iQ in contrast to third party LLMs is that it understands your given schema, whereas the rest are too generic. Well not all of them. As we've found out it in Query Your Database In Natural Language With Vanna, Vanna is a framework with which you can talk to your database in plain English that is actually trained on your data/schema : For Vanna's LLM to work its magic, it first needs to be trained. To do that you can feed it pre-made SQL queries, database schemas or even your database's documentation so that it can become familiar with the data. For instance to train with DDL Statements, which contain information about the table names, columns, data types, and relationships you do: vn. train(ddl=""" Of course, it goes without saying that if you're using Couchbase, it's own solution will be much easier to make use of than to integrate a third party solution like Vanna. But mileage varies. Talking about integration another boon is that developers can use Capella iQ within the Query Workbench in the Capella UI and within VS Code and JetBrains IDEs as plugins available from the respective market places. This integration also allows data from the queries to be visualized as JSON docs, tables, and charts. So there you have it, GenAI for SQL too to make it easier and more productive when working with your database in extracting business value out of your data silos. More InformationCouchbase Capella iQ is Now Generally Available
Related ArticlesQuery Your Database In Natural Language With Vanna
To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.
Comments
or email your comment to: comments@i-programmer.info |
|||
Last Updated ( Monday, 11 March 2024 ) |