Skip to main content
Version: 2.0

Developer quickstart

Build your first RAG application with Vectara in 5 minutes. You'll upload a d ocument, query it, and get AI-generated answers with citations.

Before you begin, you need:

  • A Vectara account (sign up free - 30-day trial)
  • An API key (created in step 1)

What you will build​

Follow this workflow to create your first RAG application:

Step 1: Get your API key​

  1. Log in to the Vectara Console.
  2. Navigate to Authorization, API Keys.
  3. Copy your Personal API key.

Set the API key as an environment variable:

export VECTARA_API_KEY="your_api_key_here"
caution

Keep your API key secure. Don't commit it to version control or share it publicly.

Step 2: Create a corpus​

A corpus is a container for your documents. Create one with a single API call:

CREATE CORPUS

Code example with bash syntax.
1

Expected response:

RESPONSE

Code example with json syntax.
1

You now have a corpus ready to store documents.

Step 3: Upload a document​

Upload your first document. We'll create a simple structured document:

UPLOAD DOCUMENT

Code example with bash syntax.
1

Expected response:

RESPONSE

Code example with json syntax.
1

Your document is now indexed and searchable.

Upload files instead

You can also upload files directly (PDF, Word, PowerPoint, etc.) without structuring them:

curl -X POST https://api.vectara.io/v2/corpora/quickstart-corpus/upload \
  -H "x-api-key: $VECTARA_API_KEY" \
  -F "file=@document.pdf"

Learn more about file uploads →

Step 4: Query your data​

Now query your document and get an AI-generated answer with citations:

QUERY WITH RAG

Code example with bash syntax.
1

Response:

RESPONSE WITH CITATIONS

Code example with json syntax.
1

Notice:

  • Citations ([1], [2]) link answers to source documents
  • Search results show the matched text snippets
  • Factual consistency score (0.95) indicates high accuracy

Done! You just built a working RAG application in 4 API calls.

What you just built​

In less than 5 minutes, you:

  1. Created a corpus to store documents
  2. Indexed a document with searchable text
  3. Queried your data with natural language
  4. Got an AI-generated answer with citations

This is the foundation of every Vectara application, from simple Q&A to complex AI agents.

Next steps​

Upload real documents​

Upload a PDF, Word doc, or text file:

UPLOAD A FILE

Code example with bash syntax.
1

Learn more:

Build with agents​

Transform your RAG application into an intelligent agent:

CREATE AN AGENT

Code example with bash syntax.
1

Learn more:

Improve search quality​

Add a reranker to improve relevance:

QUERY WITH RERANKER

Code example with bash syntax.
1

Learn more:

Full example script​

Copy this complete script to test everything at once:

COMPLETE QUICKSTART SCRIPT

Code example with bash syntax.
1

Save as vectara-quickstart.sh, make it executable with chmod +x vectara-quickstart.sh, and run it!

Want more examples? See API Recipes.